Skip to content
Hallway
0:00 / 0:00

#waymo#self-drivingcars#autonomousvehicles

Sacha Arnoud, Director of Engineering, Waymo - MIT Self-Driving Cars

Lex Fridman

5M subscribers • 39 videos on Hallway

YouTube
  • Recommended by 3 people: 3 on Hacker News.
  • Presented by Sacha Arnoud, Director of Engineering at Waymo
  • May be out of date. Uploaded 8 years ago, in an area where tools change fast.

Intermediate. Assumes working knowledge.

108K views8 years ago3 recommendations

AI and machine learningComputer visionNeural networks and deep learningTraining and serving models

Sacha Arnoud explains how Waymo uses machine learning and deep learning to handle complex driving scenarios and edge cases.

This is a talk by Sacha Arnoud for course 6.S094: Deep Learning for Self-Driving Cars (2018 version). Sacha is the Director of Engineering at Waymo and his talk is titled "The rise of machine learning in self-driving cars." This class is free and open to everyone. It is an introduction to the practice of deep learning through the applied theme of building a self-driving car. INFO: Course website: selfdrivingcars.mit.edu Contact: deepcars@mit.edu CONNECT: - If you enjoyed this video, please subscribe to this channel. - AI Podcast: lexfridman.com/ai/ - Show your support: patreon.com/lexfridman - LinkedIn: linkedin.com/in/lexfridman - Twitter: twitter.com/lexfridman - Facebook: facebook.com/lexfridman - Instagram: instagram.com/lexfridman - Slack: deep-mit-slack.herokuapp.com LINKS: Playlist: goo.gl/SLCb1y Lecture 1: Deep Learning - youtu.be/-6INDaLcuJY Lecture 2: Self-Driving Cars - youtu.be/_OCjqIgxwHw Lecture 3: Deep Reinforcement Learning - youtu.be/MQ6pP65o7OM Lecture 4: Computer Vision - youtu.be/CLOAswsxudo Lecture 5: Deep Learning for Human Sensing - youtu.be/Z2GfE8pLyxc Guest talk: Sacha Arnoud, Waymo - youtu.be/LSX3qdy0dFg Guest talk: Emilio Frazolli, nuTonomy - youtu.be/dWSbItd0HEA Guest talk: Sterling Anderson, Aurora - youtu.be/HKBhP9JISF0 2017: Guest talk: Sertac Karaman, MIT - youtu.be/0fLSf3NO0-s Guest talk: Chris Gerdes, Stanford - youtu.be/LDprUza7yT4

Why it's here

3 people recommend this

What people say. Recommended as an excellent explanation of how self-driving systems utilize machine learning to handle real-world edge cases.

RosanaAnaDanaon Hacker News • Recommends

On “LiDAR scans are finding hidden Roman roads and cutting crime”

I believe this talk will specifically and completely answer your questions: link to this video Short answer: Self driving vehicles do use deep learning, but they avoid some types not because it is unreliable, but it is processing power intense. Traffic lights, road signs, pedestrians etc.. That's a whole ball of wax to unravel. Check the lecture, its fantastic imo.
View on Hacker News

lacertaon Hacker News • Recommends

On “Self-driving Uber car kills Arizona woman crossing street”

It is both an over and underhyped field depending on the area you are looking at. HUGE difference between consumer self driving car Everywhere, at all times and the Machines as a Service Geo, time, weather-fenced operations1. Waymo appears to be at the head of the pack; Sacha Arnoud, Director of Engineering for Waymo gave a talk a few weeks ago at MIT2 and gives a good idea. We are about 5 years out until these start rolling out as MaaS (machines as a service). Probably 10+ years for level 4 highway operations for consumer models according to Frazzoli. 1Emilio Frazzoli, CTO of nuTonomy link 2 link to this video
View on Hacker News

Zarelon Hacker News • Recommends

On “Uber’s Vision of Self-Driving Cars Begins to Blur”

The second article I linked to also mentioned work on unmapped roads: link Waymo has solved problem after problem you think they haven't solved yet, for some reason. They've intentionally gone after unpredictable situations and dealt with them. Look at any video where they explain how it works, and you'll notice how many situations they can manage: link to this video And even if Waymo only works on well-mapped cities? That's still far from "can only work if they repurpose existing transportation infrastructure to only belong to self-driving cars" which is the comment I was replying to.
View on Hacker News

verdvermon Hacker News • Mentions

On “GPT is all you need for the back end”

Google/Waymo demo'd the AI driving in a snow storm and the method they used to see through the flakes and maintain object detection. Having trouble finding the video I'm thinking of. Here are some videos related to self-driving in snow and progress on weird edge cases. - link (snow, like the google demo) - link to this video | link to this video (snow, but not the one I was thinking of)
View on Hacker News