Skip to content
Hallway
0:00 / 0:00

#teslaautopilot#computervision#neuralnetworks

Andrej Karpathy - AI for Full-Self Driving at Tesla

Matroid

6.7K subscribers • 2 videos on Hallway

YouTube
  • Recommended by 4 people: 4 on Hacker News.
  • Presented by Andrej Karpathy, Senior Director of AI at Tesla
  • May be out of date. The tools, versions or practices it shows have likely moved on.

Intermediate. Assumes working knowledge.

374K views6 years ago4 recommendations

AI and machine learningSystems programmingNeural networks and deep learningComputer visionTraining and serving models

Andrej Karpathy explains how Tesla trains vision-based neural networks for self-driving using large-scale fleet data collection.

For more talks and to view corresponding slides, go to scaledml.org, select [media archive]. Presented at the 5th Annual Scaled Machine Learning Conference 2020 Venue: Computer History Museum scaledml.org | #scaledml2020

Why it's here

4 people recommend this

What people say. Recommended as a key technical presentation explaining Tesla's vision-based approach to autonomous driving.

maxharrison Hacker News • Recommends

On “German court bans Tesla ad statements related to autonomous driving”

If you actually believe that Tesla will fail to deliver full self-driving in the coming years, I have two questions. 1. have you watched this entire technical presentation made by Andrej Karpathy, Senior Director of AI at Tesla? link to this video 2. if you understand what you've seen in that video, why do you think Tesla will fail?
View on Hacker News

TaylorAlexanderon Hacker News • Recommends

On “Tesla to produce $25K car as early as 2022”

Removing the cameras may be a good idea, but note that their extensive fleet of camera-equipped vehicles is an important part of their potentially VERY lucrative self driving software development. EDIT: I highly recommend watching head of AI at Tesla Andrej Karpathy's talk on their self driving architecture. "The Fleet" as a source of data is a vital functional part of their self driving software development. They may be able to calculate that including cameras and a computer on a car that will ship in high volumes would increase sales of their self driving option across all Tesla vehicles (including that low cost model) enough to justify the inclusion of those parts. link to this video
View on Hacker News

TaylorAlexanderon Hacker News • Recommends

On “Tesla auto-pilot keeps confusing moon with traffic light then slowing down”

…ples they can create unit tests to ensure that the moon stops activating the stoplight detector. Once trained, the unit tests presumably help ensure they don't end up with future regressions. So basically every time you see a Tesla do a weird thing, there is a good chance it will stop doing it soon enough. At least if it's hitting hacker news. 1 link to this video…
View on Hacker News

kjksfon Hacker News • Recommends

On “Waymo has raised $3B in the last two months”

Here's the most recent talk by Karpathy about this topic: link to this video (there are more if you google for "karpathy talk") Here's the summary via 2 examples. 1. Example of gathering data that needs further labeling To implement neural network (NN) to recognize stop signs they program the cars to recognize things that look like stop signs and deploy that to the fleet of over 600 thousand cars on the road. The cars send those "might or might not be a stop sign" images back to tesla and they get manually labelled and added to a training set. They gather enough images and the "recognize stop signs" feature is done. Apply the same logic to other recognition tasks: recognize cars, pedestrians, animals,…
View on Hacker News

fossuseron Hacker News • Recommends

On “Nikola: How to Parlay an Ocean of Lies into a Partnership with GM”

It's not the same: link to this video You can watch that talk and see the approach they're taking. Maybe you're more skeptical than they are about the near term possibility, but you can see that the work and progress is real. The AGI risk is real too. What Milton said doesn't make semantic sense, it's not a question of timelines. link
View on Hacker News

maxharrison Hacker News • Recommends

On “Tesla’s Nemesis in China Is a Tiny $5k Electric Car from GM”

Better yet, let's get rid of cars altogether from city streets. This is coming along very nicely... link Autonomous driving is just around the corner, too, which means that there is no need to waste space on parking structures, either. Here's a Tesla engineer that gave a great technical talk demonstrating their progress as of early this year: link to this video EDIT: yes, there are clear reasons why having an three-dimensional underground structure will absolutely affect the social dynamics above-ground in a city, yet it remains true that it is possible to banish cars from downtown cores in the near future (i.e., say by 2030 or so), given the present shift to electrification and autonomous driving. T…
View on Hacker News

maxharrison Hacker News • Recommends

On “Trump left a traffic-safety mess for Biden.Item one:Tesla’s self-driving claims”

This is anti-Tesla astroturfing, so I flagged it. If you'd like a high-level technical overview of Tesla's FSD efforts, check out this talk by Andrej Karpathy from February 2020: link to this video There are literally thousands of videos of people filming the FSD beta doing amazing things. They are making great progress very, very quickly: link As you can see from videos like the one above, real-world data is needed to make FSD practical. There is a very long tail of things to get right, so blocking this progress with regulations would effectively outlaw FSD, or delay its development by a very long time. Given the number of road accidents that human drivers cause (think of just sleep deprivation and…
View on Hacker News

maxharrison Hacker News • Mentions

On “American billionaires have gotten $280B richer since the start of the pandemic”

…ke the emerging eVTOL scene. it's possible Tesla may enter that space and dominate it, because batteries determine everything there, too. in the meantime, I bought some shares of eHang (Chinese company, listed on the Nasdaq under EH) 3) they have a huge lead in autonomous driving. LiDAR is a dead-end, and they're ahead of everyone else there, too: link to this video 4) demand is not a problem at all, especially in C…
View on Hacker News

KKKKkkkk1on Hacker News • Mentions

On “Ask HN: What startup/technology is on your 'to watch' list?”

LIDAR vs camera is a red herring. The fact that Elon and his fan club fixate on this shows you how little they understand about self driving. The fundamental problem is that there is no technology that can provide the level of reasoning that is necessary for self driving. Andrej Karpathy's most recent presentation showed how his team trained a custom detector for stop signs with an "Except right turn" text underneath them 0. How are they going to scale that to a system that understands any text sign in any human language? The answer is that they're not even trying, which tells you that Tesla is not building a self-driving system. 0 link to this video
View on Hacker News

fossuseron Hacker News • Mentions

On “Nikola: How to Parlay an Ocean of Lies into a Partnership with GM”

…erchargers and drive costs down. This has been massively successful and their EVs (particularly the model3/y) have no equal at any price point EV or gas. The level 5 autonomy was really a bonus on top of that EV transition that they've added to, and if anyone can pull it off it will be Andrej Karpathy and the fleet of Tesla's they can train with ( link to this video ). Bullshit and really big ideas can sound similar, but that doesn't mean they are - there's a lot of value in being able to…
View on Hacker News

maxharrison Hacker News • Mentions

On “Ask HN: Are we in tech-stock bubble?”

I'm sorry you missed out on one of the best investments of the decade, but there is a lot of room left for this to run. Tesla's coming FSD and robotaxis still haven't been priced in. link to this video
View on Hacker News

TaylorAlexanderon Hacker News • Mentions

On “OpenAI disbands its robotics research team”

…the real world. Good work in RL happening there though. Gosh, yeah, this is gonna take decades lol. Maybe we will have a spark that unites all this in one efficient system. Improving transformer efficiency and achieving big jumps in scale are a combo that will probably get interesting stuff solved. All the groundwork is a real slog. 1 link 2 link to this video 3 link…
View on Hacker News

wcoenenon Hacker News • Mentions

On “Tesla to recall vehicles that may disobey stop signs”

There is a mix of a "neural net planner" and a "explicit planning and control" in traditional code1. The explicit planner has the last word, and uses input from both the "vector space" and the neural net planner. Karpathy has commented about the neural nets gradually replacing the traditional code. See his presentation2 around 18:45. 1 link 2 link to this video
View on Hacker News

baryphonicon Hacker News • Mentions

On “US moves closer to recalling Tesla’s self-driving software”

> All evidence from their own AI/AP team and presentations is that there is no real design and system validation going on over there. They're flying by the seat of their pants, introducing potentially lethal regressions in every update. What is this evidence? I've seen a few talks from Andrej Karpathy that indicate to me a more deliberate approach.0 "Software 2.0" itself seems like an approach meant to systematize the development, validation & testing of AI systems, hardly a seat-of-your-pants approach to releases. I have my own criticisms of their approach, but it seems there is pretty deliberate care taken when developing models. 0 link to this video
View on Hacker News

jsighton Hacker News • Mentions

On “Tesla’s self-driving technology fails to detect children in the road, tests find”

The actual report is here: link It failed to detect a stationary mannequin in one specific scenario. Does this generalize? Does this mean there's a major safety problem? These would be assumptions that this test can not prove. A comprehensive safety analysis has to also include these scenarios: link to this video
View on Hacker News

joewadcanon Hacker News • Mentions

On “Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision”

They are reliable enough to use for FSD: link to this video so i think it's reliable enough for park assist, summon etc. Yeah you're def right about the moisture sealing... it's been hit or miss on production tolerances
View on Hacker News