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

201–210 of 214 posts

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

#201

Post by etrautmann »

rpmisms wrote: post #194
pokerhobo wrote: post #153

Earlier quoted context omitted.

LIDAR in a drizzly city like Seattle is of minimal value so the system has to fallback to vision only anyways

It's an anti-fragile approach, a term you'll recognize if you know of Nassim Taleb and his work. I think it will win in the long run, because not requiring HD Maps or specialized sensors is an advantage, and even if it takes more resources to make it work initially, it will save billions in the future, assuming, of course, it ever ships. Obviously, pure vision is a viable system, as it's what we as humans use. The qu…

This is not a good argument overall for several reasons. First, we should aim to greatly exceed human performance on safety. Second, whatever work goes into making the algorithms work well using vision can just as easily still inform a system that fuses that data with LIDAR for enhanced situational awareness and safety.

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

#202

Post by jowday »

blueblisters wrote: post #174
ra7 wrote: post #58

Earlier quoted context omitted.

> You get sparse point cloud from LIDAR sensors Take a look at how dense the point cloud from Waymo's 5th gen LIDAR is: https://www.youtube.com/watch?v=COgEQuqTAug&t=11599s . They just talked about this a few days ago.

Any idea why this video went private?

They're cutting up the original 3 hour long Livestream into separate videos for each presentation.

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

#203

Post by semi-extrinsic »

CrazyStat wrote: post #88
semi-extrinsic wrote: post #18

Earlier quoted context omitted.

There are many things humans do with vision alone that machines can't. For instance see if a person standing 50 ft away is looking at you or at the house behind you. The human vision system operates at a bitrate equivalent of well beyond 500 gigabits per second. Resorting to "humans can do it with vision alone" is only a sufficient argument if your computer vision system can match that.

> The human vision system operates at a bitrate equivalent of well beyond 500 gigabits per second Do you have a source for this claim? Academic sources suggest numbers 4-5 orders of magnitude smaller: 6Mbps [1], 10Mbps [2]. [1] The Oxford Companion to the Mind (1987) [2] https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1564115/

Alright, I should clarify, as my first post was a bit sloppy.

We know the eye has highly nonuniform resolution, with the high resolution region moving around all the time to cover areas of interest. I agree this system has something like 10 Mbps actual bitrate.

But we don't know how to make such a system for computer vision. Our CV systems all have uniform resolution. And thus a CV system needs to match the peak resolution of the human vision system. That requires a ~500 megapixel resolution at 24 bits per pixel and ~50 frames per second.

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

#204

Post by aeternum »

rasz wrote: post #166
aeternum wrote: post #14

Earlier quoted context omitted.

In the talk, he gave clear examples with detailed position + velocity graphs where the vision system detected obstacles sooner and with less jitter than the radar system. Specifically the overpass where radar triggers erroneous braking, and the pulled over truck where radar detects the obstacle significantly slower.

and yet cars with radar based collision avoidance dont end up decapitating people, or plowing into parked cop cars.

I believe the teslas involved in those collisions were versions that were using radar.

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

#205

Post by justapassenger »

marvin wrote: post #192
nickik wrote: post #181

Earlier quoted context omitted.

Hi-def 360 LIDAR that companies like Waymo or Aurora are absolutely not ready to put into millions of vehicles for a price that makes it anywhere close to reasonable. Multiple companies that have announced Lidar have later removed it for the cars. The Lidar that are actually currently deployed that you can 'just' get from suppliers is of the not of the same quality and we have yet to actually see real high volume car…

Elon Musk is a lot of things, but stupid isn't one of them. I'd be willing to bet that Tesla continuously looks at the state of LIDAR tech and evaluates whether it's at the point where it will be feasible to put it in a mass-market car in two years. People keep getting hung up on their vision strategy because it sharply diverges from that of all other players, but it's really just tackling the "no one knows how to do…

Tesla cannot go into LIDAR without huge destruction of the company valuation and pissing off large base of customers. They've been selling a car ready for FSD for almost 5 years now, for a huge extra margin. LIDAR retrofit is impossible, and admitting that they need it means there's huge amount of customers who paid for product that will never exists. Refunds will not only put a huge dent on finance, but it'll also further damage brand of Tesla as a player in that space, and Elon as a god-like visionary.

Is LIDAR required for self driving? Probably, but it's not certain. But one thing is certain - Tesla is in the corner, and they have to deliver solution without it, using few years old inference HW and 5 years old+ cameras. Selling HW for a problem that doesn't even have a theoretical solution in software, so you don't even know what HW you need, is a bold, bold move.

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

#206

Post by babesh »

fpgaminer wrote: post #165
babesh wrote: post #161

I think the more interesting question is how much human context is necessary in decreasing accident rates. The signal question and tunnel answer hinted at that. Some context is very local and some context is general at the level of humans. Examples: human eyes will have trouble adjusting to the sudden darkness of tunnels so some people will tend to brake suddenly; that person looks old and will probably have slower r…

I agree, though I think there's an obvious path towards that higher order understanding of the road that humans have. Suppose they eventually have this current system dialed in and they get really good, accurate bounding boxes around all interesting objects on the road. So now, in addition to their 10 second samples of video data they're collecting, they start collecting 10 second samples of scene representations. Th…

Yes, building the next level of abstractions and inferences.

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

#207

Post by jiofih »

ra7 wrote: post #197
jiofih wrote: post #196

Earlier quoted context omitted.

Sounds like “none”.

None what? I just gave you an example of Waymo using 4D imaging radar [1]. Aurora also uses imaging radar [2], Mobileye as well [3]. AutoX is going to start using Arbe radars. All of them are leading players in SDC industry. [1] https://blog.waymo.com/2020/03/introducing-5th-generation-wa... [2] https://aurora.tech/technology/driver [3] https://www.mobileye.com/blog/radar-lidar-next-generation-ac...

You said “everyone else” besides Tesla uses 4D radar, and “that's why Teslas have poor performance like phantom braking”. But there are zero production vehicles on the road using this tech right now.

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

#208

Post by ra7 »

jiofih wrote: post #207
ra7 wrote: post #197

Earlier quoted context omitted.

None what? I just gave you an example of Waymo using 4D imaging radar [1]. Aurora also uses imaging radar [2], Mobileye as well [3]. AutoX is going to start using Arbe radars. All of them are leading players in SDC industry. [1] https://blog.waymo.com/2020/03/introducing-5th-generation-wa... [2] https://aurora.tech/technology/driver [3] https://www.mobileye.com/blog/radar-lidar-next-generation-ac...

You said “everyone else” besides Tesla uses 4D radar, and “that's why Teslas have poor performance like phantom braking”. But there are zero production vehicles on the road using this tech right now.

I said “The rest of the SDC industry uses 4D radars” in a follow up comment, which clarifies I don’t mean car manufacturers.

Given this post is about radar usage in self driving and how Tesla/Karpathy touts their capabilities, I compare them to other SDC players, not other car manufacturers who are not in the game. And their SDC competitors are running away because they have the newer 4D radars.

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

#209

Post by aeternum »

justapassenger wrote: post #205
marvin wrote: post #192

Earlier quoted context omitted.

Elon Musk is a lot of things, but stupid isn't one of them. I'd be willing to bet that Tesla continuously looks at the state of LIDAR tech and evaluates whether it's at the point where it will be feasible to put it in a mass-market car in two years. People keep getting hung up on their vision strategy because it sharply diverges from that of all other players, but it's really just tackling the "no one knows how to do…

Tesla cannot go into LIDAR without huge destruction of the company valuation and pissing off large base of customers. They've been selling a car ready for FSD for almost 5 years now, for a huge extra margin. LIDAR retrofit is impossible, and admitting that they need it means there's huge amount of customers who paid for product that will never exists. Refunds will not only put a huge dent on finance, but it'll also f…

It is a bold move, but perhaps we need more of those. How much of the talent in SV is focused on optimizing ad placement or building messaging systems?

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

#210

Post by jiofih »

ra7 wrote: post #208
jiofih wrote: post #207

Earlier quoted context omitted.

You said “everyone else” besides Tesla uses 4D radar, and “that's why Teslas have poor performance like phantom braking”. But there are zero production vehicles on the road using this tech right now.

I said “The rest of the SDC industry uses 4D radars” in a follow up comment, which clarifies I don’t mean car manufacturers. Given this post is about radar usage in self driving and how Tesla/Karpathy touts their capabilities, I compare them to other SDC players, not other car manufacturers who are not in the game. And their SDC competitors are running away because they have the newer 4D radars.

Well, until these are actually adopted by a car company and out on the road, any claims about performance are meaningless. Your original comment implied Tesla chose to use inferior tech compare to the market which is not true in the slightest.
Post reply on HN