Do people really think this will replace all newly licensed drivers in less than 15 years?
Driverless robotaxi fleet paralyzed for hours in San Francisco
401–410 of 514 posts
Re: Driverless robotaxi fleet paralyzed for hours in San Francisco
#402Earlier quoted context omitted.
Dead reckoning works surprisingly well at least in Teslas, of which the precision can be seen when they move around in underground facilities and finally resurface: the car pops up pretty close to the entry point. In any case, aren't all self-driving vehicles equipped with lidars and work in pre-mapped regions? I would 100% expect they are able to just use those maps with lidar to precisely geolocate themselves, prob…
> aren't all self-driving vehicles equipped with lidars I believe Tesla has made a lot of noise about not using lidar.[0] [0]: https://venturebeat.com/2021/07/03/tesla-ai-chief-explains-w...
Maybe at some point in the future, but Teslas aren't self-driving vehicles: you always need a driver in them, even (or maybe even: more so) in the case of FSD Beta.
I imagine these robotaxi vehicles would not have stayed on the road had they have had a safety driver in them :).
Re: Driverless robotaxi fleet paralyzed for hours in San Francisco
#403In 40 years time, we'll be taking to the streets in joy and laughter, wiping the tears from our eyes, when the robotaxi fleet is finally paralyzed completely.
Re: Driverless robotaxi fleet paralyzed for hours in San Francisco
#404Earlier quoted context omitted.
It couldn't possibly be GPS, right? Networks are unreliable, the cars must be able to reach a safe state if the network drops out. They appear to have stopped in the road. If these cars can't safely navigate their way to the side of the road using local sensors, they are wildly, hilariously unsuited for autonomous operation. > at least a dozen autonomous Chevrolet Bolts from GM Cruise Automation were spotted blocking…
Yeah they have Lidars for 10s of 1000s of $ mounted and should be able to go for certain distances without GPS. If a GPS outage was designed as failure mode. But it would perhaps be one of the later items on any engineer‘s priority list since it is so reliable.
A network failure is, like, the world's most predictable problem though.
Re: Driverless robotaxi fleet paralyzed for hours in San Francisco
#405Earlier quoted context omitted.
It couldn't possibly be GPS, right? Networks are unreliable, the cars must be able to reach a safe state if the network drops out. They appear to have stopped in the road. If these cars can't safely navigate their way to the side of the road using local sensors, they are wildly, hilariously unsuited for autonomous operation. > at least a dozen autonomous Chevrolet Bolts from GM Cruise Automation were spotted blocking…
You've nailed the dirty little secret of the AV industry. Everyone's safety model is underpinned by the ridiculous assumption that a human will be (a) reachable with very high reliability over shitty cellular networks; (b) able to correctly interpret complex situations with extremely limited information; (c) able to resolve safety-critical situations by making planner adjustments, without direct control over steering…
For some reason I thought these were supposed to be real products, that sounds more like they are still in the prototype/proof-of-concept phase.
Re: Driverless robotaxi fleet paralyzed for hours in San Francisco
#406Earlier quoted context omitted.
Fsd isn’t as hard when you have tons of LiDAR cameras, radar, and super high definition mapping. Tesla is the only one working on real world FSD that doesn’t rely on all that stuff
It’s almost like a problem is solvable when you have the right tools and technology.
It’s easy to solve problems in the lab. Getting it out in the real world with mass manufactured products is the hard part. You cannot scale FSD with high precision mapping and expensive cameras worldwide. Every time there’s a road update or repair, those maps need to be updated.
If you seriously think Tesla is ignorant here, you are not paying any attention. Elon musk’s SpaceX has patents on LiDAR they’ve developed for their rockets, it’s not like they don’t use them and are not aware of their strengths and weaknesses
Re: Driverless robotaxi fleet paralyzed for hours in San Francisco
#407I am just wondering how many people have to die before it finally dawns on on us that the current approach is idiotic. The supposed smart cars can't even talk to each-other directly 'without internet' to warn of a car pileup! They can't report to city traffic control about their condition. We should be innovating in infrastructure instead - create standardised computer readable infrared road markings, equip each traf…
>>The supposed smart cars can't even talk to each-other directly 'without internet' to warn of a car pileup! They can't report to city traffic control about their condition.
- This by far in my opinion is the single most important attribute of any autonomous fleet of vehicles that is needed. There should be first of all a standard of communication via RFC defined for autonomous vehicles and drones. Any vendor manufacturing autonomous vehicles or drones should follow this standard of communication and be able to communicate to each other with the primary objective of avoiding collisions. This should be a RFC so that it works across vendors and is as standardized as TCP/IP. Communication medium can be over radio frequencies as well as the internet and can work as backup of each other but first there should be a established standard that all vendors adheres to.
Re: Driverless robotaxi fleet paralyzed for hours in San Francisco
#408I am just wondering how many people have to die before it finally dawns on on us that the current approach is idiotic. The supposed smart cars can't even talk to each-other directly 'without internet' to warn of a car pileup! They can't report to city traffic control about their condition. We should be innovating in infrastructure instead - create standardised computer readable infrared road markings, equip each traf…
You're describing exactly the kind of autonomous car development that was going on for the last 40 years. It went absolutely nowhere. It wasn't until tech got good enough and developers started treating vehicles as independent agents that any real progress has been made.
Re: Driverless robotaxi fleet paralyzed for hours in San Francisco
#409Earlier quoted context omitted.
You've nailed the dirty little secret of the AV industry. Everyone's safety model is underpinned by the ridiculous assumption that a human will be (a) reachable with very high reliability over shitty cellular networks; (b) able to correctly interpret complex situations with extremely limited information; (c) able to resolve safety-critical situations by making planner adjustments, without direct control over steering…
Wow. I had no idea that these things had such fundamental limitations. I'd feel a lot less safer using one now, to be honest. If you had to estimate, how long would it be before AVs would be able to do all their calculations locally? Is that something that's even under consideration at the time?
Tesla’s AV design philosophy differs from everyone else’s for just this reason. The idea of using centimeter-accurate models of the environment and having an always-on network connection is fundamentally at odds with handling surprises.
I don’t think a current Tesla would have a good time with no GPS either, but philosophically they stand to better handle intermittent unreliability and adverse conditions once they figure things out.
Re: Driverless robotaxi fleet paralyzed for hours in San Francisco
#410I am just wondering how many people have to die before it finally dawns on on us that the current approach is idiotic. The supposed smart cars can't even talk to each-other directly 'without internet' to warn of a car pileup! They can't report to city traffic control about their condition. We should be innovating in infrastructure instead - create standardised computer readable infrared road markings, equip each traf…
40k people are dying a year from cars, and the problem is that driverless electric cars are not the solution. They are the faster horse kind of innovation. If we were serious about reducing fatalities, improving health, and reducing pollution, the solution would be to drastically reduce the amount of miles driven per year and the number and the size of the cars. We need to encourage people to bike and walk and use pu…
None or few of those options are particularly accessible (EDIT: for people who cannot walk/cycle long distances). Public transportation often is quite inaccessible while still claiming to be accessible (like the London Underground and the New York Subway). Central management of driverless cars could solve the problem in a more inclusive fashion and isn't just more of the same idea. We should still reduce the size of the vehicles, though.
EDIT clarification: Accessibility for wheelchair users, blind people, and anyone with ambulatory restrictions. Most stations are not wheelchair accessible to the train and having to go on much longer routes to compensate is not equal access. And many 'encouraging other use' initiatives block all cars, leaving these people in the lurch. Something that gave door-to-door access to everyone, equally, via a fleet of cars, could be superior.