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

Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

youtube.com

Post reply on HN
Print view View original

91–100 of 214 posts

Re: Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

#91

Post by minhazm »

dheera wrote: post #55
sadfasf122 wrote: post #53

Earlier quoted context omitted.

lol what? did you watch the video at all

Well yes, but I think they'll be singing a different tune in 5 years, and even more so when more Tesla cars actually start driving in weather conditions less favorable than Palo Alto and Austin. At some point when LIDAR is cheap enough there is no reason for Elon Musk to not give in and use them. Right now he's constraining the problem to the cost of the car.

LiDAR is not better in worse weather conditions. LiDAR performance degrades in rain and snow. That’s where something like radar is better. The Tesla get is that humans drive with vision so they should be able to as well. Also every other self driving solution must solve the vision problem also in order to be successful. LiDAR doesn’t tell you that it’s a bag on the road vs a raccoon. So the question is that once you solve the vision problem, do you still need LiDAR for any meaningful impact?

Re: Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

#92

Post by cscurmudgeon »

minhazm wrote: post #82
AndrewKemendo wrote: post #70

Earlier quoted context omitted.

>Tesla's self-driving is far safer than human driving: the number of accidents and deaths per mile driven are something like an order of magnitude lower Still not close to good enough for people to accept: "Participants from both countries required Self Driving Vehicles to be 4-5 times as safe as Human Driven Vehicles" [0] 0: https://pubmed.ncbi.nlm.nih.gov/32202821/

It’s already about 10x. But it is a bit tricky since they don’t break the numbers out by highway and local driving. Also their active safety features outside of AP also improve safety. So does it need to be 4-5x better than an already improved system that has AEB and lane departure avoidance and other safety features? https://www.tesla.com/VehicleSafetyReport > In the 1st quarter, we registered one accident for every…

> It’s already about 10x.

It is not from your data alone. It maybe, but the data is not from a controlled experiment.

Because:

1. Autopilot disengages in dangerous/ambiguous situations. 2. The set of users with autopilot is different from those without.

Re: Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

#93

Post by aimkey »

01100011 wrote: post #49
tokipin wrote: post #46

Earlier quoted context omitted.

I predict the opposite. Tesla sold half a million cars last year and will sell nearly one million this year. The data they have access to is increasing by orders of magnitude. I bet there is a point, let's say 20 million cars total, where they can pull so much high quality data that they will be able to surpass lidar capabilities for the purposes of self driving. The lidar/no lidar discussion is a fun one because peo…

The fallacy here is that the scale of the neural network used by Tesla is sufficient to capture the problem of driving given enough training. There is no guarantee that a reasonably priced neural network can encompass the task of driving. Having training data beyond a certain point is overrated, and Tesla's advantage in gathering it is overstated. Other companies are capturing this data as well. Is there any indicati…

It seems as if the people gobbling up the "Tesla has the data! Autopilot will keep getting better!" line have never trained a neural network in their life. Models converge. Loss stops decreasing, regardless of more incoming data. Extreme manual data cleaning effort becomes required to prevent overfitting. Model architecture has to change and hyper parameters have to be tweaked. Then you're back at square one as far as testing goes if you change any of those things.

The notion that Tesla's model HAS to keep improving simply because they will be able to pile on more (unlabeled!) data is laughably false. And, in fact, quite insulting to the intelligence of even the most casual ML engineers.

Re: Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

#94

Post by olyjohn »

cs702 wrote: post #63
bluepanda928752 wrote: post #34

Tesla's decision not to use the LIDAR as a safety feature (i.e. having reliable high-resolution data about things the car can collide with) is so incredibly indefensible, since solving the last 1% of this using only vision likely requires a general artificial intelligence Prediction: Tesla will be the last of all major auto manufacturers to get to L5 autonomy. Time interval between when Tesla L5 FSD is finally availa…

I strongly disagree. By all measures I've seen (including a couple of slides in the OP's video), Tesla's self-driving is far safer than human driving: the number of accidents and deaths per mile driven are something like an order of magnitude lower (i.e., around 10x safer). I mean, the machine never gets distracted, tired, sleepy, emotional, drunk, etc., so it is a LOT LESS likely to crash on boring, monotonous road…

Tesla does not have self driving. Production Autopilot is not self driving. It's advanced cruise control with lane keeping, nothing that any other manufacturer doesn't offer on their cars. Full self driving doesn't even work, and is acknowledged by Tesla themselves, calling FSD a beta. And FSD can barely even do basic tasks like making an unprotected left turn.

Re: Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

#95

Post by vgchh »

bluepanda928752 wrote: post #34

Tesla's decision not to use the LIDAR as a safety feature (i.e. having reliable high-resolution data about things the car can collide with) is so incredibly indefensible, since solving the last 1% of this using only vision likely requires a general artificial intelligence Prediction: Tesla will be the last of all major auto manufacturers to get to L5 autonomy. Time interval between when Tesla L5 FSD is finally availa…

Ultimately the proof is in the pudding. With Tesla FSD you can drive the highways from New York to Boston without any issues. I am sure there are many more routes across the country that can also be driven like that. Definitely not L5, but it works. Yet to see that from any other automaker, LIDAR or not. As far as I am concerned, great job Tesla! Keep it up, I am sure you will work through more tougher problems.

Re: Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

#97

Post by trhway »

bluepanda928752 wrote: post #39
SheinhardtWigCo wrote: post #35

Earlier quoted context omitted.

They’re betting that they can use a massive feedback loop to train a set of neural networks to the point where they are as accurate as LiDAR without actually firing any lasers. Even if you believe this goal is possible to achieve at some point in the future, I think the argument falls apart when you consider that it will take years, probably decades, for a pure vision approach to catch up to where Waymo is today in t…

I understand why they made the "no-LIDAR" bet early when the LIDARs were completely unpractical for a production consumer car However, nowadays it starts to look that 100% reliable depth estimation from cameras might actually require a human-level AI to work and also solid-state LIDAR technology is becoming cheap enough and integrateable into normal cars, but Tesla can't really change their stance on this without adm…

>100% reliable depth estimation from cameras might actually require a human-level AI to work

you don't need 100%, and even humans are far from 100% (500Mpx resolution of our eyes allows to basically sheer brute force through it in many cases). The stereo setup provides great and fast estimation with several megapixel resolution with good fps (way better than lidar) for majority of situations. It is some share of the [part of the] scenes, and you really know it right then and there, where you need AI and/or very sophisticated compute heavy algorithms. So instead of throwing AI and the compute power at those parts, you just pull the points from the lidar (and even radar if the things are that bad) covering that segment. And that way, given a couple more iterations of sensors (from current 20Mpx+ to the hundreds Mpx) and compute, it will be doing even better than humans. Anybody not doing sensor fusion would be a loser though - just like going into a fist fight with one hand intentionally disabled.

Re: Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

#98

Post by gibolt »

ra7 wrote: post #43
practice9 wrote: post #42

Earlier quoted context omitted.

> I think the argument falls apart when you consider that it will take years, probably decades, for a pure vision approach to catch up to where Waymo is today in terms of safety. (They have cameras too.) On what set of metrics do you think Waymo is safer? IMO it's too early to compare and cherry-picked proofs both from Waymo and Tesla are not really representative.

Waymo has published detailed safety performance data of their Arizona operations: https://waymo.com/safety/performance-data You can read their other safety whitepapers in https://waymo.com/safety

Arizona roads are also mapped to extreme precision, have very wide lanes, and are optimized for cars. Waymo has prioritized low intervention by being overly cautious and avoiding hard maneuvers (like many left turns).

That doesn't work when they scale up to any other set of normal roads, especially as density and complexity increases.

Re: Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

#99

Post by Animats »

jonas21 wrote: post #56
practice9 wrote: post #42

Earlier quoted context omitted.

> I think the argument falls apart when you consider that it will take years, probably decades, for a pure vision approach to catch up to where Waymo is today in terms of safety. (They have cameras too.) On what set of metrics do you think Waymo is safer? IMO it's too early to compare and cherry-picked proofs both from Waymo and Tesla are not really representative.

For starters, Waymo reported 1 disengagement per 29,944 miles driven in 2020 to the California DMV [1], while in the talk, Karpathy implies that a Tesla being able to drive around the SF area for 2 hours without a disengagement is unusual. Note that Tesla didn't file a disengagement report because they didn't do any autonomous testing on public roads in California in 2020. There are issues with reading too much into…

Waymo's number for 2019 was around 11,000 miles driven per disengagement. It's been improving steadily, at a reasonably good rate.

Tesla wimps out and won't test in California, because they'd have to report.

Re: Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]

#100

Post by ketamine__ »

revscat wrote: post #90
karpathy wrote: post #26

Earlier quoted context omitted.

For the record these are some blatant & false FUD attempts.

There is a lot of that on HN whenever Tesla is the subject.

If Elon was any good at keeping his word it wouldn’t be an issue.
Post reply on HN