It didn't use GPS or any sort of pre-fabbed maps. It drove purely by eye / machine vision using four cameras. No radar or lidar.

I'm asking, specifically, what machine vision technology it used? In 1994 there wasn't much machine vision (that I'm aware of) that would even be able to do lane-keeping, except under incredibly idealized conditions (empty roads, no weather, good lighting). If so, I would request that whomever claimed this guy invented the self driving car temper their claim.

Here is what someone on the project had to say about it:

>Our vision system relied (heavily, not exclusively) on sensing prominent horizontal features symmetric about a common centerline. (Cars and trucks, especially at the time, have a lot of horizontal lines: bumpers, window top/bottom, valence, etc.)

Thread here: https://news.ycombinator.com/item?id=10328687

Ah! Yes, I also watched the video and I see they are identifying little "cups" (one horizontal line and two vertical).

Bridges also have many hoizontal features symmetric about a common centerline. I would expect many false positives driving near bridges.

I do believe they DID use a radar system. A HN user that worked on the project did mention something about using such a sensor.

The linked video states they could recognize obstacles years later, so I think there was no reading of signs etc. involved. It must have been only lane mark recognition that was used to steer.

The van from the vid came years after the two mercedes s cars. I think there was no breaking for obstacles, exiting the highway, or even using interchanges. It was simply holding a lane (maybe change it when told to) and holding a set speed.

Correct me if I am wrong, as I did not read into the experiment.

https://www.youtube.com/watch?v=I39sxwYKlEE

OK, if this is correct, then I wouldn't call this a self-driving car, or basically it was L1.

Not interesting, and frankly, takes away from the dramatic results of recent self-driving cars.

This does not seem to be the case. Check out this guy that worked on the project:

https://news.ycombinator.com/item?id=10333126

The had auto-breaking, car detection and lane merging the least.

The text you linked to isn't very convincing for any of those. it describes a false positive that nearly caused an injury to the head of the project.

I think it's safe to say that while this was pioneering work, none of the technology it used was acceptable in terms of safety or generalizability.

I said they had those functionalities, never claiming they had neither a perfect track record nor something comparable with what we have today.

I pointed that those functionalities existed and presumably sometimes worked, as opposed to OP that said they did _not_ have them. At the very least, the false positive proves they had emergency breaking.

What I find amazing is what they managed to do with much less powerful HW than what we have today, with much more primitive camera systems. To put it into context, the project is older than I am and they managed to achieve things that most of my live until pretty recently I would have categorized somewhere between amazing and impossible.

They had emergency braking... which just means applying the brakes. If you false positive emergency brake, that's worse than doing nothing (increased risk of crash, integrated over a wide range of possibilities).

My concern is that this article massively overstates the results that Dickmanns had in a way that implies his work had any real chance of being used in a production environment. There is a substantial difference in the sorts of Probabilistic systems that Thrun and others build today.

Whether today’s approaches are acceptable in these terms also remains to be seen.