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

81–90 of 145 posts

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

#81

Post by couchand »

SlowRobotAhead wrote: post #4
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…

>I mean, are we going to also remove ABS, because the AI could learn to modulate the brakes itself? This is the topic that I feel SDC enthusiasts forget. Not everything HAS TO BE AI. And we could maybe make steps towards SDC, not fantastic leaps that get people killed and really just get government involved where it doesn't need to be yet. We could replace the ABS/ESP/traction control systems in current vehicles with…

> Ideally, at first, we'd see components in consumer vehicles

We do, though. Look at the cruise control or auto-park on a vehicle produced in the last few years. The totally autonomous car may make headlines, but these sorts of features will be what really make the technology ubiquitous.

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

#82

Post by couchand »

natch wrote: post #24

I'd like to see a law that says: to obtain certification to operate a self-driving car on a roadway, an organization must agree to: 1) Conform to a standard set of protocols for how sensors provide data to a self-driving software system. 2) Log data in a form that could be submitted to any conforming self-driving software system, to obtain results from that system reporting what the system would do given these inputs…

Oh no, we could never have that. It would squash innovation! We can't possibly have any regulation of self-driving cars or we'll lose to China.

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

#83

Post by wnoise »

ams6110 wrote: post #76
jmalicki wrote: post #61

Earlier quoted context omitted.

" I mean, are we going to also remove ABS, because the AI could learn to modulate the brakes itself?" I think that's a reasonable definition of ABS - an AI (in most cases for ABS, an expert system AI) that knows how to best mediate the brakes, with levels of performance that exceed the vast majority of humans.

The conventional ABS system is not AI in any sense. It is a few sensors and maybe some look up tables of what to do under various speed / brake pressure / wheel rotation situations

That doesn't make it not an AI -- it makes it a very simple, explicable AI. Unless you follow the definition that AI is whatever we don't know how to program yet.

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

#84

Post by philwelch »

Animats wrote: post #65

This is looking at it all wrong. Watch Chris Urmson's video from SXSW on how Waymo does it. I've mentioned that before. You build a map of what's around the vehicle. Then you try to tag some obstacles to help predict their behavior. But the obstacle detection is geometric, and does not depend on the tagging, which uses machine learning. If there's an obstacle, the system doesn't hit it, even if it has no clue how to…

Devils advocate here, but what if a supposed “obstacle” is a plastic bag or a jet of steam coming out of a sewer grate?

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

#85

Post by bkanber »

wffurr wrote: post #16

They should release all of their sensor data and logs from the incident, and then some of us could actually answer the question in the headline. This should be standard procedure for any future incidents.

The NTSB has control of the investigation and the data for now. That should be standard procedure IMO.

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

#86

Post by dreamcompiler »

I am freaking sick of this notion that AI==ML. AI is a much bigger field than neural nets. AI can be programmed with rules, with logic, with symbols, with subsumption, and with a thousand other things that are both deterministic and don't require huge training sets.

If you're making a living doing AI, you damn well should know this.

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

#87

Post by dreamcompiler »

philwelch wrote: post #84
Animats wrote: post #65

This is looking at it all wrong. Watch Chris Urmson's video from SXSW on how Waymo does it. I've mentioned that before. You build a map of what's around the vehicle. Then you try to tag some obstacles to help predict their behavior. But the obstacle detection is geometric, and does not depend on the tagging, which uses machine learning. If there's an obstacle, the system doesn't hit it, even if it has no clue how to…

Devils advocate here, but what if a supposed “obstacle” is a plastic bag or a jet of steam coming out of a sewer grate?

Then you stop. Type 2 errors for cars are much less dangerous than Type 1 errors.

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

#88

Post by smileysteve »

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.

Birds, plastic bags, cardboard boxes, small pieces of wood, and pieces of tires are perfectly good reasons to apply brakes and drive with caution to avoid.

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

#89

Post by randomdata »

ams6110 wrote: post #76
jmalicki wrote: post #61

Earlier quoted context omitted.

" I mean, are we going to also remove ABS, because the AI could learn to modulate the brakes itself?" I think that's a reasonable definition of ABS - an AI (in most cases for ABS, an expert system AI) that knows how to best mediate the brakes, with levels of performance that exceed the vast majority of humans.

The conventional ABS system is not AI in any sense. It is a few sensors and maybe some look up tables of what to do under various speed / brake pressure / wheel rotation situations

Does that not fit the definition of artificial intelligence? The system makes decisions – ones that would be otherwise done by a human – based on its perception of the world. That is what I have always understood AI to mean. To be sure, a conventional ABS system does not use machine learning, but machine learning is only a subset of AI.

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

#90

Post by taneq »

Gibbon1 wrote: post #71
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…

That sort of thing is common in industrial controls. Start the big ass air compressor and if the oil pressure doesn't hit 100 psig in five seconds the interlock trips. That's handled by a controller on the pump itself. Also really common or required that the interlock be totally separate from the control system.

Agreed. You use the lowest-tech option which is practical at every stage. So if you have a mechanism which can travel between points A and B and will cause damage if it leaves that range, your best option is a physical stop at each end. Second best option is a hard-wired limit switch at each end which cuts motor power. Third best is a limit switch which is used by software. You wouldn't use machine vision or LIDAR.

And then as you say, safety related functions (anything on which human life depends) need to be separate from general control code and to meet the requirements of whatever safety spec you're working to (e.g. SIL).

Post reply on HN