Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why collision avoidance is harder for an AI-based system

medium.com

Post reply on HN
Print view View original

41–50 of 145 posts

Re: Why collision avoidance is harder for an AI-based system

#41

Post by phyzome »

decacorn wrote: post #6
mtgx wrote: post #3

I don't know what would have happened if "this guy programmed it", but the answer should be yes , the car should have seen the cyclist and it should have pressed the brakes. This was an interesting post, too, by Brad Templeton who worked on Google's self-driving car project for a while: http://ideas.4brad.com/almost-every-thing-went-wrong-uber-fa...

in response to that piece by Brad, I sincerely hope that the "safety" driver in the uber accident was fired.

The safety driver is basically irrelevant, beyond being a scapegoat. I've written up some words on this: https://www.brainonfire.net/blog/2018/03/23/safety-driver-sh...

Re: Why collision avoidance is harder for an AI-based system

#42

Post by wnoise »

martinrebane wrote: post #32
jdmichal wrote: post #2

> AI is not preprogrammed to monitor a known input from a sensor to take a predefined action. I guess one of my outstanding questions, which reading this only confirmed, is why this is the case? I mean, humans are pretty good examples of intelligence. And yet we still have and use these anti-collision systems. Because, in the end, when wrong decisions are made these systems save lives. Why would AI-driven vehicles no…

Author here :) I cannot answer for Uber, but the grand reason why we cannot put deterministic parts into the AI is the same as for humans - we do not control the internals of it, the complexity is too high. Although we can build systems that are composed of both AI and deterministic collision avoidance (as seen on new cars today). It is what I also suggested in the article.

Ah, then I should complain to you that "AI" is a broad suite of techniques and goals, rather than a specific black-box technique which has these flaws.

Re: Why collision avoidance is harder for an AI-based system

#43

Post by wnoise »

martinrebane wrote: post #34
SlowRobotAhead wrote: post #5

Has anyone been able to even remotely explain why the LIDAR system wasn't going nuts? I saw the "it was dark" nonsense, but I assume this vehicle had laser and IR right? The camera footage was released, I'd like to see the lidar representation.

Author here :) LIDAR itself is just a sensor, it does not process the data nor does it output a directly usable image like a camera more or less does. LIDAR in this case is a rotating laser and while it scans, the vehicle moves (imagine moving a paper when a copier scans it). All processing is done later, first to construct an image and then to understand and use it. Part of why I wrote the piece was to explain how t…

You don't have to "construct an image" to use LIDAR returns. Minimal processing on the point cloud will tell you that there's an obstacle, and you don't need more than that to start trying to avoid hitting it. A simple occupancy grid map, for instance, would suffice.

https://en.wikipedia.org/wiki/Occupancy_grid_mapping

Re: Why collision avoidance is harder for an AI-based system

#44

Post by hangonhn »

Hang on. That argument makes no sense. We've had subsumption architecture for a long time now( https://en.wikipedia.org/wiki/Subsumption_architecture ). Subsumption architecture puts some of the intelligence in the lower level systems. While the higher level controls can tell the lower level systems what it wants, it can't do things that the lower system determines is dangerous.

So if a normal Mercedez has a collision avoidance system that automatically brakes, there is no reason why an AI based system can't be built on top of that and the collision avoidance system automatically braking without intervention from the higher AI systems. A subsumption system prevents higher level controls from doing something catastrophic like hitting a pedestrian or, in biology, a person holding their breath until they die.

Re: Why collision avoidance is harder for an AI-based system

#45

Post by btrettel »

hangonhn wrote: post #44

Hang on. That argument makes no sense. We've had subsumption architecture for a long time now( https://en.wikipedia.org/wiki/Subsumption_architecture ). Subsumption architecture puts some of the intelligence in the lower level systems. While the higher level controls can tell the lower level systems what it wants, it can't do things that the lower system determines is dangerous. So if a normal Mercedez has a collisio…

As I was skimming the article, I was thinking some sort of system like this could be made, and I was pleasantly surprised to see the approach has a long history. This is one reason I like Hacker News.

Re: Why collision avoidance is harder for an AI-based system

#47

Post by nabla9 »

wnoise wrote: post #43
martinrebane wrote: post #34

Earlier quoted context omitted.

Author here :) LIDAR itself is just a sensor, it does not process the data nor does it output a directly usable image like a camera more or less does. LIDAR in this case is a rotating laser and while it scans, the vehicle moves (imagine moving a paper when a copier scans it). All processing is done later, first to construct an image and then to understand and use it. Part of why I wrote the piece was to explain how t…

You don't have to "construct an image" to use LIDAR returns. Minimal processing on the point cloud will tell you that there's an obstacle, and you don't need more than that to start trying to avoid hitting it. A simple occupancy grid map, for instance, would suffice. https://en.wikipedia.org/wiki/Occupancy_grid_mapping

The problem with naive occupancy grid mapping from sparse LIDAR data is that things like birds, falling leaves, pieces of paper of plastic bags flying in the wind can mark the grid occupied.

Emergency breaking for all these cases would be very dangerous. The same object must be scanned multiple times to get the idea if the object is something to be avoided.

Re: Why collision avoidance is harder for an AI-based system

#48

Post by saetaes »

hangonhn wrote: post #44

Hang on. That argument makes no sense. We've had subsumption architecture for a long time now( https://en.wikipedia.org/wiki/Subsumption_architecture ). Subsumption architecture puts some of the intelligence in the lower level systems. While the higher level controls can tell the lower level systems what it wants, it can't do things that the lower system determines is dangerous. So if a normal Mercedez has a collisio…

Doesn’t the author recommend exactly that in the last sentence of the article?

Re: Why collision avoidance is harder for an AI-based system

#49

Post by jvanderbot »

hangonhn wrote: post #44

Hang on. That argument makes no sense. We've had subsumption architecture for a long time now( https://en.wikipedia.org/wiki/Subsumption_architecture ). Subsumption architecture puts some of the intelligence in the lower level systems. While the higher level controls can tell the lower level systems what it wants, it can't do things that the lower system determines is dangerous. So if a normal Mercedez has a collisio…

Yep! Every single autonomous system I'm aware of (and that I'm allowed to speak about) has such a system designed in from the ground up. The article presupposes we allow "intelligence" handle all decision making, which seems ridiculous even in biological systems, let alone those we design for a single purpose.

Re: Why collision avoidance is harder for an AI-based system

#50

Post by wnoise »

nabla9 wrote: post #47
wnoise wrote: post #43

Earlier quoted context omitted.

You don't have to "construct an image" to use LIDAR returns. Minimal processing on the point cloud will tell you that there's an obstacle, and you don't need more than that to start trying to avoid hitting it. A simple occupancy grid map, for instance, would suffice. https://en.wikipedia.org/wiki/Occupancy_grid_mapping

The problem with naive occupancy grid mapping from sparse LIDAR data is that things like birds, falling leaves, pieces of paper of plastic bags flying in the wind can mark the grid occupied. Emergency breaking for all these cases would be very dangerous. The same object must be scanned multiple times to get the idea if the object is something to be avoided.

Quite true -- but LIDAR has a very high refresh rate, and it's not hard to do better than naive grid mapping. This was a full height pedestrian plus bicycle, which would have multiple nice returns from a Velodyne HDL 64 at these distances.
Post reply on HN