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

151–160 of 214 posts

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

#151

Post by tedk-42 »

01100011 wrote: post #51
sam_goody wrote: post #2

tldr: Tesla uses vision alone, and has dropped radar and the other sensor. He makes a very decent argument why. (Surprisingly, he basically ignores night driving.)

Not a fan of TSLA, but isn't night driving just a special case of daytime driving if you use IR and/or hyperspectral cameras?

I imagine it's far more tricky due to the lower image quality and increased noise on the sensors (less light/energy hitting them).

Loss of colours in your visual imput as well is a bit of an issue...

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

#152

Post by pokerhobo »

Animats wrote: post #99
jonas21 wrote: post #56

Earlier quoted context omitted.

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.

Isn’t Waymo only driving in small HD mapped areas? Previously the were only driving within a 50 mile area of Arizona where it’s clear weather all the time.

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

#153

Post by pokerhobo »

etrautmann wrote: post #45
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…

The vision-only strategy only made a shred of sense before high performance / low cost LIDARs like the Ouster OS1 became available. Now it’s an indefensible position on safety or economic grounds.

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

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

#154

Post by pokerhobo »

nickik wrote: post #5

I resonantly had an argument on here where somebody insistent that breaking because of over-passes were issues with vision system. Seem pretty clear that it is the resolution of the radar, not the shadow of the bridge that causes the issue. Good to get some more insight into this. This is the right thing to focus on, as it is by far the largest issue with Autopilot on the highway. Multiple people who do testing of th…

The video directly addresses this…

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

#155

Post by minhazm »

dragonwriter wrote: post #136
kortex wrote: post #134

Earlier quoted context omitted.

My understanding is that LIDAR is diminished on the aspect of not just "not needed," but also potentially exacerbating local minima under good (e.g. fair weather) conditions. Having LIDAR means you can rely on LIDAR, which means you need the LIDAR to be 100% reliable. I've read some companies claiming their lidar works through rain and snow but I haven't seen actual renders of it yet to judge for myself. No lidar act…

> No lidar acts as a forcing function for Tesla to get their vision system that much more reliable. Alternatively, no LIDAR means you aren't gathering corresponding LIDAR and vision data that you can use to improve detection of the vision system.

Tesla does use LiDAR for calibration and testing of their vision systems. But they also have a million cars on the road with radar which also gives fairly accurate depth information. They use the depth information provided by the radar to automatically label their data and then they can check their vision based estimates against that data. Karpathy has mentioned this approach in a few different talks.

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

#156

Post by justapassenger »

aeternum wrote: post #14
nightski wrote: post #9

It's interesting that an academic conference now feels like a marketing op for industrial research labs more than anything. His claims about how accurate their vision system is and how it is exceeding other sensors is not verifiable in any way to the public. Given how well qualified he is I am sure he is not wrong! Andrej is brilliant. But this is an academic conference right? This isn't open science, it's a discussi…

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.

1. Radar isn't gold standard of object detection. LIDAR is. 2. From reports by owners of latest Teslas, that don't even have radar installed, they still have erroneous braking. Driving is hard.

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

#157

Post by justapassenger »

nickik wrote: post #124
stefan_ wrote: post #30

Earlier quoted context omitted.

That's a strawman. No one is looking to build FSD with radar sensors that have shipped on cars for 20 years now for things like adaptive cruise control. LIDAR is what vision only is compared to.

Radar is the technology that is actually shipping in millions of cars. Lidar is future tech that is not practically to deploy in millions of cars as of now. There is absolutely 0 chance they could just 'put in lidar' from now on so for what he has to do its not relevant.

When was last time you looked at LIDAR tech? It's already cheap enough that it can be easily deployed in millions of cars.

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

#158

Post by aimkey »

cs702 wrote: post #150
aimkey wrote: post #118

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 (i.e., around 10x safer). Lies, damn lies, and statistics. Tesla here, is, again, being funny with the numbers. They LOVE to cite autopilot ON death statistics as being "10x safer than normal driving". What they fail to note is that Autopilot can ONLY be on while dri…

> So, Tesla autopilot stats should be compared to other comparably priced vehicles while driving on the highway ONLY. I disagree. Autopilot driving on the highway should be compared to all human drivers driving on the highway. Otherwise you wouldn't be comparing against human performance per mile driven apples-to-apples.

Modern vehicles have much safer crash characteristics than older cars. The average vehicle on the road in the US is 11 years old. Do you know how much crash characteristics of cars have improved in the last decade? The comparison needs to stay in the modern, $65k+ vehicle realm for it to be apples-to-apples. Otherwise, you're comparing a bunch of decade old rust buckets with heat-cycled rubber, no blind spot monitoring, and Takata airbags to modern vehicles and claiming victory. Come on.

The BMW F10 535i had ZERO FATALITIES over its entire life in the US. Zero. It had no "self-driving" capabilities. Just lane-departure warning, BLIS, and ACC.

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

#159

Post by dheera »

minhazm wrote: post #91
dheera wrote: post #55

Earlier quoted context omitted.

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…

> LiDAR doesn’t tell you that it’s a bag on the road vs a raccoon

I think that's largely an issue with the early LIDAR devices today, but not necessarily what may be to come.

There's something to be said about measuring actual data with solid physics vs. inferring distances with billions of operations on RGB data. If you were landing a commercial aircraft in fog, you most certainly don't rely on your eyes to do most of it, but it is in fact possible to do safely precisely because we do have good sensors on them.

I fully agree with leveraging the scale and maturity of RGB sensors for cars today, the talk is spot on about that, but that's (a) circling back to the fact that Tesla needs to sell cars now not next year and (b) not a good case against use of LIDAR in the future.

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

#160

Post by minhazm »

dheera wrote: post #159
minhazm wrote: post #91

Earlier quoted context omitted.

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…

> LiDAR doesn’t tell you that it’s a bag on the road vs a raccoon I think that's largely an issue with the early LIDAR devices today, but not necessarily what may be to come. There's something to be said about measuring actual data with solid physics vs. inferring distances with billions of operations on RGB data. If you were landing a commercial aircraft in fog, you most certainly don't rely on your eyes to do most…

It’s easy to add a few hundred thousand dollars of sensors to a $100 million plane. But $20k on a $40k car is too much and makes it cost prohibitive for most people. If vision alone can get you to say 1 crash in 10 million miles, that’s more than good enough to replace human drivers. If someone decides they want to go the extra mile and will pay for something rated for 1 in 20 million miles for 2x the cost, then they are free to do so.

As mentioned in this talk Tesla is taking an iterative approach and trying to make things safer for people today, not in 5 yrs from now. Maybe in a few years Tesla will see that to go from 10 million miles to 20 million miles they need 4k cameras at 60 fps, but the work they had already done would still have had a big impact. You don’t need to do things in one shot and get to the finish line.

Post reply on HN