Avid fans of Map Happenings may recall an article titled “ChatGPT (et al) for Geospatial. You Ain’t Seen Nothing… Yet.” That was 18 months ago, which is essentially an epoch in AI terms.

Given it’s been so long I decided it was high time to do a little digging and provide an update on where things stand. Has any progress been made?

If you read the article mentioned above you might remember that back in that infantile period ChatGPT not only failed miserably at basic directions, it couldn’t even do basic maths: ¹

Today, for mathematics at least, ChatGPT looks like it’s started to pay a little more attention at school:

But what about geography? Has ChatGPT — or any other so called ‘AI’ for that matter — had any schooling?

Lets Start with the Basics

For the following examples I used ChatGPT. I also tried using Claude: it produced similar results.

My first attempt to poke and prod was to determine if ChatGPT could figure out basic information about addresses and coordinates.

Ok, let’s plot that coordinate on a map:

Oh dear, ChatGPT seems to have the location in the middle of the freeway, about 3.3 miles away from the actual address:

If you read my last missive on the topic you may recall the attempt to use ChatGPT for directions: the result was a hilarious hallucination, resulting in the need for catapults. Has it got any better? Well you won’t need catapults anymore, but you’ll still get hopelessly lost:

The Issue with LLMs

Those who have a smidgen of perspicacity will by now have realized that there is a basic flaw in my poking and prodding LLMs. It is like poking Michelin-star chefs and expecting them to produce the winning goal at the World Cup final. Yes, dear reader, we should focus on the meaning of the acronym ‘LLM’ and, in particular, the second ‘L’ . As I think most of you will know, it stands for ‘language’. LLMs are power-hungry beasts that are designed principally to spit out words — and they’re barely capable of doing anything else.

In order for any geographic intelligence to become apparent in your favorite chatbot it has to get plugged into something that understands concepts beyond human language. ChatGPT started down this path in April 2023 with the very concept of ‘plugins’. Plugins didn’t take off, and instead were quickly replaced with the concept of custom GPTs. One of the first companies to jump on the custom GPT bandwagon was Wolfram. Wolfram is best known for developing Mathematica, a powerful computational software, and perhaps more well known for Wolfram|Alpha, a computational knowledge engine. While signed into ChatGPT you can use Wolfram’s GPT to ask natural language questions regarding just about anything that Wolfram|Alpha can answer.

And it does a better job on geographic basics than vanilla ChatGPT. For example, here is Wolfram GPT’s answer to the question, “what is at 51.50104° N, 0.14207° W?” — it correctly deduces that the coordinate is at Buckingham Palace, whereas ChatGPT thinks the coordinate is about a mile away at Wellington Arch:

Ask Wolfram GPT a question even remotely more complex and it quickly falls over, but at least it doesn’t hallucinate:

Perhaps this is unfair to the primarily mathematical Wolfram GPT. Perhaps instead I should use another custom GPT that is more capable of understanding geography and geospatial functions?

Good luck finding one.

The problem with the search function in ChatGPT’s “GPT Store” is that the search results are singularly execrable — to put it mildly: they are an unfilterable quagmire of useless slop.

If you search for geospatial GPTs in ChatGPT’s GPT store it will come back with a seemingly never ending list, but you’ll quickly find that the vast majority of them are nothing more that textual guides to try to help you navigate Geographically Insidious Systems (‘GIS’). It’s impossible to find the nuggets. And asking ChatGPT directly isn’t much help either.

But we shouldn’t overlook another key issue with trying to use LLMs for geospatial …

They fail to provide a map-centric UI.

But then conversely, if you use traditional consumer or professional geospatial apps, you will find that they lack the deliciousness of a natural language interface that LLMs provide.

You can see this with a simple query to Google Maps where I ask for “grocery stores within 2 miles of 311 E Congress St Tucson, AZ 85701 United States that are open after 8pm”:

Google Maps fails to search on “grocery stores within 2 miles” and “that are open after 8pm”. It can only find the address:

I should also note that if you try the same query on Apple Maps you will find it fairs no better.

But Are There Signs of Progress?

It turns out there are a number of areas where AI is beginning to seep in to the world of geospatial, and it’s just starting to get interesting.

First let’s go back to the Google query and use it to poke once again at ChatGPT:

At first glance: the results look amazing — especially compared to the non-answers from Google Maps and Apple Maps. But dig a little deeper and you’ll find the results aren’t so rosy:

• The first result is acceptable, it is roughly within two miles.
• The second result just does not exist: it’s an empty lot.
• The third result may well be open 24 hours, but it’s over three miles away.
• More importantly perhaps: the results missed an amazing local store called Time Market, which is just one mile away and is open until 10pm.

So lovely, friendly answers, but entirely untrustworthy. For the query above ChatGPT claimed to talk to Bing as well as a bunch of yellow page and grocery store sites. Yellow page sites? Are you surprised it didn’t work?!

Now my tinkering is just that. I am not even scratching the surface. However, it turns out there is a highly respected institution that’s been doing some much more serious digging into the question of geospatial AI. That organization is the Alan Turing Institute who was commissioned to write an independent report on Geospatial AI for Land Use, specifically to “to explore how land use decision making can be supported by geospatial data, including earth observation data, and artificial intelligence”.

In the report they include a section on the value of LLMs:

The point therefore is to make the data more accessible, enabling a non-geospatial analyst to get the answers they’re looking for by simply asking natural language questions . The Turing Institute explored how a map-centric UI with a built in specialized LLM chatbot could help broaden the audience, in their case with an app called ‘Demoland’:

Here is typical conversation with the chatbot in Demoland:

Question: In areas of high deprivation has access to jobs improved? 

Answer: In approximately 15.4% of the areas with high levels of deprivation, job accessibility has improved. This suggests that while some progress has been made, there is still a significant proportion of high deprivation areas where job accessibility has not improved. It’s important to continue efforts to improve job accessibility in these areas, as this can play a key role in reducing deprivation. 

Question: How has air quality changed around schools? 

Answer: Sure, let’s take a look at the changes in air quality around some schools: 

1. St Joseph’s Roman Catholic Aided Primary School: The air pollution index has increased by 0.1074 units. This school is located in Gateshead. 
2. Newcastle Bridges School: The air pollution index has increased slightly by 0.0479 units. 
3. Alternative Education Service – The Beacon Centre: There has been no change in the air pollution index at this location in South Tyneside. 
4. Yamaha Music School: Similarly, there has been no change in the air pollution index at this location in North Tyneside. 
5. New Silksworth Academy Junior and Infant: Both these schools, located in Sunderland, have also seen no change in the air pollution index. 

Please note that these changes are relative to the current air pollution index at each location. 

This certainly seems to be very promising. One of the key recommendations coming out of the report is to develop a set of Geospatial AI Toolkits for LLMs:

Clearly this is precisely what we’re missing from geospatial apps — it’s evidenced not only by my tinkering but by the institutes performing much more serious study. But when those geospatial AI toolkits are integrated into LLMs the results are very promising.

I’m sure there are many organizations, large and small, focused on such integration. One startup I’ve come across that is doing precisely this is Aino. Their natural language interface is used for fairly atomic queries as this point, but it still significantly lowers the barrier to entry relative to a traditional Geographically Insidious System.

Here’s a demo of Aino’s platform being used for site selection (click to play):

But what about the larger organizations? What are they doing?

One notable and recent example of employing AI and natural language interfaces to query geospatial data has been the collaboration between Microsoft and NASA for something Microsoft is calling “Earth Copilot”.

If you follow Microsoft then you’ll know that “Copilot” is the brand they use to indicate integration of AI into their products. You can think of it like their version of “Apple Intelligence”. You might think, therefore, that Earth Copilot is Microsoft’s attempt to turn the whole planet into a computer to answer the Ultimate Question of Life, The Universe, and Everything.

Alas, it’s not quite that bold. But it is designed to help non-geospatial analysts quickly answer questions about the planet from the petabytes of earth observation data that NASA has collected. Here’s Microsoft’s CEO, Satya Nadella, announcing Earth Copilot at Microsoft Ignite 2024 just a few days ago:

Now we all know Microsoft has a tendency to pre-announce something as a product well before it’s generally available, and Earth Copilot is no doubt one of those cases. Nonetheless, the announcement paints a clear vision of what’s (hopefully) coming to all of us.

An American might summarize all this by saying: “We want to democratize access to geospatial data and geospatial systems”.

However, a Brit might simply say: “Let’s make stodgy and dodgy mapping technology work for everyone!”²

Beyond Natural Language Interfaces

When contemplating using AI for geography we shouldn’t be myopic and limit our thinking to the use of LLMs and natural language interfaces. Indeed there are two other important use cases for AI that are worth exploring:

• Use of AI for classification of objects on the ground
• Use of AI for positioning — i.e. locating oneself

Let’s dig into this a little further…

Object Classification

The concept of using AI for object classification is not new. Indeed Google Photos started giving users the ability to search for objects inside photos back in 2015. That’s almost ten years ago. So back then you could attempt to search your photo library for “cats” or “cars” and the app would miraculously list the photos with cats or cars. In 2024 this has now advanced significantly and with the Ask Photos feature you can ask questions like “show me the best photo from each national park I visited”.

Now this approach also works in the geospatial world for identifying objects on the ground. In fact organizations like NASA and the US Department of Defense were experimenting with rudimentary approaches to automatically identify like forests and urban areas back in the 1980s. However, it wasn’t until recently, with the advent of machine learning, neural networks and sheer GPU horsepower that the capability has really taken off.

Obviously there’s a great deal of work going on in this space that we don’t know about. For example, it has tremendous applicability to military applications. So no doubt the likes of Palantir are focused on this problem full bore.

For the rest of us though there’s another company that enabled some enormous progress. And that company is …

Meta.

Meta’s research labs have developed and released something they call “SAM”, otherwise known as the “Segment Anything Model”. By ‘segmenting’ Meta means classifying things or objects that are present in a photographic image. And Meta’s lofty goal is to live up to its tag line: they want to be able to recognize any object or thing in any image.

You can learn a bit more about SAM by visiting the Segment Anything website. Here’s a demo from the site (you may need to tap/click to play):

Why is SAM relevant to geospatial? Well it’s been used by geospatial organizations to interpret aerial and satellite imagery very effectively. One such organization that is successfully employing SAM is that age-old enterprise mapping technology juggernaut: Esri.

Esri’s R&D arm has published something they call “Text SAM” that combines the power of Meta’s SAM with another open source model called “Grounding DINO” which can find objects given a text prompt.³ The results are pretty impressive:

You could argue that Esri has not actually invented anything here. They are merely integrating capabilities developed by other organizations into an Esri workflow. Indeed this may be true, but their work still illustrates great potential.

Imagine if you were to combine this object recognition capability with the power of a natural language interface:

• “Produce a map of all the buildings under construction in the suburbs of Chicago together with an accompanying chart that shows total area under construction by ZIP Code”
• “Compare the tree cover for the years 2016 to 2024 and produce a chart showing changes by county over the years”

Positioning

The challenge of figuring out your location is not new. It’s also a problem that has by no means been solved. In fact with GPS jamming it’s getting worse. BTW: if you’re interested in the history of positioning technology then I recommend you read “12 Map Happenings that Rocked our World: Part 8 — Oh Brother, Where Art Thou?“

I’m sure you’ve all experienced the frustration of trying to locate yourself.

One of the most confounding issues facing anybody who has used a navigation app is “which way do I go first?”. For example, this is particularly perplexing when exiting a subway station: should I start by going left or by going right?

In an effort to solve this problem organizations like Google and Apple have started to provide augmented reality guided solutions to help people get off on the right foot. Basically you are told to hold up your phone and wave it around the buildings in front of you. It will then magically recognize exactly where you are and promptly encourage you to go in a specific direction.

Apple calls this “Visual Localization”, but more recently the industry has been calling this “VPS” which stands for “Visual Positioning System”.

Now it turns out providing VPS requires collecting a tremendous amount of imagery data, and so this feature is generally only available in a few cities around the world.

But there is an organization that is about to change all that.

Their name is Niantic, and they’re probably most famous for building the incredibly popular game: Pokémon GO.

Now what you might not know is that the super smart guys who formed Niantic also invented Google Earth and later made Google Maps what it is today. Niantic started as a separate organization within the greater Google empire back in 2010 and was later spun off as an independent company in 2015.

In 2016 Niantic launched Pokéman GO. This game quickly became the most popular — and most profitable — augmented reality app of all time.

But just a few weeks ago, on November 12, Niantic announced they were pioneering something well beyond a popular game:

They announced that they were pioneering something they call a “Large Geospatial Model”.

In other words Niantic has set out to replace the ‘L’ (for ‘Language’) in LLMs with a ‘G’ (for ‘Geospatial’) to create some called an ‘LGM’.

But what, exactly, does this all mean?

Well to quote from their blog:

At Niantic, we are pioneering the concept of a Large Geospatial Model that will use large-scale machine learning to understand a scene and connect it to millions of other scenes globally.

When you look at a familiar type of structure – whether it’s a church, a statue, or a town square – it’s fairly easy to imagine what it might look like from other angles, even if you haven’t seen it from all sides. As humans, we have “spatial understanding” that means we can fill in these details based on countless similar scenes we’ve encountered before. But for machines, this task is extraordinarily difficult. Even the most advanced AI models today struggle to visualize and infer missing parts of a scene, or to imagine a place from a new angle. This is about to change: Spatial intelligence is the next frontier of AI models.

Even with all the scans that Niantic collects — they have 10 million scanned locations around the world and are receiving about 1 million fresh scans each week, each containing hundreds of discrete images — it’s a drop in the bucket. There is simply not enough data to make VPS pervasive, even with Niantic’s scale.

But that’s where Niantic’s LGM will come in: it will essentially fill in the blanks:

Imagine yourself standing behind a church. Let us assume the closest local model has seen only the front entrance of that church, and thus, it will not be able to tell you where you are. The model has never seen the back of that building. But on a global scale, we have seen a lot of churches, thousands of them, all captured by their respective local models at other places worldwide. No church is the same, but many share common characteristics. An LGM is a way to access that distributed knowledge.

An LGM distills common information in a global large-scale model that enables communication and data sharing across local models. An LGM would be able to internalize the concept of a church, and, furthermore, how these buildings are commonly structured. Even if, for a specific location, we have only mapped the entrance of a church, an LGM would be able to make an intelligent guess about what the back of the building looks like, based on thousands of churches it has seen before. Therefore, the LGM allows for unprecedented robustness in positioning, even from viewpoints and angles that the VPS has never seen.

The global model implements a centralized understanding of the world, entirely derived from geospatial and visual data.

With Niantic LGM the goal is to be able to locate you to within a few centimeters — just about anywhere on the planet.

Essentially it will be your ultimate hack for GeoGuessr … 😱

So What Does The Future Hold?

As is usual for all things AI, things are moving fast. Here are just a few predictions as to where we’ll end up…

Converse With Any Geospatial App

Gone will be the days of brain dead search boxes. You will now expect any mapping app, consumer or professional, to be not only capable of understanding what you type into a text box, but you’ll also expect to be able to have a conversation with it. So answers to questions like the one I tried asking Google Maps above will be answered flawlessly and with the ability to maintain context.

This capability will obviously be of tremendous benefit to the billions of people that use consumer mapping apps every day, but where it’s really going to make a huge difference is in professional apps, in many cases eliminating the need for professionally trained “GIS analysts”.

Now the department or individual that normally has to rely on the geospatial geeks in the basement will be able to get the answers they’re looking for themselves. You only have to look at the queries used in the “Demoland” app that the Alan Turing Institute highlighted to understand where it’s all going.

Gone will be the days of contingent values, complex edges, feature barriers and topological unfathomables. You’ll just ask questions.

For example, I can imagine how a map-centric site selection app might work in this world. No buttons. No pull-downs. No ribbons. Just an interactive map, a query text box and an icon to invoke the microphone:

• “show me the areas in west London that have a median income greater than £65,000 and have a higher density of Millenials”…
• “now show me all available retail locations less than 200 square meters that are within a five minute walk of these areas”…
• “now eliminate all potential locations that are within a three minute walk of a Lululemon store”…
• “ok. now give me a list of those locations together with the contact details of the leasing agent”

Get ready. It’s going to happen.

Locate Me and Orient Me — Immediately, Anywhere

When they work, satellite positioning systems are great. But they don’t work in concrete canyons. And they don’t work indoors. They don’t work underground. They get spoofed. Unless you invest in very expensive equipment, they’re mostly accurate to only few meters. And, when you start your journey, they’re not good at telling you which way to turn.

VPS is beginning to change that. But it relies on pre-scanning the area (outside or inside) to make it all work. And to do that globally, everywhere is plainly not achievable — especially for areas which are not drivable. We need to add some intelligence to fill in the blanks. And it’s organizations like Niantic that are showing the way.

In this new world HD location will be a pervasive entitlement. Not being able to locate yourself precisely, accurately, anywhere — particularly indoors — will be expected. Just like Wi-Fi, it’ll be a new layer in Maslow’s hierarchy of needs.

A World of Geospatial Agents

Now I haven’t mentioned AI agents thus far. But there’s a lot of buzz about them across many companies and industries.⁴ As you might expect these creatures will be lurking in the background, monitoring, checking, acting on your behalf. You can imagine their use in consumer apps for keeping an eye on on prices, availability, and taking actions when certain specified conditions are met — think reservations for that table at a popular restaurant, or perhaps that amazing Airbnb villa in Tuscany that you’ve always wanted to stay at.

In the professional world it will enable you to be productive in other ways while the geospatial AI agents are doing grunt work on your behalf. In a site selection app, keeping an eye out for properties that meet your requirements. Or in a public safety app, automatically alerting you and others should dangers arise.

Agentive AI for geospatial is going to be huge. And we haven’t even started.

---

Footnotes

1. BTW, with the exception of American spelling this article is written in English, so it’s “maths”, not “math”. Q: did you sadly only study a singular “mathematic” at school? ↩︎
2. I can envisage a new marketing campaign for an innovative new mapping startup: “Not stodgy and dodgy — easy peasy, lemon squeezy”. Who says I don’t have a second career as a CMO? ↩︎
3. ChatGPT’s comparison of SAM vs. Grounding DINO. ↩︎
4. And more only yesterday: Google’s AI enters its ‘agentic era’ ↩︎

Living in the US in the lead up to a national election is sure to increase your anxiety at the best of times. And experiencing it in 2024 is even more collywobbling. And then there is everything else going on. In these situations I’ve found that escape is always good. So, if you’re like me — and are looking for a welcome distraction — perhaps you’d like to join me on a journey some 380,000 kilometers from Earth: a journey to the Moon…

An Amazing Era

A few of you fellow crinklies might have grown up in the amazing era of NASA’s endeavors in the 1960s and 70s. The 1960s marked the dawn of the space era, but the most exciting period was from 1969 to 1972 when NASA successfully landed six manned spacecraft on the Moon. These were of course the Apollo Missions.

But how did they navigate there? Where exactly did they land? How far did these astronauts venture from their landing craft? And how did their excursions compare to the journeys us Earthlings take every day? To learn more, please join me on this amazing expedition…

Navigating to the Moon

Yours truly was a wee six years old when Apollo 11 landed, so almost too young to be impressed. But impressed I was.

If you’re a young ‘un, you might be a bit blasé about NASA’s efforts. After all, everyone’s BFF, Mr. Musk, seems to launch about 1,000 satellites every day. So what’s the big deal? Well let’s just say in 1969 things were a little more challenging.

For those of you who read the Map Happenings post on the birth of in-vehicle navigation systems, you might have been gobsmacked by the fact that the 1985 Etak Navigator came out before GPS, CD-ROMs and ran on an Intel 8088 CPU which had only 29,000 transistors. And you might be even more impressed when you compare that to Apple’s latest M4 chip: it has not a million more transistors than the Intel 8088, but a million TIMES more¹.

But, by Apollo standards the Intel 8088 was like magic.

Imagine if you were fortunate enough to have talked to one of the engineers who developed the guidance and navigation computers for Apollo. I’m sure they would have given their two front teeth for something as powerful as an Intel 8088. In fact I have no doubt they would probably have promptly regaled Monty Python’s Four Yorkshiremen sketch — “You were lucky!”

By the way, speaking of Yorkshiremen, at the time Apollo 11 landed on the Moon in 1969 my family lived in the sheep farming country of northern England — the Yorkshire Dales to be precise. And our house was in a valley with no line of site to any TV signals, so we had to make do with the radio and printed newspapers. That didn’t stop yours truly from learning everything I could about Apollo. My most distinctive memory of the time was building a 1:144 scale Airfix model of the Saturn V rocket, complete with separate stages and an extractable Lunar Module. It was fantastic.

We finally got a television signal in time for Apollo 13. My grandmother was visiting at the time. I remember her exclaiming: “I’m not going to watch it. If I do, it’s sure to go wrong!”

But let’s get back to the Apollo guidance and navigation computers…

There were four guidance computers on Apollo:

• one for the Saturn V booster to get the astronauts off the launch pad and into Earth’s orbit
• one for the Command Module to get the astronauts from Earth’s orbit to the Moon’s orbit and back to Earth
• two for the Lunar Module: one for landing and subsequent ascent back to the orbiting Command Module and a separate emergency abort computer in case something went horribly wrong.

Designed by the bright lads and lasses at MIT, these computers were super advanced for their age. In the 1960s most computers filled multiple cabinets with electronics and had to be housed in large air-conditioned rooms. The Apollo Guidance Computer, or ‘AGC’, in the Lunar Module weighed just 30kg (66lbs) and was about the size of a small suitcase:

To get a sense of some of the challenges engineers were faced with to develop these computers, I recommend you watch this nine minute video by ‘Curious Droid‘. It’s seven years old, but still very informative:

The AGC in the Lunar Module, with only 2K of erasable memory (RAM) and 36K of fixed memory (ROM)², had to do the complicated calculations to help the astronauts land on the Moon and return safely to re-dock with the Command Module. It was one of the first computers to use integrated circuits (ICs) for its CPU, but don’t get too excited: each IC contained just three (3) transistors. A far fly from the super advanced Intel 8088! Also, don’t assume this 30kg suitcase was filled with these diminutive ICs. It wasn’t.

Probably the most complex modules contained in the AGC were the extremely laboriously hand woven “core rope memory” modules for the fixed memory (or ROM).

What’s intriguing to me as a former software engineer is that all the software programs in the AGC were actually encoded in the hardware using the core rope memory. So, the software was actually hardware. A mistake made in painstakingly weaving these core ropes by hand could therefore have introduced a software bug. As one module of core rope memory took three months for someone to weave, making mistakes was incredibly expensive.

To give you an idea of just how complex the core rope memory was, here are some visuals. A single core rope module was about 30cm (12″) wide and a about 10cm (4″) tall:

Zooming in to see the detail. The number of wires and complexity of the weaving was astounding:

Here is a lady painstakingly weaving the wires in one of the modules:

So imagine the job: taking this big heavy code listing, and literally weaving it into hardware:

For a fascinating deep dive, read Ken Sherriff’s blog. As he says in his article:

At a high level, core rope is simple: sense wires go through cores to indicate 1’s, or bypass cores to indicate 0’s. By selecting a particular core, the sense wires through that core were activated to provide the desired data bits.

So the software was encoded in the hardware. And there were bugs.

In the case of Apollo 11 a bug was discovered in the code for the abort landing just one a month before the planned launch. If it ever manifested there was a chance it would have sent the lunar lander tumbling head over heels. Needless to say Neil Armstrong was not happy. As a result somebody had to get inside the already fully stacked Saturn V rocket, make their way into the Lunar Module, remove the AGC and extract the offending core rope module. The replacement had been painstakingly modified to correct the bug. This involved locating the offending wire from the many, many thousands of wires inside the module, terminating it at both ends and then threading a new replacement wire, this time through the correct cores.

Most of the staff tasked with weaving the core ropes were women. One of the most impressive women on staff was Margaret Hamilton. David Brock recounts the history in his article “Software as Hardware: Apollo’s Rope Memory” in IEEE Spectrum:

The supervisors responsible for overseeing the careful integration of changes and additions to the software were known as “rope mothers,” regardless of their actual gender identity. The rope mother’s boss, though, was a woman: Margaret Hamilton. Before Apollo, Hamilton worked as a programmer at MIT’s Lincoln Laboratory on the Semi-Automatic Ground Environment (SAGE) air-defense system. After MIT won the contract to supply the guidance and navigation system for Apollo, Hamilton got a job working on the systems software, and she eventually led the team that created the onboard flight software.

If I’ve succeeded in piquing your interest in the Apollo navigation computers, and you want to nerd out on the really gory details, then watch this superb 1965 interview with the MIT engineers who designed and developed the AGC:

All pretty astounding, and I’d frankly be surprised if today’s young MIT graduates could pull it off given the same constraints.³

The Six Apollo Landings

The Moon travels around Earth once every 27.322 days in an elliptical orbit, or an elongated circle. It is tidally locked with Earth, which means that it spins on its axis exactly once each time it orbits our planet. Because of this, people on Earth only ever see one side of the Moon. All the Apollo landings were on the ‘near side’ — the side we can see from Earth.

[BTW: China is the only country to have successfully landed spacecraft on the far side of the Moon. This first landing was only a fairly recent accomplishment: achieved in January 2019. Earlier this year China also became the only country to have successfully collected lunar samples from the far side of the Moon and return them safely to Earth.]

If you’ve ever done any geospatial work, you may have done something called ‘site selection’. And you don’t have to be a geek to do it. For example, many people use off-the-shelf geospatial software to select the best site for a retail store or the best site for a smart locker. The folks at NASA went through a similar process when selecting potential landing sites for each of the Apollo missions.

Using images from uncrewed lunar orbiters that were launched in 1966 and 1967, NASA looked for sites that met the following criteria:

• Smoothness of the area: the sites should have relatively few craters;
• Approach paths: there should be no large hills, tall cliffs or deep craters which could cause incorrect altitude signals to the landing radar;
• Propellant: the sites were selected to allow for the expenditure of the least amount of propellant;
• Countdown delays: the sites were selected to allow for the ‘recycling time’ of the Saturn V if the countdown were to be delayed;
• Free-return: the sites must be within reach of the Apollo spacecraft in the free-return trajectory, that is: a path that would allow a coast around the Moon and safe return to Earth without any engine firings should a problem arise on the way to the Moon;
• Lighting: for optimum visibility during the landing approach, the Sun angle should be between 7 and 20 degrees behind the LM; for any given site, this results in a one-day launch window per month;
• Slope: the general slope of the landing area must be less than 2 degrees.

For Apollo 11 this selection process narrowed it down to five sites. All were within an area on the visible side of the Moon between 45 degrees east and west longitude and between 5 degrees north and south of the lunar equator.

A similar site selection approach was taken for the other six planned missions (Apollos 12- 17), each one being slightly more ambitious. Of course Apollo 13 never landed. But five subsequent missions did. Here is a marvelous video created by Ernie Wright (USRA) and Noah Petro (NASA/GSFC) of NASA’s Scientific Visualization Studio showing the six landing sites. The timing of the landings and the phase of the moon are all relatively correct — notice the big gap between Apollo 12 and 14. [note: you may need to tap to play video]

Here’s a summary showing the locations and statistics for each mission:

Apollo 11 was certainly one of riskiest landings. Not only did the AGC throw error codes and reboot several times during the decent, Neil Armstrong encountered a rock field at the intended landing spot. He had to manually maneuver the lander to another smoother location. In doing so they almost ran out of fuel. The Lunar Module indicated just 17 seconds of fuel left when they touched down⁴. The final landing spot end up being about 7 kilometers (4.25 miles) downrange from the intended landing site.

To begin to understand the complications of the landing you need to get to know Peter Adler and Don Eyles. These were two of the ‘young experts’ at the MIT Instrumentation Lab — the Draper Lab — who worked on the software for the Apollo Guidance Computer. Peter recounts the story in his 1998 article on the “Apollo 11 Program Alarms“:

You have to constantly keep in mind the amazing — to anyone using a PC today — constraints we had to work with in programming the [Apollo Guidance Computer]. There were 36,864 15-bit words of what we called “Fixed” memory, which today would be called ROM, and 2048 words of “Erasable” memory or RAM. With only rare exceptions, all of the executable code was in the Fixed memory, along with constants and other similar data. Erasable memory was used for variable data, counters, and the like. With so little Erasable memory available, we were forced to use the same memory address for different purposes at different times. Thus, a location whose contents might be altitude-over-the-lunar-surface during the landing stage might have contained the results of a sextant sighting of a navigational star from the alignment program. I think there were some memory locations that were shared seven ways. You can imagine the testing we had to do to ensure that the same memory location was not being used by more than one program at the same time.

You also have to remember that, long before Bill Gates, we had developed a real-time multi-tasking operating system. There were interrupt-driven, time-dependent tasks — e.g., turn the [Lunar Module] Descent Engine on at the correct time — as well as priority-ordered jobs that dealt with less time-critical things. Each scheduled job has some erasable memory to use while it was executing.

During the descent, the Apollo Guidance Computer (AGC) repeatedly threw 1202 alarms and later 1201 alarms. This was due to the fact that repeated jobs to process rendezvous radar data were scheduled because of a hardware bug: a misconfiguration of the radar switches. As a consequence the AGC quickly ran out of space to store data in its erasable memory (or RAM). Peter continues to recount the story:

On Apollo 11, each time a 1201 or 1202 alarm appeared, the computer rebooted, restarted the important stuff, like steering the descent engine and running the [Display/Keyboard] (DSKY) to let the crew know what was going on, but did not restart all the erroneously-scheduled rendezvous radar jobs. The NASA guys in the [Mission Operations Control Room] knew — because MIT had extensively tested the restart capability — that the mission could go forward.

Apollo 11 wasn’t the only hairy landing. Coming eight months after the near disaster of Apollo 13, Apollo 14 suffered a critical issue: a loose ball of solder was floating around in zero gravity inside the ‘Abort’ switch in the Lunar Module and was randomly shorting it out. It was the young MIT engineer, Don Eyles, that came to the rescue. Stephen Cass and Christine Dabney recount the story in writing for IEEE Spectrum:

In the early hours of 5 February 1971, Don Eyles had a big problem: Apollo 14 astronauts Alan Shepard and Edgar Mitchell were orbiting the moon, preparing to land, but it looked like they were going to have to come home without putting so much as a single footprint on the surface. The only way to save the mission was for Eyles to hack his own software.

Now remember, the software was all encoded in rope memory hardware, so Eyles had to develop an extremely clever work around. It involved the astronauts having to punch in 61 very carefully typed instructions into the computer that would result in the abort switch signal being bypassed. He later won a NASA award for his efforts. Eyles talks about it in this IEEE Spectrum interview from 2018:

None of the other landings had particularly significant issues with the exception of Apollo 15. It apparently landed on a tilt of about 10 degrees. The design limit for Lunar Module ascent stage lift-off is variously stated as 12 or 15 degrees. So it was close to the limit, but no issue ensued.

Mapping the Extra Vehicular Activities (EVAs)

The excursions that the astronauts made for the first three landings were pretty limited as the astronauts didn’t bring along any Cybertrucks to cause havoc. As a consequence they were constrained by their own two feet and, in the case of Apollo 11, time. That all changed for the last three missions when the astronauts brought along their 210kg EV buggy — the Lunar Roving Vehicle.

It’s pretty interesting to look at how far they actually ventured and compare that to where you and I might travel on Earth.

Let’s start with Apollo 11.

Neil Armstrong and Buzz Aldrin didn’t spend much time outside the Lunar Module — only about 2.5 hours. Much of it was spent collecting a few rocks, planting a flag and setting up experiments. So they didn’t get too far.

Fortunately we have a way to see exactly where they went with the help of the the Lunar Reconnaissance Orbiter or LRO. Launched in 2009 this robotic spacecraft orbits the Moon at an altitude of 50-200 km (30-125 miles). LRO’s primary objective is to make fundamental scientific discoveries about the Moon. It contains a number of instruments, including a system of three cameras that capture high resolution black and white images and moderate resolution multi-spectral images of the lunar surface. The high resolution camera has about 0.5m resolution per pixel, so it’s good enough to spy on the Apollo landing sites. 😁

So here’s what we can see of the Apollo 11 landing site:

You can clearly make out the left-behind Lunar Descent Module⁵ and the path that the astronauts walked to the edge of a nearby crater. But at no time did they venture further than 60 meters (200 feet) from their spacecraft.

Let’s compare where they went on the Moon to a trip across Paris: [note: you may need to tap to play video]

So, for all the hard work of those intrepid explorers, they didn’t even get out from under the Eiffel Tower!

Apollo 12 was a little more interesting. On April 20, 1967, about two and a half years before Apollo 12 landed on the Moon, another spacecraft had landed. It was called Surveyor 3. The Surveyor missions are little remembered but impressive precursors to the Apollo missions. Starting with Surveyor 1 which landed in June 1966 and ending with Surveyor 7 which landed in January 1968 these uncrewed craft laid the groundwork for Apollo. Five of these spacecraft, Surveyor 1, 3, 5, 6 and 7, successfully soft-landed on the lunar surface. In addition to demonstrating the feasibility of lunar surface landings, the Surveyor missions provided photos and the scientific and technological information needed for the Apollo manned landing program.

Why was Surveyor 3 so interesting? Well the Apollo 12 astronauts, Commander Charles “Pete” Conrad and Lunar Module Pilot Alan Bean, landed the Lunar Module “Intrepid” in the Ocean of Storms, a mere 160 meters (535 feet) from the robotic Surveyor 3 lander. A pretty amazing feat. You can get an idea of how precise the landing was by looking at this photo of Alan Bean inspecting the Surveyor with the Lunar Module in the background:

The Apollo 12 astronauts were much more energetic than their Apollo 11 counterparts. Over the period of their 31 hour stay on the Moon they made two “extra vehicular activities” (EVAs) for a total of almost eight hours trudging across the Moon. Again comparing their travels to a trip across Paris: this time they made it out from under the Eiffel Tower, across the Seine to the Trocadéro! [note: you may need to tap to play video]

Apart from the scary loose ball of solder floating around inside the ‘Abort’ switch, Apollo 14 went off without a hitch. Astronauts Alan Shepard and Ed Mitchell landed the Apollo 14 Lunar Module in the Frau Mauro formation on 5 February 1971. They stayed on the lunar surface for 33 hours, during which they performed two EVAs totaling a little over nine hours. Just like their predecessors they set out to beat the Guinness Moon Record for distance traveled:

On the second EVA, shown in green, the crew made a round-trip traverse of 2.5 kilometers (1.5 miles) toward the rim of Cone Crater, east of the landing site.

On to the last three missions: Apollo 15, 16 and 17. These were effectively “Apollo 2.0” with beefed up Command, Service and Lunar Modules designed to support longer stays. The main upgrade though was the addition of the Lunar Roving Vehicle (LRV) which was strapped to the side of the Lunar Module and subsequently deposited on the lunar surface like a fold down Murphy Bed:

Just like the first road cars, the LRV enabled ambitious exploration, allowing the astronauts to roam far from their humble Airbnb:

Here’s a map of Apollo 15’s drives across the moon, giving you an idea of the hilly terrain. The Apennine Mountains are 3,000 meters (10,000 feet) high to the east of the landing site, which required an unusually steep landing approach:

When you look at the map of their tracks a question starts to come to mind. Just how did they find their way around? Open their iPhone and bring up Google Maps? Well it turns out the Lunar Rover did have some navigation aids. There was no GPS, so it had to rely on dead reckoning. Each of the four wheels of the Rover were driven and also had odometers. Compasses on the Moon are useless as the Moon has no magnetic core. Instead the heading had to be determined from a gyro, which was initially calibrated by measuring the pitch and roll of the Rover using an attitude indicator and measuring the Rover’s orientation with respect to the Sun using a “Sun shadow device”. Here’s a picture of the Rover’s dashboard: you can clearly see the bearing and distance indicators, as well as the speedometer:

I’ll end this post with one final set of maps: the journeys of Apollo 17’s astronauts. Commander Eugene Cernan and Lunar Module Pilot Harrison “Jack” Schmitt landed the lunar module Challenger on December 11, about 240 meters (800 feet) from the pre-planned landing site. Cernan and Schmitt performed three moonwalks totaling just over 22 hours. At one point they traveled 7.4 kilometers (4.6 miles) away from the safety of the Lunar Module, the farthest during the Apollo program. To get an idea of just how far that was let’s compare their journeys to a trip across Manhattan: you can see that they made it as far as north as the Bronx and as far south as the Brooklyn Bridge: [note: you may need to tap to play video]

Or, if you’re more familiar with London, you’ll see their first EVA (in green) started from Harrods with a short trip to Battersea Park. Their second EVA (in Yellow) went from Harrods, to Regent’s Park, over to the City of London, and back through Trafalgar Square and St James’ Park. But their third and final EVA (in Blue), took them all the way from Harrods to Kew Gardens and Richmond-Up-Thames: [note: you may need to tap to play video]

If you’re wondering what it looked like from their perspective, here’s a photo they took on their second EVA. Far, far away in the distance you can just about make out the Lunar Module: [note: you may need to tap to play video]

So, does it make you feel lonely? Or do you want to return to the mayhem of planet Earth?

---

Acknowledgments

• NASA
• Peter Adler and Don Eyles of MIT
• Ernie Wright (USRA) and Noah Petro (NASA/GSFC) of NASA’s Scientific Visualization Studio
• David Brock, Stephen Cass, Christine Dabney: writing for IEEE Spectrum
• The Lunar and Planetary Institute (LPI)
• Curious Droid on YouTube
• Monty Python
• The London Telegraph newspaper

Further Reading and Viewing

Moon Trekking and Landing Sites

• Do your own “moon trekking” at https://trek.nasa.gov/moon
• “The Apollo Lunar Surface Journal“: NASA
• Website for the Lunar Reconnaissance Orbital Camera (LROC): Credit LROC
• Downloadable high resolution animations of the six Apollo landing sites: credit NASA’s Scientific Visualization Studio

The Apollo Flight Computers

• The Apollo Flight Journal: “The Apollo On-board Computers” by Phill Parker.
• “Inside the Apollo Guidance Computer’s core memory” by Ken Shirriff
• “Software woven into wire: Core rope and the Apollo Guidance Computer” by Ken Sherriff.
• CuriousMarc: 50 minute YouTube video delving into the Apollo Core Rope memory. This team restored an Apollo Guidance Computer to get it running again. Watch the video to find out how.
• “The Apollo 11 Program Alarms“: Peter Adler, MIT.
• “Light Years Ahead | The 1969 Apollo Guidance Computer“: excellent, nerdy presentation into the Apollo 11 program alarms by Robert Wills.
• “Don Eyles: Space Hacker This programmer saved the Apollo 14 mission with a few dozen keystrokes“: Stephen Cass and Christina Dabney in IEEE Spectrum.
• Sunburst and Luminary: An Apollo Memoir by Don Eyles, recounts his story of developing the onboard software for the Apollo spacecraft.

Other Items of Interest

• The full Apollo 11 Astronaut communications voice transcript: NASA
• The Lunar and Planetary Institute (LPI): Apollo Missions
• List of all missions to the Moon: crewed and uncrewed. Published by Wikimedia
• Hack the Moon: a website about the people, the tech and the missions that made the Apollo program possible
• The Yorkshire Dales

Footnotes

1. The Apple M4 chip has approximately 28,000,000,000 transistors. That’s 28 with a ‘B’. ↩︎
2. These were 16 bit words, so 2048 x 16 bits of RAM and 36,864 x 16 bits of ROM. 15 of the sixteen bits were for data and one was for parity. ↩︎
3. By the way, just for fun I asked ChatGPT if it was up to the task of creating a program to land on the moon. As is becoming all too common, ChatGPT misunderstood and made mistakes. It didn’t understand the memory constraints so I had to correct it. Here is the full chat log. ↩︎
4. Actually it was later found that Apollo 11 had about 45 seconds of fuel left. Sloshing in the fuel tank during Armstrong’s search for a safe landing site caused the fuel gauge to give an inaccurate reading. ↩︎
5. For a better understanding of what was left behind watch this video of Apollo 17 lift-off from the Moon. ↩︎

[MAJOR UPDATE on 27 January 2026: check out maphappenings.com/f1 — an interactive 3D map of all the tracks and teams]

Ok, a little reveal: yours truly is a bit of an F1 fan.

In case you’re not familiar, that’s the Formula 1 World Championship, the pinnacle of motor racing worldwide. I find the engineering side of the business just as interesting as the racing itself. There are 10 teams, each running two cars. The well funded teams have over a 1,000 employees on staff to design and manufacture their cars. Further interesting fact: the cars are continuously evolving: at every race every teams are installing newly designed and upgraded parts in an effort to give their drivers an edge.

If you want to learn a little bit about just how crazy it is, check out this video on what one of the teams goes through just to manufacture a bolt:

[BTW if you liked that video, you should also watch this one.]

Although the last two years of the championship have been interminably soporific with the advent of the Orange anticliMax¹, there is perhaps a glimmer of hope for the rest of the 2024.

It’s a grueling season with 24 races all over the world, in 2024 running from March to December. They do get a summer break though: during the month of August there is a three week lull. If you’re like me, boredom in August consequently sets in. What should one do, pray?

Well in my case I went looking for maps. Maps about F1. And I could find very few. Really?

I was left with only one option. I endeavored to make some myself. So, without further ado, please let me reveal my feeble effort. If you like what you see, feel free to download the PDF here. You can also review the list of locations in a live map on Apple Maps (now available on the web!):

• F1 Teams
• F1 Power Unit Manufacturers
• F1 Tracks

For any of the images below click on it to get a bigger picture.

F1 Teams

There are 10 F1 Teams in 2024. The vast majority are based in England:

Here are maps of the individual team locations. They’re all at the same scale, so you can compare sizes:

F1 Power Units

In 2024 four different organizations supply “power units” to the teams. The term “power unit” is defined as the combination of the internal combustion engine and an electric motor powered by two different energy recovery systems, one from regenerative braking and one from engine heat recovery. The four suppliers are:

• Ferrari
• Mercedes AMG Powertrains
• Red Bull Powertrains
• Renault

F1 Tracks

In 2024 there are 24 tracks spread around widely around the world:

Here are the specific tracks, listed in the order of events. For the schedule, visit Formula1.com:

---

Acknowledgments and Credits

• Formula One World Championship Limited
• PlanetF1.com
• McClaren Racing
• Red Bull Racing
• Apple Maps

Further Reading

• Foster+Partners McLaren Technology Centre:

Footnotes

1. That’s a chap called Max Emilian Verstappen. ↩︎

A Relentless Quest for Maps

Ladies and gentleman, come with me and prepare to rewind your clocks: I want to take you back to the year 1967. This was the year that the Beatles released Sgt. Pepper’s Lonely Hearts Club Band and Rupert Murdoch got married for only the second time.¹ It was also the year that marked the formation of a tiny new organization — an organization that became one ingredient in a momentous Map Happening.

Let me recount the story.

At that time there existed a large and successful company in Chicago by the name of R.R. Donnelley. Originally founded in 1864 by its namesake, Richard Robert Donnelley, R.R. Donnelley became a global printing behemoth. By 1967 it had become famous for printing the first telephone directories (in 1874!), the marketing material for the Ford Model-T, the Sears Catalog and LIFE Magazine.

To support its printing empire Donnelley had purchased a number of large and very expensive color printing presses and they were always looking for ways to recoup their investment. The company was already printing tons of phone books and magazines but it still had capacity on its presses going to waste. So what did it do? Donnelly made a proposition to the oil companies to create and print road maps. One of those companies was Shell Oil.

At the time Shell already had a large network of stations across the US and Donnelley thought they could give them an edge. The pitch went something like this:

“How about we design and print some beautiful road maps on our super high quality presses and you give them away at your gas stations as a promotional product?”

The offering was well received. But it didn’t stop there. Pretty soon Donnelley was producing all manor of custom maps for travel publications, for text books, for encyclopedias and for atlases. The business became big enough that in 1967 Donnelley formed a new division: Donnelley Cartographic Services.

1967: Donnelley Cartographic Services

Donnelley wanted this new organization to be close to one of its printing plants, so it got headquartered in the glorious city of Lancaster, Pennsylvania. Lancaster is in a mostly rural area populated by the Amish and has been made famous by one of Peter Weir‘s most successful films (well worth a watch BTW):

As the years progressed Donnelley Cartographic Services became the biggest custom mapping organization on the planet.

But in 1990 along came another opportunity.

A small software startup in McClean, Virginia needed some state highway maps as well as some funding for a trip planning product it was hoping to develop. That company was Spatial Data Sciences (SDS) and was headed by one Dr. Barry Glick. SDS pitched both Rand McNally and Donnelley on the concept. Rand didn’t bite but Donnelley did. The project started as a joint venture but only a year later Donnelley decided to take full control and buy out SDS’s share. Donnelley was now firmly in the mapping software business.

But just four years later, in 1994, Donnelley decided to refocus on its printing business. Glick and others convinced management that the organization could be grown much more quickly as an independent company with VC funding. As a result the cartographic services division and the recently formed geospatial software division was spun off, birthing an entirely new organization: GeoSystems Global Corporation. Glick was named the founding CEO.

1994: GeoSystems Global Corporation

GeoSystems was a pioneer. It developed interactive mapping applications for the first generation of electronic yellow pages, travel guides, CD-ROM based street atlas products, driving direction kiosks for car rental companies and web sites for real estate organizations. Its list of clients was impressive:

• Nearly all of the largest US phone companies — NYNEX, Bell South, Bell Atlantic, Ameritech and Pacific Bell
• Many of the largest automobile associations: AAA in the US and the Automobile Association (AA) in the UK
• Hertz and later AVIS
• Moore Real Estate: with GeoSystems’ expertise Moore became the most innovative player in the US real estate market with their launch of the world’s first website for home search: CyberHomes.com

GeoSystems even had Apple as a customer: GeoSystems developed the Fodor’s 94 Travel Manager for the Apple Newton and Apple published it as part of a suite of apps.

But let’s all remember what times were like in those days …

I realize many a reader will be a young whippersnapper whose brain is unaccustomed to being deprived of a Wi-Fi enabled screen. But even if you’re an old crinkly like me your brain may still need a Biden prompt to remember what life was like.

By now we’re in the year 1995 when America Online (AOL) was all the rage and the most popular web sites were the likes of Yahoo!, GeoCities, Netscape:

The Moon Shot Idea

So the bright minds at GeoSystems ² made note of all of this hype and decided to go for a moon shot: what if they developed a consumer website focused on mapping and funded it through advertising?

But the question was: what to call it? The original idea for a name was “webmapper”, but a company in the website management business trademarked the name just before the planned launch. A frantic internal competition ensued to come up with a new name. The winning name was nailed by an employee’s wife ³.

It’s a name some of you may of heard of. It was:

Yes, dear reader, MapQuest.

And so on February 5, 1996 the site was launched. It looked something like this ⁴:

Q: so what happened after the launch? A: all hell broke loose.

Remember where the company was located: Lancaster, Pennsylvania. A town with a population of about 50,000 and most famous for the Amish, who eschew modern things like electricity and who still use horse and buggies instead of cars:

It ain’t exactly the Valley.

Word about MapQuest spread quickly on the social media conduits of the day (i.e. people talked to each other). Within a few days traffic to the site skyrocketed and there was a mad, crazy scramble to add more capacity. One of the larger rooms in the office rapidly became swamped with folding tables, stacked servers and a rat’s nest of cables.

And then Lancaster’s entire internet capacity was mostly sucked into serving MapQuest. The team did everything it could to keep the site up.

And this was all with just a very basic product at launch: MapQuest didn’t even provide directions. It only did one thing: it rendered a static map for an address — and only if that address was in the US.

Things moved rapidly from there:

• GeoSystems opened an office in Denver and relocated MapQuest servers there
• MapQuest launched turn-by-turn directions for the US, resulting in another huge bump in traffic
• MapQuest launched B2B offerings — so businesses could embed MapQuest maps & directions in their own site
• MapQuest expanded internationally, providing coverage in Canada and western Europe

The site became so popular it was rare not to see someone carrying their MapQuest printout when boarding a plane:

Even cartoonists of the day picked up on MapQuest’s popularity:

A year after launch things moved at an even more rapid pace. In July 1997 raised $12M in a Series C and in 1998 a few of the founding members of MapQuest left for other endeavors. The most impactful change came in August 1998 when Mike Mulligan, formally a senior VP at American Express, was installed as CEO.

Then things started moving at warp speed.

By the late 1990s the ‘dot com’ boom was in full swing. Everyone was anxious to ride the wave. In 1995 Netscape had gone public. Then in 1996 so did Yahoo. In 1997 it was Amazon. 1998 saw IPOs from the likes of GeoCities, InfoSpace & Inktomi. ⁵ But by 1998 there were already murmurings of a possible dot-com bubble burst, so time was of the essence.

So Mulligan quickly took the company down a path to an IPO.

May 1999: The IPO

The company knew it wasn’t going to get the valuation it needed with the name “GeoSystems Global Corporation”. It had to leverage the mindshare the MapQuest brand had achieved. Originally the thought was simply to rename the company MapQuest. But at the time companies were doing everything they could to leverage their internet prowess. By simply adding “.com” to your name you could get a huge lift in value (sound familiar?) — so that made the decision easy. In February 1999 GeoSystems Global Corporation became MapQuest.com, Inc.

Mulligan also knew a leading ‘dot com’ headquartered in sleepy Lancaster, PA wasn’t going to cut it. Instead the HQ was quickly relocated to a swanky office on Park Avenue in Manhattan.

By January 1999 MapQuest had grown to 222 employees (46 in sales!) and had an impressive list of customers, including:

• Yahoo! (MapQuest powered Yahoo!Maps) ⁶
• Other search engines of the time: Excite, Infoseek, Lycos, Ask Jeeves
• Elon Musk’s Zip2
• AAA, Avis, Hertz, Budget
• Travelocity, American Express, Galileo
• National Geographic
• FedEx, Blockbuster, Borders, Home Depot, Sears
• Marriott, Hilton
• Ticketmaster

Revenues were ~$25M but at the time only about 30% (or ~$8M) was coming from MapQuest’s internet business, i.e. advertising on the MapQuest site and MapQuest B2B web services. The rest was coming from the legacy custom print map business, formerly Donnelley Cartographic Services. Of course the pitch to investors was the growth potential of the internet business was going to far outpace the legacy business.

When discussing potential valuations I remember the internal discussions well. Very conservatively we thought the company was worth $40M. If we were hugely optimistic and MapQuest hit a home run the company might be worth $400M.

MapQuest went public on May 4, 1999 and the stock popped 49% on the first day. This company, with about $8M in internet related revenue, was now worth $800M.

But that promise to investors about the potential growth of the internet business was not a pipe dream. By the end of 1999 MapQuest had about 2,500 customers. Many of those were businesses that just wanted a store locator on their web site. The big sites like Yahoo! used MapQuest to add maps to their search results and to power their own map offerings.

For advertising revenue MapQuest had an edge: it could drive the value of an ad in a way nobody else could: MapQuest knew where you were going. So MapQuest was the first site to offer ‘geocentric’ ads. Hotels, airlines and fast food chains loved it.

In the months following the IPO MapQuest continued to soar and expand. MapQuest now offered its services in five languages and 78 countries and became the first mapping website to offer satellite imagery. It was by far the most popular mapping site on the web — in November 1998 Media Metrix had ranked MapQuest as the 34th most visited web site in the world and MapQuest was the number one travel web site. It also won awards from PC Magazine and Yahoo!Internet Life.

A Potential Acquisition Target

All this hype and activity started to attract the attention of the big boys. Having just suffered going through the due diligence of an IPO, MapQuest was now a ‘cleaner’ company and therefore easier to acquire.

One of the companies MapQuest was courting at the time was America Online (AOL). MapQuest was hoping to ‘map enable’ AOL’s many properties. By then AOL was at its zenith. It had bought its largest competitor, CompuServe. It had bought the popular instant messaging site ICQ. And it had bought Netscape. And it was hungry to continue its expansion. AOL was particularly interested in gaining access to large volumes of web pages where it could place local advertising.

Shortly after MapQuest went public, Mike Mulligan overheard his assistant trying to arrange a meeting between him and Paul DeBenedictis of AOL. DeBenedictis was head of AOL Digital Cities, a site that provided local content and event information for cities across the US. Paul was in the process of identifying companies that could provide AOL with a substantial amount of local advertising inventory.

Mike interrupted his assistant and asked to speak to Paul directly. They quickly managed to agree on a much earlier meeting date. It was lucky for MapQuest that they did.  In the meeting with Paul, it turned out AOL had just started to think about acquisition candidates to add traffic to their AOL Digital Cities effort.  With a favorable meeting early in the process MapQuest got to the head of the queue for acquisition discussions. Had the meeting not happened so early it may have been a different story.

Truth be told, AOL’s interest in MapQuest wasn’t really about the maps. They also didn’t care about MapQuest’s B2B business. They just wanted one thing: ad inventory.

But even with this lucky break the deal almost didn’t happen.

The potential acquisition went south in due diligence. AOL wasn’t happy with MapQuest’s data contract with NavTech (now HERE). They decided to pause discussion and asked MapQuest’s permission to conduct contract discussions directly with NavTech. MapQuest consented. They negotiated a new deal with NavTech and came back months later to renew acquisition discussions. By this time MapQuest’s stock price had risen and MapQuest ended up with a substantially more favorable deal as a result.

Concurrent with the MapQuest acquisition discussions, AOL was pursuing a different and much bigger mega-acquisition: Time Warner. But it wasn’t long before the Time Warner negotiations broke down. It was during this lull that the Mapquest deal was brought back to the table and was subsequently approved by the AOL Board.

Had the Time Warner deal not fallen off the MapQuest acquisition would probably never have been considered.

December 1999: Acquisition Announced

Finally on 22 December 1999 the deal was announced. AOL agreed to purchase MapQuest in a stock deal that was worth about $1.1B. Not bad for a company that at the time had revenues of around $35M.

But that valuation didn’t last long. AOL’s stock had peaked about 10 days earlier. Less than a month later, on 10 January 2000, AOL announced its much more outrageous acquisition: it was going to buy Time Warner for $183,000,000,000 (yes, that’s 183 with a ‘B’). But within a day of the announcement AOL’s shares tanked 11%, taking the value of the still-to-close MapQuest acquisition with it. By 18 January 2000 the value of MapQuest deal had shrunk to about $785 million.

Many MapQuest employees weren’t happy about AOL, particularly those who’d put their hearts and all their energy into developing the internet side of the business. The idea of being acquired by AOL was abhorrent. To them it would almost have been like being acquired by an organization like DJT today. AOL? They don’t understand the internet! All they did was fill your mailbox with AOL CDs.

But eventually the deal closed in the second quarter of 2000. MapQuest was now the property of Big, Bad AOL.

2000: The Slow Demise Post Acquisition

At first things looked pretty rosy. AOL had a humungous amount of users. At that time four in every five Americans on the web touched an AOL property. And AOL was able to direct a ton more users to MapQuest. Traffic went further through the roof. So AOL got what it wanted: a huge number of page views on which to display ads.

But soon there were signs that utopia was going to be elusive.

On January 11, 2001 AOL’s acquisition of Time Warner closed, one year after the deal was announced. Civil war between AOL and Time Warner executives quickly broke out. A day after the close AOL stock traded at $47.45 — down from an all time high of $94.19 on 15 December 1999.

Things were not looking good. A company-wide hiring freeze was implemented, affecting AOL Time Warner and all its properties, including MapQuest.

By this time yours truly had a new manager as Mike Mulligan had helicoptered into the sunset. In fact I had several managers within the first year post acquisition — actually seven — yes — seven. I had been told: if you want to advance your career you should relocate to AOL’s HQ in Dulles, Virginia. ‘Yes, sir’ I said. Then, the night before I was due to move my family from Lancaster to Virginia, I got a call from my then boss: AOL was going to close the MapQuest office in Lancaster the next day and lay off all staff. 😱

I relocated the next day as planned, arriving at the new house with the movers and all the moving boxes. Out of the blue I get another call from an executive assistant to a senior AOL VP. She gave me a somewhat disturbing message: “Err, you know we’ve just had a big re-org and I know you’ve just moved your house and family to Virginia, but we don’t know what your role will be or who your next boss will be. But please don’t worry.” 😱😱

Hmm. Very encouraging.

The new management seemed to have very little interest in anything to do with MapQuest, particularly as it related to product road map and strategy. And with the layoffs and hiring freeze there weren’t enough resources to do anything substantial even if there was a good plan.

I tried to make matters clear and pleaded with the powers that be: MapQuest was a site built on map data but it didn’t make maps. In fact 98% of the map data was licensed from third parties^.7 I knew MapQuest had to build a moat around the product otherwise someone else could swoop in, license the same data and build a better product.

And you won’t win any prizes for guessing who did.

On 8 February 2005 a new site launched. Unlike MapQuest it had big ‘slippy’ maps — maps that you could pan just by clicking and dragging. It also had a brand:

Google.

I think you’ll agree: the rest is history.

MapQuest Today

Somewhat surprisingly, it still exists.

It’s now owned by System1, an internet advertising company. All of MapQuest’s IP and mapping know how has been pretty much discarded. It now seems to rely mostly on technology from Mapbox.

What a sad way to have to end a story about a truly great company.

But it truly was a ‘Map Happening’ that rocked our world.

---

References, Acknowledgments, Further Reading and Viewing:

• Many thanks to Perry Evans, Barry Glick, Mike Mulligan, Michael Nappi and Paul Ross, without whom the juicy details of this post would not have been possible.
• Security and Exchange Commission: S-1 prospectus for MapQuest IPO.
• Chicagology: RR Donnelley: a short history on how R.R. Donnelley came to be.
• Articles on the GeoSystem’s Apple Newton product for Fodors:

• “MapQuest Investors Eye AOL Warily“: by Ariana Eunjung Cha, then at the Washington Post, January 19, 2000.
• “Big, Bad AOL“: by Gary Rivlin, formerly a writer for the Industry Standard. The article won a Loeb award as the best business article appearing in a magazine that year.
• Post MapQuest IPO interview with Mike Mulligan on CNBC:

Other Articles in This Series

• Part 1 — The First Map
• Part 2 — The Birth of Coordinates
• Part 3 — Road Maps!
• Part 4 — The Epic Quest for Longitude
• Part 5 — The Dawn of Tube Maps
• Part 6 — The Advent of Computer Based Mapping
• Part 7 — Those Views from Above…
• Part 8 — Oh Brother, Where Art Thou?
• Part 9 — A Curious Phenomenon Called ‘Etak’

Footnotes

1. He’s now up to number five. Full chronology: [1] Patricia Booker – 1956; [2] Anna Torv – 1967; [3] Wendi Deng – 1999; [4] Jerri Hall – 2016; [5] Elena Zhukova – 2024. ↩︎
2. Some of the key bright minds involved with the initial development, launch and success of MapQuest.com in February 1996 (apologies if I missed any one): Perry Evans, Chris Fanjoy, Barry Glick, Simon Greenman, Harry Grout, Marshall Matthews, Paul Metzger, Michael Nappi, Bob Rudi, Travis Shirk, Joan Silver, Mike Swartz. ↩︎
3. The wife of Perry Evans. ↩︎
4. I don’t have a screenshot from launch. This one is about 18 months after the original launch. If any of my ex-colleagues have one from the launch please share and I’ll add it to this post. ↩︎
5. As did ARM Holdings! ↩︎
6. What about Google? Well it didn’t even get founded until September 1998. At this time it was only 3 months old. ↩︎
7. NavTech (now HERE), Etak and GDT (now TomTom), A.N.D (now Geojunxion) and others. ↩︎

If you’ve noticed a slight lull in the cadence of Map Happenings posts it’s not because I don’t love you. It’s because I’ve been preoccupied with other matters — and one in particular: a grand tour of Great Britain, encompassing a few of the most iconic locations in England, Scotland and Wales.

This was a three week road trip with a different stop practically every night.

The process of planning the trip proved to be long and arduous, but actually a lot of fun. It involved tons of research into places to visit, the best places to stay and eat and the best routes to get from A to B. The tools and information sources I used were varied and while they enabled me to build a plan, it wasn’t particularly straightforward. But I got there in the end.

Now that I’m back I’d like to share the memories of the trip. However, like the trip planning, building and sharing a coherent résumé of my journey is far from straightforward — actually in many ways it sucks.

Net/net: nobody has cracked the trip planning nut and nobody has cracked the trip memories nut.

So if you’re a passionate mapping nerd with some developer chops here’s your challenge and opportunity: build a seriously magical product for travel that becomes the go-to default for planning, organizing and reliving a trip.

I’ll recount my experience below so you can use it as one set of data points. Take your own experiences as another set of data points. Talk to your family and friends about how they’ve planned trips and shared memories. Then be ruthless and question every requirement. Boil everything down to the very essence of what people actually need. And be sure to weave in design wizardry from the get-go to make the product insanely easy and a delight to use.

I’ll bet you a dollar: you’ll have a winner on your hands.

Let’s Start with The Planning

Where do you start? In my case I had some ideas and some parameters. There were certain places I knew I wanted to visit and a few places I knew I wanted to stay. The trip was time bound to three weeks and I knew I didn’t want to spend all day driving in a car. So the goal was fun and easy.

If you do some poking around you will discover there are some apps out there that attempt to help you build a trip plan. But they’re all pretty laborious to use.

The closest I could find to a reasonably good trip planner was Wanderlog. It’s pretty comprehensive and allows you to build an itinerary, make notes, set budgets and collaborate with others. It’s also got pretty good place search and a nice ‘mappy’ interface. And of course like any of today’s products from search engines to bananas — it’s AI enabled:

But remember, yours truly is a Jaded Mapping Curmudgeon (JMC), so would I use such a new fangled tool? Well I did try. But I was immediately faced with the uncertainty. If I were to spend copious hours investing in this tool would it give me the results I need? And would I be able to use it easily on the trip? And could I (with short arms and deep pockets) get what I wanted without having to fork out $$$ for the pro version? And, as an Apple Maps bigot, would I be forced to use Google Maps?

FUD quickly consumed me. I demurred.

So what did I use? Well it boiled down to two tools with which I had extreme familiarity: Apple Maps and a spreadsheet — in my case Numbers. Let me explain the process:

Similar to Google Maps, it turns out Apple Maps has an extremely useful feature to build lists of places and add to them to collections. In Apple Maps’ case they call them ‘Guides’. Apple Maps Guides come in two forms: curated guides and then ‘My Guides’. Curated guides are lists of places put together by well know publications and there are now hundreds and hundreds of them in Apple Maps. Here’s a sample for London:

But Maps also provides an easy way to create your own guides on your iPhone, iPad or Mac. Simply take a place of interest, tap the “… More” button and select “Add to Guides”. Bingo. Now you can quickly build a list of places that are relevant to your trip and add or delete items from the guide with a couple of taps:

Here’s a view of the guide I created for my UK trip, complete with hotels, places I wanted to visit, attractions and even laundries:

What was beautiful about this approach is everything I needed was immediately accessible: phone numbers, web sites, directions and by viewing the guide and zooming into a particular area I could quickly filter the list to what was relevant for a particular day. And with one tap you can share the guide with others.

What was missing of course was all the details: arrival and departure dates, reservation numbers, booking references, costs & budgeting. Now I could have spent the energy and put all that information in the Wanderlog app, but like I said, I was wary of trusting the information to an unfamiliar app. I also found it was difficult to get the app to summarize the information in the form I was looking for. So naturally what do I do? I turn to a spreadsheet. Here’s the one I created and it provided everything I needed right at my fingertips:

Because it was cloud based it was easily accessible from any of my devices and, using the collaboration features of Numbers, easy to share and edit with others.

But how did I figure out where to stop, stay and eat? That, dear reader, is where the research started in earnest. If you’ve read any of my past posts, in particular ‘Why Rating Systems for Places & POIs Suck… and a Possible Fix‘ you’ll realize I’m not a fan of crowdsourced ratings — the main reason being that the Venn diagram of my tastes and opinions seldom overlaps with the tastes and opinions of the general masses. Also many — if not all — place ratings tend to be dominated by the opinions of septics. No offense, but when you hear stories about such people complaining vociferously about the lack of French toast in Parisian bistros it quickly makes you realize that perhaps you should take their opinions with a grain of salt.

So my research relied mostly on well respected travel publications. If you’re ever searching for places to stay in the UK I can highly recommend perusing The [London] Telegraph travel web pages. I would strongly advise you stay clear of any web site driven primarily by booking revenue and stay clear of highly popular sites (particularly US based) that claim to provide ‘travel advice’. Look for the smaller, quirkier publications. Or go by word of mouth from friends and family. I think you get the picture.

Pretty soon you’ll be building up a nice personal guide in your favorite mapping product. With a companion spreadsheet you’ll have what you need.

You could say that all this laborious research is part of the fun — like looking for a brilliant sale on that item you’ve always cherished. A relentless search for the perfect place provides not only the reward but also the endorphin. So, if someone made it too easy would you feel like you were making the right decisions? You be the judge.

On The Journey

The Apple Maps guide I created for the trip worked like a charm. I immediately had all the pertinent information I needed at my fingertips. And when traveling to the next destination the ‘avoid highways’ option gave me a reasonably good and lesser traveled route that was more interesting to drive.

But it did uncover my three big wishes for Apple Maps:

• Tweaks to my guide in Apple Maps didn’t promulgate to the people I shared it with. So sharing a guide is really a ‘send a copy’ feature, not a ‘collaborate’ feature. Apple has both options for Notes, Pages, Numbers and Keynote documents. I wish they’d bring the same to Apple Maps Guides.
• I would have loved a ‘Scenic Route’ option for directions.
• If there was one area I was longing for some ‘Apple Intelligence’ it was for suggesting places to stop along the route — perhaps for some good coffee or a site worth visiting. There were at least two occasions when we drove right past a spectacular site that we didn’t know we were going to pass.

Here they are:

Angel of the North

The Angel of the North is a contemporary sculpture by Antony Gormley, located just south of Newcastle, England. Completed in 1998, it is believed to be the largest sculpture of an angel in the world. It stands 20 metres (66 ft) tall with a wingspan of 54 metres (177 ft), larger than that of a Boeing 757 aircraft.

The Kelpies

The Kelpies are a pair of monumental steel horse-heads near the Scottish town of Falkirk. They were designed by sculptor Andy Scott and were completed in 2013. A kelpie, or water kelpie, is a shape-shifting spirit inhabiting lochs in Irish and Scottish folklore. It is usually described as a horse-like creature and is able to adopt human form.

Sharing the Memories

Facebucket? Instagam? X? TikTok? MySpace? You won’t catch this JMC in that festering world. Me: I want to share different sets of photos with different sets of people — and not with the whole world thanks very much.

So along the journey I resorted to Messages, WhatsApp and an ancient appy thing Gen Z users have never heard of: “electronic-mail”. Painful? Yes. But at least I was in full control of distribution.

The trouble really started when I got back home. I had taken nearly 700 photos and they were widely geographically distributed. Furthermore, if I shared a set of pictures of a particular location, say Sterling Castle, the people I shared it with weren’t necessarily, shall we say, ‘geographically capable’. So they had no idea of place or context.

Finding all the photos of a particular location is fairly easy to do in Photos on iOS or macOS: use the ‘Places’ tab and zoom into the map location of interest. You can then subselect and share the set of photos from there.

If you want to get cute: open iMovie on your iPhone, select “Start New Project” and then select ‘Magic Movie’:

It’s actually pretty awesome. Here’s a Magic Movie I created for Sterling Castle in Scotland:

But again — what’s missing from all this?

Err … how about a map boys and gals?

It turns out there is no magic way to include a map. One app I tried with supposedly good ratings, Tripcast, provides a map view option on uploaded photos, but it is up to the user to select the map and there is [AFAIK] no way to recreate the journey with map animations. Also, it takes ages to upload any photos to their servers. I tried uploading all the photos I took on the trip and the app repeatedly crashed. Ugh.

Now some of you Apple fanpeople may have watched the recent WWDC24 Keynote and noticed a new feature coming to the Photos app called ‘Trips’. Here’s the clip about the new Photos app coming in iOS 18:

But does the ‘Trips’ filter include a map? Alas, I don’t think so.

And more importantly: does the ‘Trips’ feature include map animations? I seriously doubt it. If you want to recreate a journey with map animations and share it with others it’s hard. Seriously hard. You can try using StoryMaps¹ (sorry: it’s hard and painful). If you’re a pro you can use an Adobe After Effects template like WorldTravelMaps (even harder and even more painful):

Another possible app you might want try for sharing memories is called Polarsteps. From what I can tell, Polarsteps seems to be a Facebook for trips, so you can go there to search and browse for trips other people have taken and you can use it to create a résumé of trips you may have taken yourself. It seems mountains better than Tripcast in that it will (somewhat scarily) scan your photo library and automatically build trips from that. I downloaded Polarsteps from the app store and after about 10 minutes of scanning and about another 20 minutes of poking I was able to build a rudimentary version of my GB Grand Tour:

Polarsteps was about 70% successful in rebuilding the trip. However, it did hallucinate a bit when trying to associate photos with location. But, all-in-all, not too bad.

I see Clare Jones, formerly of What3Words, is now CEO of Polartrips. I can’t wait to see what she does.

A Possible Magical Product

So what’s the perfect app?

An app that helps me plan and collaborate effortlessly. Totally map centric. And super smart. 

• Automatically add details to my itinerary by mining my emails about bookings and reservations
• Make suggestions based on places I like and other people like me like (not just the general masses)
• Leverages the apps I use every day: Maps, Photos and Calendar
• Suggests more interesting routes especially scenic routes

And importantly: similar to what Polarsteps attempts to do: it auto-magically allows me to recreate the journey so I can relive it when I get home: a journey with gorgeous map animations and smart clustering of the photos and videos I took along the way.

Apple Maps and Photos (or Google equivalents) sort of come close to solving some of the challenges. Wanderlog makes a valiant try but is still laborious and totally misses on memories. Polarsteps goes a long way to reliving a trip but lacks the capabilities of trip planing.

So what’s a possible future?

Perhaps, just perhaps: some more mischievous sherlocking by that nefarious fruity company in Cupertino. I can see it now:

Trips: your magical companion for any journey.

---

Footnotes

1. Secretly published by the Environmental Systems Research Institute I believe ↩︎

Acknowledgements

• Apple
• Esri
• Polarsteps
• Tripcast
• Visit Scotland
• Wanderlog
• Wikimedia
• WorldTravelMaps

It’s not often you come across an organization that has the potential to make a difference. I mean really make a difference. This tiny organization called ‘PLACE’ is one of them.

PLACE first came across my radar when I was contacted by its founder, Peter Rabley, last July.

Peter is a geographer. He was born in Southampton, England which coincidentally is not too far from the Ordnance Survey headquarters. Perhaps that was a signal that he would eventually get involved with mapping.

It turns out Peter and I share a few common threads: during the late 1970s we both suffered through a Roman Catholic boarding school education in England and we both quickly became ex-pats. Not only that: just like me Peter’s first serious involvement with technology was with VAX/VMS mini-computers. But while I fled to Silicon Valley, Peter’s journey was much more exotic.

He spent his youth growing up in the Bahamas and then ended up studying Geography at the University of Michigan. Then in 1984 he headed to the University of Miami to acquire a masters in Economic Geography and GIS. It was while he was at Miami that he got familiar with mapping technology, cutting his teeth on what must have been an excruciatingly painful and early version of Esri’s ARC/INFO.

What? I’m calling early versions of ARC/INFO exotic? No, but wait!

The exotic part was when Peter got a job focusing on urban planning in Washington, DC. From this position he was promptly dispatched to various locales in Pakistan and Nepal. Fast forward a few years and Peter had built expertise in international land management, both from a policy point of view and in the foundational technology used to make it all work efficiently, especially in developing countries.

In 1996 Peter founded International Land Systems (ILS). ILS focused on software and services for property registration and property boundary mapping. And they did this in over 30 countries worldwide: including in China, Ukraine, Ghana and Jamaica as well as in the US, the UK and Germany.

In 2011 ILS got acquired by Thomson Reuters and within a year Peter had left to form another property information venture, this time with a philanthropic organization called the Omidyar Network. In case you’re not familiar, this organization was established by Pierre Omidyar who founded eBay.

By that time Peter had come to realize that a dire lack of information about buildings and properties was holding back urban planning. More importantly it was holding back economic growth. This was particularly the case in developing countries around the world.

At the macro level it all boiled down to one thing: a lack of detailed data about cities, communities and neighborhoods was a serious crimp on the social well being of hundreds of millions of people across whole continents.

But these countries didn’t just need software to manage data. They needed the raw data to power it. And they didn’t have it.

What’s the best way to go about creating this data? Well, guess what folks, it all starts with a map.

It was out of this need that in January 2020 PLACE was born.

PLACE Fundamentals

When Peter founded PLACE he focused relentlessly on the fundamentals. Fundamentals about data. Fundamentals about organizational structure. Fundamentals about incentives. And perhaps most importantly — fundamentals about trust.

PLACE was not just going to be another commercial mapping company. And nor was it going to be another open data organization. PLACE had to be structured in such a way that the organization could produce high quality data efficiently and in volume. This required a ‘back to first principals’ rethink of how data companies are structured, how incentives are aligned and how data is collected and published.

PLACE also had to focus on producing the right kind of data. In peeling the question back to the most atomic level Peter came to realize that in order to build very detailed maps suitable for helping communities grow and prosper you first needed something even more basic: you needed imagery.

But not just any imagery. The kind you could get from commercial satellites just didn’t cut it. You needed something much more HD.

So what did PLACE set out to do?

They made it their mission to collect and publish super high resolution, high-accuracy aerial and street imagery for cities across Africa and small island countries around the world.

This imagery would be the fuel to build the maps. And the maps would be the fuel to stimulate growth and prosperity.

Thinking Different

The beauty of PLACE isn’t so much about the data they collect. It’s about the way they do it.

First: PLACE gives ownership of any data collected in a country to the government of that country. At zero cost.

In return PLACE asks for three things:

• Getting the respective government to provide the necessary licenses and permits to collect the data
• Getting the right to permanently steward the data in the PLACE Trust, a legal data trust based in the UK
• Getting the right to license the data in the PLACE Trust to PLACE Members

PLACE also pledges not to compete with its Members. So they’re not going to build street map data or a land information systems from the imagery. In a sense they’ve taken a leaf out of TSMC’s book. TSMC pledges not to complete with its customers in the silicon chip manufacturing business¹.

All of this aligns the incentives and builds trust.

In return for getting the data at no cost governments are incentivized to provide the necessary approvals to allow the data collection to take place. For example: permits to land and fly specific aircraft or UAVs and notices to ministries of defense, air traffic control and to the police.

Getting these permits is often arduous, costly and time consuming, so incentivizing the governments to provide rapid approval is invaluable. Peter told me a story about another commercial aerial survey company that was kept waiting 110 days for their permits. Can you imagine the cost of having your plane and equipment grounded for almost 4 months? Ouch.

Second: As an organization PLACE is built on a principle of trust:

• Governments are screened and vetted before any data collection agreements are signed.
• Any third parties want to use the data must apply to become a PLACE Member. They also get vetted and screened.
• Terms of Use are subject to the LOCUS Charter, which defines a set of common international principles to support ethical and responsible practice when using location data.
• PLACE Members and governments must abide by these principles and must remain in good standing in order to maintain access to any data in the PLACE Trust. If governments don’t abide then they can say goodbye to any ongoing or future data collection. If PLACE Members don’t abide then they can say goodbye to data access.
• The data is collected by one arm of the PLACE organization called the PLACE Foundation, based in the USA. But the data is stewarded and licensed by a completely different legal entity called the PLACE Trust, based in the UK. In that way the data can continue to be properly protected even in the event of failure of the PLACE Foundation.

Third: The focus is on collecting data the right way, but done fast.

PLACE isn’t just collecting data using a few cheap DJI drones. They focus on photogrammetric rigor using the latest LiDAR and UltraCam aerial cameras. Mounted in Lear jets or Event 38 mapping drones, data can be collected at a rate of up to 5,000 square kilometers per hour.

PLACE’s framework is already proving its value:

In three short years (mostly during the global pandemic) PLACE is quickly gaining traction. They’ve signed agreements with nine countries including Ghana, Cote d’Ivoire, Turks and Caicos, Anguilla, Malawi and Kenya. Nigeria, with a population of 230 million, is the latest large country to join.

They’re finding that the PLACE framework is disintermediating data collection and eliminating the need for consultants to get the job done. For example no longer do you need someone to help you get permits. The framework’s incentives for governments short circuit all that.

The end result: rapid, high quality data collection that any organization in good standing can quickly put to use.

Show Me the Data

So what does the data look like?

Well, here’s PLACE Aerial data for a street intersection near the Plateau Mosque in Abidjan, Côte d’Ivoire:

And here’s the equivalent in Google Maps and Apple Maps:

Google and Apple generally strive for the best available commercial satellite data, so you can see that the PLACE Aerial data is significantly higher resolution and thus significantly more useful for determining things like property boundaries, land use, economic activity and population. And of course it’s more than good enough for building a street map.

The PLACE Aerial data has a ground sample distance (GSD) of around 5cm. The is an order of magnitude better than typically available commercial satellite imagery which has a GSD of 40-50cm.

But PLACE doesn’t stop at collecting aerial data. They also collect anonymized street level data. Here’s a sample of PLACE Ground data for Côte d’Ivoire:

Putting PLACE Data to Use

PLACE data is a horizontal bedrock for so many uses: for governments just to be able to create an accurate map of their communities is a godsend. It can form the basis for understanding population and land use. It can be critical to stimulating economic development, administering healthcare and eduction programs or for fairer and more efficient property tax collection.

For commercial organizations the uses are many. In the insurance industry the data can help people understand risks, particularly for flooding. The data is valuable for building construction and financial modeling. And of course the data is a foundation for consumer applications: mapping, wayfinding and business search.

The data can be used to build models — quickly and efficiently — whether it be vulnerability analysis models for flooding or heat from buildings, or transportation models for routing goods or population growth models to benefit urban planning.

And AI is only going to supercharge all this analysis.

In Africa in particular there is a desperate need for all this work. Populations are growing like crazy and economies are growing with it. For example, the population of Malawi is about 22M now but is expected to grow to 110M by 2050.

We should also expect many use cases for the data that people have yet to invent. Remember when iPhone launched in 2007? Who thought of Uber back then?

The same thing is going to happen in Africa. It has a population of 1.2B and the median age is only about 19. And despite what you might think, many of the young un’s are getting a good education — and many are super smart. So young African entrepreneurialism is going to drive growth: Africans creating businesses for Africans.

The potential is awesome. And it’s going to be fascinating to watch how PLACE Data is put to good use.

PLACE’s Biggest Fans

In its three years of existence PLACE has already built a fan base.

Esri is one. Obviously it fits with their secret evil plan of making sure everyone on the planet has an ArcGIS license, but in all fairness it actually perfectly aligns with Jack Dangermond’s sincere goal of wanting to make a difference.

Universities around the world love PLACE data for research as do many well known international agencies.

And then there are the organizations that help governments process data, understand it and gain insights from it. Many of these are development agencies, a.k.a. ‘beltway bandits‘ in Washington, DC or similar organizations in other parts of the world.

And of course AI companies like AtlasAI and Impact Observatory are loving what PLACE is doing.

PLACE has 52 Member organizations at the time of writing and they’re adding about two a week. And they have funding from a number of significant organizations including The Global Innovation Fund, The Dovetail Impact Foundation, The Rockefeller Foundation, The Omidyar Network and The Mozilla Foundation.

As word gets out about PLACE I can only imagine that membership and funding will snowball.

How Do You Access PLACE Data?

The PLACE business model is simple.

It’s US$1,000 per year to be a PLACE Member. This is considered tax deductible if you’re a US tax payer. If you’re feeling generous you are free to pay more than $1,000 per year if you’d like. 😉

If you want to use the data for non-profit or not-for-profit purposes then there is nothing more to pay, but PLACE’s preference is that derivative works get published under a Creative Commons license.

For commercial use there is a one-time data license fee for the data. The fee is based on the number of cities that are licensed and there are discounts for multiple cities. Updates for a city are treated like another city. For example, the fee for the data captured of Abidjan in 2024 might be $X. You’d pay $X again for the data captured of Abidjan in 2025.

Commercial licensees are not allowed to sublicense the data as is, but they are allowed to create derivative works and license those works for a fee. There are no revenue share requirements back to PLACE for derivative works.

Where Next for PLACE?

PLACE has achieved a huge amount in the three years they’ve been in existence:

• They’ve signed data collection deals with nine countries, including some large ones like Ghana, Kenya and Nigeria.
• They’ve got alignment with those countries to make sure the governments have the right incentives to work with them.
• With the PLACE Foundation and the PLACE Trust, they’ve got their organizational structures in place that will easily be able to deal with large scale data acquisition.
• They’re getting traction with membership
• They’ve got foundational funding from a number of significant organizations.

But they haven’t quite reached critical mass.

PLACE has yet to put enough data on-the-shelf to generate significant commercial revenue. And so they need more funding to get to that critical mass of data so they can be self sustaining. I’m convinced they’ll get there, but it’s going to take more work — and frankly more cash.

But it’s going to get even more interesting when they do reach critical mass. PLACE already has plans to leverage commercial revenues to subsidize capturing data in areas of need rather than just in areas of interest. In other words: using the licensing revenue they get from licensing data for high growth cities to fund capturing data in poorer areas.

Another interesting sidebar: Peter’s framework for PLACE, particularly its organizational structure built around trust (with the PLACE Foundation and the separate PLACE Trust), together with the built-in incentives and alignment for cooperation has got key people in other industries thinking: could the same model work well for healthcare data or agriculture data? Hmm. There’s a thought.

If you’d like to learn more about PLACE I’d strongly recommend visiting the PLACE website which is at thisisplace.org . Alternatively consider pinging Peter Rabley, Managing Partner of the PLACE Foundation or Denise McKenzie, Managing Partner of the PLACE Trust.

I can’t wait to watch PLACE going forward. I’m sure there will be some great surprises to come…

---

Acknowledgments and Footnotes

Acknowledgments:

My heartfelt thanks to Peter Rabley, Managing Partner of the PLACE Foundation as well as to Denise McKenzie, Managing Partner of the PLACE Trust for taking the time to talk to me and helping me to get to know and understand the PLACE organization.

It should be noted that PLACE took no part in sponsoring this article (and nor did anyone else for that matter).

Footnotes:

1. TSMC is the Taiwan Semiconductor Manufacturing Company. They manufacture silicon chips for the likes of Apple, NVIDIA and AMD. From day one they have steadfastly committed not to compete with their customers. According to TSMC: “Our mission is to be the trusted technology and capacity provider of the global logic IC industry for years to come.” ↩︎

A Curious Phenomenon Called ‘Etak’

Every once in a while, a revolutionary product comes along that changes everything. Or so said Steve Jobs when he announced iPhone in 2007.

But I’m talking about a different revolutionary product. A foundational product that forever changed how everyone on this planet gets to where they need to be.

Today, I’d like to tell you about the Etak Navigator, a truly revolutionary product and the world’s first practical vehicle navigation system.

Here’s a picture of it:

At the time, it was considered out-of-this-world. This is what Silicon Valley’s San Jose Mercury News said about it:

The Etak Navigator launched 39 years (!) ago in 1985. 😱

Back then Reagan and Gorbachev were negotiating the end of the cold war.

And it was the year Steven Spielberg released the film “Back to the Future”…

And I’m sure at that time many of you were but a twinkle in your mother’s eye…

Back in 1985 you used paper maps to navigate, like this one from a Thomas Brother’s map of Los Angeles:

As you can see, the maps weren’t always pretty. By today’s standards it was also supremely difficult and tedious to find locations and even more difficult to work out how to get there.

So, when the Etak Navigator launched, it was like something from the future.

It immediately got tons of press, including the front cover of Popular Science:

Nearly everything about the Etak Navigator had to be conceived from scratch.

Most important was the self contained positioning system. Remember that back in 1985 GPS was not available (see “12 Map Happenings that Rocked our World: Part 8 — Oh Brother, Where Art Thou?“)

Before GPS, navigation systems used a technique called ‘dead reckoning‘. Dead reckoning relied on sensors to determine distance traveled and direction of travel. However, no sensor is perfect. As a result the further you travel the greater the errors build. Pretty quickly you have no idea where you are.

To solve this problem Etak invented ‘augmented dead reckoning’. This used a process to match the position given by the navigation sensors to a topologically correct electronic map. Whenever the vehicle turned you made the assumption that you’re driving on a road. At that point the location could be ‘snapped’ back to the road and the error from the sensors could be reset. This technique was later adopted by all navigation apps and is still in use today.

Like all attempts at building a navigation system before it, without this key invention the Etak Navigator would have failed.

The second key invention was a ‘heading up’, moving map display. This meant that the vehicle remained at the center of the screen and the map moved and turned under the vehicle. What you saw ahead of you in the windshield was what was displayed on the screen. This proved highly intuitive.

Third: the Etak Navigator was also the first consumer device to introduce the concept of address search, or what the geospatial industry has come to call ‘geocoding’.

Here is a clip from the only video I could find of the Etak Navigator in action: 

As you can see the map moves and turns as the vehicle drives. 

The buttons on the right control the zoom level which is denoted as the number of miles between the vehicle symbol and the top of the screen. 

The top of the screen shows the current zoom level, the heading to the destination, the number of miles to the destination as the crow flies, and which way is north.

The address search allowed entry of destination by address, street or intersection. You could also store common locations like home and work.

The Etak Navigator had twelve buttons, six on each side of the screen. 

These were soft programmed depending on the current function.

In the screen below you can see how street names were entered. Note how any letter or digit could easily be entered with just two button pushes. Also, you only had to enter the first few letters of a street name:

And after that you simply selected the street from a list:

This is the Etak Navigator in navigation mode:

Note that the Etak Navigator did not provide turn-by-turn directions. Instead you simply zoomed out the map to see your destination, shown as a flashing star. As you got closer to the destination you zoomed in revealing more of the local roads. You had to use your own noggin to determine the most appropriate road to take.

The lack of turn-by-turn navigation did not prove to be an issue. I know from much personal experience that the system worked very well!

Etak Navigator System Details

There were five key components to the Etak Navigator:

The first was a vector CRT display — similar to what you might find in an oscilloscope.

The navigation app and data were stored on cassette tape. The cassette tape drive was specially developed to read the tape at very high speed. In a music player a cassette tape is read at about 5cm (1 and 7/8″) per second. The cassette tape in an Etak Navigator was read at about 200cm (80″) per second!

There was an electronic compass installed on rear window of the vehicle.

To determine distance traveled and to augment the heading info from the compass, magnetic wheel sensors were installed on the un-driven wheels of the vehicle. This involved sticking special magnetic tape on the inside of the wheels and mounting magnetic sensors on the brake calipers.

Finally there was metal box about the size of a shoe box that contained the CPU and motherboard. This was installed in the trunk.

The cassette tapes stored both the navigation app and the map data. The maps were called “Etak Maps”. It took 6 tapes to cover the San Francisco Bay Area:

The original price for the Etak Navigator was US$1,395:

That’s the equivalent of about US$4,000 today.

On top of the cost of the Navigator there was an expensive installation cost: it took an experienced technician about 4 hours to install the whole system.

Just Some of the Technical Hurdles

Back in 1985 there were huge technical constraints.

GPS barely existed. In those days the government prevented anyone but the military getting more than 100 meter accuracy. And GPS receivers were both large and expensive.

In addition there were no large capacity interchangeable media. Floppy disks couldn’t store enough information and CD-ROM technology was brand new and too costly. 

The most important problem to solve was overcoming inertial navigation error from the wheel sensors and the compass. 

Here the solution was topological map matching. 

This invention, above all others, made the product viable.

Another issue was data storage and latency. 

The cassette tapes only held 3.5 megabytes and had 10 second average seek times.

The dev team had to invent a way of storing the 2D map on a one dimensional medium, making sure that regions close by on the map were also close by on the tape. 

Years later, when hard drives became cheaper and CD-ROMs became more readily available Etak’s highly efficient map data storage algorithm paid off in spades and resulted in very high performance maps.

Another problem was heat. 

Users commonly left tapes on their dashboards and obviously dashboards can get very, very hot.

You can see from the tests that not all brands of cassette tape did very well:

However, a brand that worked was finally found. It had a shell made of polycarbonate.

Yet another problem was dealing with inclines.

The map had no elevation information and so if you were traveling up or down a hill errors would be compounded in the system as the distance traveled on the road was not equal to the distance traveled on the map.

To compensate we therefore needed to know the slope of the hill. To compute this Etak’s lead hardware engineer invented a special inclinometer that used fluid and a capacitive sensor. In tests on various fluids he found that Tequila worked quite well!

Another problem were magnetic anomalies. 

Bridges can be highly magnetic and can really throw off a compass. 

The positioning algorithm therefore had to recognize these anomalies. When an anomaly was detected the positioning instead relied on the different speeds of the wheels to determine changes in direction. It wasn’t quite machine learning, but at the time it seemed pretty close!

The system also had to compensate for the magnetic fields generated by the rear window defroster.

In 1985 there wasn’t the luxury of 25 billion transistors and an M3 chip.

Instead the system relied on an Intel 8088 CPU which had 8-bits, ran at 5MHz and only had 29,000 transistors. 

Thus every line of code had to be incredibly efficient. It was all written in C, except for key parts of the OS kernel which were written in assembly. 

What about the digital map?

Etak had to create it — more or less from scratch. 

Originally Etak thought it could get maps from the government. Back then the US Census Bureau had something called GBF DIME files (which predated TIGER). But they were stick maps and didn’t contain any shape to the roads. 

Etak therefore embarked on a massive program to build a map of key metropolitan areas across the US and later in Europe. 

To reposition the GBF/DIME files and give them some shape we used 1:24,000 scale United States Geological Survey quadrangle maps, otherwise knowns as ‘USGS quads’ as a reference. 

Each map was photographed onto 10” transparencies and then scanned using a very expensive drum scanner. 

The entire map production program was developed and ran on a single VAX minicomputer. This blazing machine had 2MB RAM and two 400MB hard drives. It cost about US$120,000 in today’s dollars.

This little devil was burdened with a mammoth set of tasks. It supported:

• 4 map digitizing workstations 
• The engineers developing and compiling code 
• Batch jobs to process and compile all the map data 
• The company admins who used it for word processing

This was the coding environment:

A dumb monochrome terminal. 

You edited code using the ‘vi’ editor. Sometimes you waited an hour for your programs to compile. 

The jobs to process the map data took up to two weeks to run … which was longer the the mean time between failure for the VAX mini-computer. The engineers used to joke that they should run the long jobs only immediately after a hardware failure had been fixed (knowing full well they were uttering a statistical fallacy).

The map digitizing environment was also revolutionary:

Each digitizing workstation was comprised of a PC clone with an 8-bit color graphics card and a 19” monitor. Initially there were four workstations which were manned by three shifts a day. Later this grew to 36 workstations. Etak digitized maps 24 hours a day, 5 days a week and 8 hours a day on weekends.

The map editing system was the first ever to use ‘heads up’ digitizing and was a huge trade secret at the time. It was so secret that the methodology was never patented and the digitizing environment was walled off from prying eyes — especially from the CEO of a particular company called ‘Environmental Systems Research Institute‘ — i.e. a gentleman called Jack Dangermond who I’m sure would have leapt at the chance to borrow the concept. 😉

Before this invention people used to digitize ‘blind’ using digitizing tablets which was highly inefficient and error prone.

Etak’s map production system leveraged the eight bits of the color graphics card very efficiently. 5 bits were used to display the scan of the USGS quad in greyscale and the other 3 bits were used to display the digitized map on top. The system was used to reposition the GBF/DIME files as well as to digitize new roads and edit road attributes like street names and addresses:

The Amazing Team Behind It

Etak was founded in 1983 by a truly amazing engineer, Stan Honey.

Stan was already a world renown sailor. More importantly he was a world class navigator and had already beaten many sailing records across the Pacific by relying on his navigation skills. 

Before founding Etak, Stan was a research engineer at SRI International in Menlo Park, California. 

Stan has gone on to do many things. His most recent achievement was as the director of technology for the America’s Cup sailing races where he developed a system to track the America’s Cup boats to within 2cm, five times per second!

The original idea for Etak came when Stan Honey and a serial entrepreneur, Nolan Bushnell, were on a sailing boat together. Nolan had hired Stan to navigate his racing yacht through the 1983 Transpacific Yacht Race, a prestigious sailing event that spanned 2,225 nautical miles of open ocean from Los Angeles to Honolulu.

Nolan was famous for inventing the first video game, Pong, and later for founding Atari.

The story is recounted by Benj Edwards in his fantastic article for Fast Company: “Who Needs GPS? The Forgotten Story of Etak’s Amazing 1985 Car Navigation System“:

[Early one morning Stan and Nolan were on night watch together.] They began brainstorming about a computer-based navigation system for use on land. Stan thought a navigation system for automobiles could operate based on dead reckoning and comparing one’s current location to known points on a map, a technique known as map matching. It wouldn’t need satellites at all, just a good digital map, a good compass, and some sensors. Then it could display the result on an electronic screen.

Nolan reaction:  “Yeah, let’s do that and I’ll fund it”

Nolan always had an appreciation for where consumer technology might eventually go. In an interview for Inc. magazine in 1984 he said “Let’s say you’re in your car, and you want to go to dinner. You’ve got this box on the dash. You punch in ‘Japanese,’ then ‘cheap,’ then ‘good sushi.’ The box takes over and guides you to a place.”

One of Etak’s key hires was Marv White. Marv was a map scientist and mathematician and worked at the US Census Bureau on their mapping program. 

Under Marv’s direction Etak’s map digitizing productivity was three times the industry standard. Since leaving Etak, Marv has gone on to many exciting ventures, including a period as Chief Technologist for Innovation at ESPN.

There were many other supremely talented engineers behind the Navigator, many of whom previously worked at SRI International: Ken Milnes, George Loughmiller and Alan Philips to name a few.

Many of the original hires at Etak went on to other mapping organizations, including yours truly. When I worked on the Apple Maps team, 12 of my colleagues were Etak alumni.

So What Happened to Etak?

The Etak Navigator was about 20 years ahead of its time. Due to the cost of the hardware and the expensive installation process building a sustainable business proved to be very difficult (sound familiar?)

Instead Etak quickly pivoted. It licensed the navigation code to the biggest automotive OEM hardware manufacturers at the time: Robert Bosch in Germany, GM in the USA and Clarion in Japan. In turn these companies developed their own navigation systems and, many years later, the concept of a ‘Personal Navigation Device’ from the likes of Blaupunkt, Garmin, Magellan, TomTom and many others was born.

During the course of doing business Etak attracted the attention of a perhaps an unusual suitor: Rupert Murdoch’s News Corporation. It was News Corps’ John B. Evans that saw the potential.

Like Nolan Bushnell, John was a supreme visionary. You would often find him on the same platforms as Intel’s Andy Grove, Bill Gates and other technology megastars. Albert Scardino and Matt Falloon recount the story in John’s obituary in the Guardian:

The defining deal of [John’s] career came in the mid-1980s. In 1985, Murdoch invested $350m in a group of travel publications and directories. With one hand, Evans took over the consumer magazine division of Murdoch’s US organisation, including TV Guide, Elle and one he himself invented, Automobile. With his other hand, he launched a secret project in a suburban office building to develop a part of the travel group, the Hotel and Travel Index, into a new media product, codenamed Jaguar.

In the days before streaming video and large file capacity on the internet, travellers’ views of their hotels and destinations were limited to tourist brochures. Jaguar allowed an electronic visual tour of destinations, complete with views of the hotel room they had booked. Once integrated with major airline booking information and other databases and cross-referencing tools, the system threatened to leapfrog other airline, car and hotel reservation systems.

It was thus that John had the vision to use Etak’s maps and technology to benefit the Jaguar system. Thus John convinced Rupert to buy Etak.

Stan Honey recounts the conversations:

John instantly saw the power of maps in media to change the world of classified ads, yellow pages, travel, and broadly answer the questions of “where is the nearest?” and “how do I get to it?”.  Naturally, John and my shared sailing background created an instant group of common friends and experience.  I remained close friends with John until he passed away and visited him often.  Long after John had left News Corp, whenever I was tee’d up in New York waiting for a weather window for a Transatlantic record attempt under sail, I’d always invite John to come visit the boat, which he found fascinating as the boats were 100 foot monohulls or multihulls.  I doubt that Etak would have ever appeared on Murdoch’s radar screen without John Evans’ vision and commitment to his vision, and to Etak.  At the time of his decision to buy Etak, Murdoch also asked Barry Diller, who was then running Fox, for his opinion.  Barry Diller was hard-nosed and direct in his questions, and had a slightly shorter term vision than did John, but Barry also supported News Corp’s acquisition of Etak, and focus on the maps.

John really was a long-term visionary, as was Nolan Bushnell.  During the Etak days, both would visit and “wind-up” the Etak crew with their predictions.  That was very helpful as the two of them kept our minds wide open.  But it was also helpful that they would mostly stay away because we were burdened with the need to actually get things to work, which visionaries seldom are.  It is interesting to note that all of the things that Nolan and John predicted, have happened.  It is also interesting to remember how far-fetched they seemed at the time of their visits.

But the times there are a changin’: as fate would have it in 1989 Murdoch sold the Jaguar system to Reed International for a profit of $500M. With Jaguar sold the relevance of Etak to New Corp lessened.

News Corp subsequently sold Etak to SONY, who then later sold it to Tele Atlas. And still later Tele Atlas was subsumed by TomTom. So what was originally Etak is now TomTom:

But Why the name ‘Etak’?

The answer goes back to the early days of Polynesian navigation. In those days the ancient mariners navigated the seas by relying on a series of environmental cues, such as the positions of islands around them. 

They imagined that that their boats were stationary and that the islands moved past them.

In the same way, in the Etak Navigator the vehicle is stationary and it’s the maps that move past the vehicle…

With that in mind, Stan decided to call his company Etak, which is a Polynesian term for moving navigational reference points.

But Wait, There is One More Thing…

When you look at any consumer mapping app in navigation mode, have you noticed something?

Have you noticed something about the symbol used to denote vehicle location?

Does it look familiar? Well, of course it does …

So it turns out the symbol used by all navigation apps today is the same one originally invented by Etak.

But why did Etak use that particular symbol?

If you talk to the engineer who wrote the original code, George Loughmiller, he’ll be meek and tell you that it seemed like a good idea at the time. But you have to remember one thing: Etak was incubated by Nolan Bushnell, founder of Atari. And at that time both Etak and Atari were housed in the same office building at 1287 Lawrence Station Road in Sunnyvale, California.

Because Etak used a vector display with limited CPU, George needed a symbol that didn’t burden the very scarce computing resources. He also needed a symbol that was easy to read. A traditional symbol for a car — 🚗 — required too many lines. It also didn’t clearly connote direction. Something simpler was needed. 

Legend has it that one of Etak’s engineers got to see a pre-release demo of one of Atari’s latest games. And that game was…

And what symbol did Asteroids use for their spaceship?

And thus the symbol for vehicle navigation was born and is still used by all navigation apps globally today:

So There You Have It…

Every once in a while, a revolutionary product comes along that changes everything.

Etak’s many significant inventions included:

• the world’s first in-vehicle nav system that actually worked
• augmented dead reckoning using map matching
• moving map heads up display
• first use of geocoding in a consumer application
• algorithms for highly efficient map data storage and retrieval  
• heads up digitizing
• the world’s first high volume digital map production system
• inventor of the universal map navigation symbol

I was but a pimply engineer at the time. Little did I know when I joined Etak in 1985 that I was going to be part of such an illustrious team.

My hats off and best wishes to everyone I worked with: it was a privilege, an honor and an amazing journey. Thank you.

---

Acknowledgements, Further Reading & Watching

• Stan Honey, Marv White and the rest of Etak team
• Benj Edwards: “Who Needs GPS? The Forgotten Story of Etak’s Amazing 1985 Car Navigation System” (2015, Fast Company)
• Popular Science Article from June 1985: Credit: Stan Honey and Popular Science Magazine
• The Etak Business Plan: May 10, 1984: Credit: Computer History Museum
• Rare and interesting documents about Etak: Credit: Computer History Museum
• Etak Innovations: Credit: Stan Honey
• Etak’s Initial Product Brochure from 1985: Credit: Stan Honey
• Paper presented at the Royal Institute of Navigation meeting in York 1985: Credit: Stan Honey
• Etak Navigator Tour & Demo: Credit: EllsworthC on YouTube: