Episode
Chris Urmson: Self-Driving Cars at Aurora, Google, CMU, and DARPA
44:58
Published: Mon Jul 22 2019
Description
Chris Urmson was the CTO of the Google Self-Driving Car team, a key engineer and leader behind the Carnegie Mellon autonomous vehicle entries in the DARPA grand challenges and the winner of the DARPA urban challenge. Today he is the CEO of Aurora Innovation, an autonomous vehicle software company he started with Sterling Anderson, who was the former director of Tesla Autopilot, and Drew Bagnell, Uber's former autonomy and perception lead. This conversation is part of the Artificial Intelligence podcast. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter, LinkedIn, Facebook, Medium, or YouTube where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on iTunes or support it on Patreon.
Chapters
Chris Urmson is a top roboticist and autonomous vehicle expert, acknowledged for his work in leading the Carnegie Mellon University's entries in the DARPA Grand Challenges, winning the DARPA Urban Challenge, and serving as the CTO of the Google Self-Driving Car team.
00:00 - 02:09 (02:09)
Summary
Chris Urmson is a top roboticist and autonomous vehicle expert, acknowledged for his work in leading the Carnegie Mellon University's entries in the DARPA Grand Challenges, winning the DARPA Urban Challenge, and serving as the CTO of the Google Self-Driving Car team. Despite the incredible challenges involved, he remains dedicated to solving the problem of autonomous driving.
EpisodeChris Urmson: Self-Driving Cars at Aurora, Google, CMU, and DARPA
PodcastLex Fridman Podcast
The speaker discusses different coordinate systems, including NADS-83 and WGS-84, used to describe the earth's non-sphericalness and tectonic shifts, and how high-resolution 3D models generated by multi-beam LIDAR were used in the Urban Challenge to understand the world around the vehicle.
02:09 - 11:15 (09:06)
Summary
The speaker discusses different coordinate systems, including NADS-83 and WGS-84, used to describe the earth's non-sphericalness and tectonic shifts, and how high-resolution 3D models generated by multi-beam LIDAR were used in the Urban Challenge to understand the world around the vehicle.
EpisodeChris Urmson: Self-Driving Cars at Aurora, Google, CMU, and DARPA
PodcastLex Fridman Podcast
The speaker discusses the differences between self-driving technology in limited environments versus scaled-up applications, highlighting the need for efficient sensor suites to create safe vehicles, and emphasizes the importance of bringing technology to market to save lives.
11:15 - 19:59 (08:43)
Summary
The speaker discusses the differences between self-driving technology in limited environments versus scaled-up applications, highlighting the need for efficient sensor suites to create safe vehicles, and emphasizes the importance of bringing technology to market to save lives.
EpisodeChris Urmson: Self-Driving Cars at Aurora, Google, CMU, and DARPA
PodcastLex Fridman Podcast
Driver assistance systems are diverging from the technology needed to deliver truly self-driving vehicles due to economic challenges.
19:59 - 26:34 (06:34)
Summary
Driver assistance systems are diverging from the technology needed to deliver truly self-driving vehicles due to economic challenges. Marketing and communication of the capabilities and limitations of the technology are also identified as problematic.
EpisodeChris Urmson: Self-Driving Cars at Aurora, Google, CMU, and DARPA
PodcastLex Fridman Podcast
Aurora's CEO discusses the company's approach to demonstrating the safety of autonomous vehicles, including working closely with experts at regulatory bodies like NHTSA, while also acknowledging the unpredictability of the timeline for large scale deployment.
26:34 - 37:04 (10:30)
Summary
Aurora's CEO discusses the company's approach to demonstrating the safety of autonomous vehicles, including working closely with experts at regulatory bodies like NHTSA, while also acknowledging the unpredictability of the timeline for large scale deployment.
EpisodeChris Urmson: Self-Driving Cars at Aurora, Google, CMU, and DARPA
PodcastLex Fridman Podcast
Companies are tackling the challenge of autonomous vehicles and pedestrian safety, as there is a difficult technical challenge, despite the simple algorithm used, in protecting pedestrians who take advantage of being too slow.
37:04 - 43:14 (06:10)
Summary
Companies are tackling the challenge of autonomous vehicles and pedestrian safety, as there is a difficult technical challenge, despite the simple algorithm used, in protecting pedestrians who take advantage of being too slow.
EpisodeChris Urmson: Self-Driving Cars at Aurora, Google, CMU, and DARPA
PodcastLex Fridman Podcast
Investing in a culture that allows engineers to focus on solving problems and using on-road testing to pull data and accelerate engineering can lead to incredible results.
43:16 - 44:50 (01:34)
Summary
Investing in a culture that allows engineers to focus on solving problems and using on-road testing to pull data and accelerate engineering can lead to incredible results. This investment in people and tools allows for less time spent on demos and more time spent on innovation.