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

41–50 of 214 posts

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

#41

Post by bluepanda928752 »

option wrote: post #10
andyxor wrote: post #8

I like Andrej from his PhD research days and awesome blog posts but this is a series of disasters in the making, that is until FTC steps in after more people die from “self-driving” accidents under interesting and unexpected circumstances. The whole vision vs. LIDAR stuff is a distraction as long as Tesla “AI” doesn’t have common sense. It literally doesn’t know what it’s doing, and the tail of edge cases to "fit" th…

There are two fundamental reasons, in principle, vision alone can do it: 1) Humans do it with vision alone 2) You can actually predict lidar’s output with vision alone. So many systems out there actually use lidar to generate more labeled data to make lidar unnecessary

With what kind of reliability can LIDAR data be predicted with vision nowadays?

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

#42

Post by practice9 »

SheinhardtWigCo wrote: post #35
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…

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 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.

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

#43

Post by ra7 »

practice9 wrote: post #42
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 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

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

#44

Post by liuliu »

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…

You get sparse point cloud from LIDAR sensors, not accurate 3D maps. This is the main reason why some people think LIDAR may not work well (mostly, only comma.ai and Tesla folks).

Vision can also get you 3D maps, either in active manner (IR floodlight or structured lighting) or not. I will reserve my judgement until see more from either side.

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

#45

Post by etrautmann »

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.

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

#46

Post by tokipin »

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 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 people have different ideas about how the world works. Personally I think LiDAR is the modern version of expert systems. It appeals to a logical/geometric intuition but the approach is brittle to real world contact, especially when paired with HD maps which are a great way to drive yourself into a local maximum.

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

#47

Post by jfim »

SheinhardtWigCo wrote: post #35
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…

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…

One of the gains from using lidar is also that it's a different sensor altogether from cameras, with different failure modes.

For example, cameras are sensitive to glare from reflections (sun near sunset or reflecting on metallic objects) and oncoming traffic at night. Lidars operate on a different narrower wavelength and are unlikely to be affected by that, although they might struggle with objects that have low reflectivity at a long distance.

The fact that these sensors are different means that the intersection where a dangerous situation would not be detected by either sensor is much smaller than any sensor individually.

In any case, once AVs are deployed at scale, if it becomes apparent that some sensors can be removed or replaced by something else, then they will be if there's a case for it.

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

#48

Post by codeulike »

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…

Innovation is a gamble. You're not wrong to point out they might fail. The likeliness of failure is what makes it worth the gamble of trying.

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

#49

Post by 01100011 »

tokipin wrote: post #46
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 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 indication that the data Tesla is collecting is of a higher value, or is it just more bytes?

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

#50

Post by nelsonfavedra »

Robotbeat wrote: post #17

He made a very good argument for vision-only, but it seems like training actually uses radar data to help calibrate vision measurements, so it seems to me there’s value in making some vehicles still contain radar (say, one out of 10) even if it’s not used for controlling the vehicle directly at drive time. Also, the sensor resolution issue he mentioned could be addressed by using a higher resolution radar sensor. I f…

> but it seems like training actually uses radar data to help calibrate vision

They seem to use radar solely to automatically label data for training.

In the given example though where according to the vision system smog interrupted the persistence of the label for the leading car, I wonder if the use of radar data to persist the label is strictly necessary.

A car disappeared then reappeared in the data, why not just tween the bounding box over time and assume the car had always been there, like, if it looked the same when it reappears or something. An extra sensor just for labelling data seems silly.

Post reply on HN