I wonder how much of this is trouble perceiving water depth vs integrating that understanding into the larger driver model without creating regressions elsewhere.
Waymo pauses Atlanta service as its robotaxis keep driving into floods
71–80 of 498 posts
Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods
#72Driving through an obviously flooded street thinking "I'll easily make it" and getting stuck in the middle? Yeah, these cars have achieved human level intelligence.
Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods
#73I assumed they went to Miami to develop their foul weather capabilities. It's still pretty early.
These self-driving companies have made very little progress on dealing with weather for how long they’ve spent on the problem.
Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods
#74Earlier quoted context omitted.
A frontal cortex isn't enough; there are plenty of corner cases that humans fail at too. The real test is if self-driving performs on par, or better than, humans in the vast majority of cases. If it saves 50,000 lives a year to go with self-driving, it's a net-win even if there are a few people who die in situations where they would have survived with a human driver behind the wheel.
Self driving cars are not going to be accepted if they have only marginally better success rates than humans. Just look at the news. Every minor self driving incident is endlessly magnified by the media while millions of human-caused accidents are just a part of life. That's just how our brains work. All major decisions are made primarily based on emotion, not analytics.
Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods
#75I wonder how much of this is trouble perceiving water depth vs integrating that understanding into the larger driver model without creating regressions elsewhere.
I don't think there's a good solution right now. You can't just go based on surrounding traffic because humans are also stupid and flood their cars all the time. You could maybe use short-wave infrared cameras combined with ground penetrating radar, but it'll get real expensive so probably not commercially viable. I think the only "good" solution is to have the car be overly paranoid, and if it detects water on the r…
If you can’t handle this issue, you really can’t operate in Atlanta.
Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods
#76I wonder how much of this is trouble perceiving water depth vs integrating that understanding into the larger driver model without creating regressions elsewhere.
I don't think there's a good solution right now. You can't just go based on surrounding traffic because humans are also stupid and flood their cars all the time. You could maybe use short-wave infrared cameras combined with ground penetrating radar, but it'll get real expensive so probably not commercially viable. I think the only "good" solution is to have the car be overly paranoid, and if it detects water on the r…
Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods
#77Earlier quoted context omitted.
Ironically, a properly sealed EV system would better deal with a flood. Combustion engines have issues due mostly to the air intake and exhaust.
You'd need to ensure every electrical connection is in a waterproof location which I'm pretty sure is not a thing for any standard car manufacturing. Cabins are also rarely watertight. AFAIK your best bet is a diesel with a snorkel, and hope things have dried off before you need to restart the engine.
Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods
#78Earlier quoted context omitted.
Ironically, a properly sealed EV system would better deal with a flood. Combustion engines have issues due mostly to the air intake and exhaust.
Are EVs typically "sealed" by default? If not, how is going through the effort to "seal" an EV different than installing snorkels for ICE cars?
Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods
#79I wonder how much of this is trouble perceiving water depth vs integrating that understanding into the larger driver model without creating regressions elsewhere.
I don't think there's a good solution right now. You can't just go based on surrounding traffic because humans are also stupid and flood their cars all the time. You could maybe use short-wave infrared cameras combined with ground penetrating radar, but it'll get real expensive so probably not commercially viable. I think the only "good" solution is to have the car be overly paranoid, and if it detects water on the r…
If the apparent road surface is higher than the mapped ground surface, probably a puddle. If your point cloud has a big hole, also probably a puddle.
This assumes you aren't doing ground plane removal, of course. But it's quite likely that Waymo is using a heavily ML approach these days, and I can imagine the poor thing getting very confused if it's not an explicit training goal.
Re: Waymo pauses Atlanta service as its robotaxis keep driving into floods
#80Driving through an obviously flooded street thinking "I'll easily make it" and getting stuck in the middle? Yeah, these cars have achieved human level intelligence.