News for hackers. Stuff that matters.
Re:Third fatal Tesla Autopilot crash renews questions about ... by Animats on Friday May 17, 2019 @12:48AM (#19936394)
This is the third known FATAL US autopilot crash. There are other non-fatal crashes. Many with video.

Fatal crash in China: [1] Rammed into street sweeper at full highway speed.

Non-fatal crash in California.[2] Rammed into fire truck stopped on freeway.

Tesla's system does not detect big solid objects in front of the vehicle. It's "recognize rear of car", then "brake for car". No recognition, no braking. Machine learning at its finest.

I know, I've posted this before, but I keep seeing denial.

[1] https://www.youtube.com/watch?v=fc0yYJ8-Dyo

[2] https://abcnews.go.com/Technology/utah-driver-slammed-tesla-...

Re:Third fatal Tesla Autopilot crash renews questions about ... by Cthulhu_ on Friday May 17, 2019 @05:51AM (#19937935)
I use Waze during my daily commute and it regularly gives me a warning about a stopped vehicle on the road or side of the road; would a crowdsourced system like that help for autopilot so they change their algorithms slightly to detect stopped vehicles more better? Or just reduce speed? Or alert the user and disable autopilot well before the location?

I'm aware that would be creating an exception for an exceptional situation and not really a root cause solution, but still.

Re:Third fatal Tesla Autopilot crash renews questions about ... by yifanl on Friday May 17, 2019 @07:54AM (#19938627)
I'd be extremely extremely hesitant to throw on more dependencies for life-death scenario handling.
Re:Third fatal Tesla Autopilot crash renews questions about ... by londons_explore on Friday May 17, 2019 @10:09AM (#19939738)
"Unfortunately my son didn't pay his Verizon bill on time, so they cut him off and since his car couldn't get updates it rammed him into a fire truck".
Re:Third fatal Tesla Autopilot crash renews questions about ... by Aromasin on Friday May 17, 2019 @04:34AM (#19937492)
My experience with machine learning and vision systems amounts to one lab assignment a few years back, so forgive me if this is a stupid question - but why is there not a 'complementary' hard coded system built in that can override cases like this? I can think of no reason as to why stopping a car driving full speed into an inanimate object would be a thing that a human can't code. Surely there must be something in place - an "if(hurtlingTowardsWall){ignoreAI; stopCarQuick;}".
Re:Third fatal Tesla Autopilot crash renews questions about ... by hnaccy on Friday May 17, 2019 @04:39AM (#19937524)
How do you know there's a stopped object in front of you?
Re:Third fatal Tesla Autopilot crash renews questions about ... by knorthfield on Friday May 17, 2019 @04:46AM (#19937572)
Don't the Tesla have forward facing radar?
Re:Third fatal Tesla Autopilot crash renews questions about ... by w0utert on Friday May 17, 2019 @05:05AM (#19937682)
Traditional radar is bad at spotting stationary or slow moving objects, and to avoid false positives at every traffic sign or other stationary object above or next to the road, any radar-based object detection has to be tuned conservatively or the car would be flipping out all the time.

That’s why other companies use lidar, which is much better at object detection, but has its own problems (like fog or heavy rain, for example)

Re:Third fatal Tesla Autopilot crash renews questions about ... by jcims on Friday May 17, 2019 @05:30AM (#19937814)
Stationary objects are very detectable with radar as they have relative motion to a moving vehicle. Also objects with no relative motion are only tricky for CW doppler radar.

The issue is mostly your last point. The radar sensors used have low resolution and would have trouble distinguishing a turning semi from an overhead sign.

Re:Third fatal Tesla Autopilot crash renews questions about ... by Someone1234 on Friday May 17, 2019 @09:57AM (#19939635)
Parallax via optical cameras. Like the human eye or Subaru's Eyesight.