Self-Driving Cars: Timothy B. Lee Answers All the Questions You Were Too Afraid to Ask

Nathan explores the cutting-edge world of autonomous vehicles with industry expert Timothy B. Lee. In this episode of The Cognitive Revolution, we delve into the current state of self-driving technology, comparing industry leaders like Waymo and Tesla. Join us for an in-depth discussion on technical challenges, safety statistics, regulatory landscapes, and the potential future of transportation.

RECOMMENDED PODCAST: Second Opinion
A new podcast for health-tech insiders from Christina Farr of the Second Opinion newsletter. Join Christina Farr, Luba Greenwood, and Ash Zenooz every week as they challenge industry experts with tough questions about the best bets in health-tech.

SPONSORS:

CHAPTERS:
(00:00:00) About the Show
(00:00:22) About the Episode
(00:03:01) Introduction and Guest Welcome
(00:03:48) SAE Levels of Self-Driving
(00:04:56) Driver Assistance vs. Fully Driverless
(00:07:02) Tesla and Waymo Experiences
(00:09:41) Liability and Driver Monitoring
(00:11:19) Waymo's Robo-Taxi Experience
(00:14:00) Tesla vs. Waymo Strategies
(00:15:15) Challenges in Self-Driving Technology
(00:17:38) Edge Cases and Safety Concerns (Part 1)
(00:18:09) Sponsors: Oracle | Brave
(00:20:13) Edge Cases and Safety Concerns (Part 2)
(00:23:53) Data Acquisition and Learning Strategies
(00:26:43) Technology Stack and Planning
(00:31:03) Sponsors: Omneky | Squad
(00:32:50) Neural Networks and Perception
(00:39:30) Hardware and Sensor Approaches
(00:45:46) Camera vs. LiDAR Debate
(00:48:20) Data Quality and Business Models
(00:52:24) Transparency and Regulation
(00:56:52) Role of Maps in Self-Driving
(00:59:49) Local vs. Remote Processing
(01:01:44) Cruise's Challenges and Future
(01:04:58) Global Self-Driving Landscape
(01:07:36) Other Notable Players
(01:10:56) Safety Statistics and Adoption
(01:20:31) Regulatory Environment
(01:23:32) Waymo's Safety Data
(01:25:39) Cultural and Technological Barriers
(01:30:09) Potential Policy Changes
(01:33:41) Market and Ownership Models
(01:36:37) Future of Self-Driving Services
(01:39:26) Unexpected Scenarios and Partnerships
(01:42:17) Comparisons to Language Models
(01:44:55) Future of AGI and AI Applications
(01:47:59) Regional Adoption Predictions
(01:49:47) Outro

---
SOCIAL LINKS:

[Nunya-lzey]

1:36:14 tesla has a mobile service team that already services their entire fleet. Also charging, cleaning, etc.

Tesla by far has the infrastructure advantage

[apple]

The thing with LiDAR vs only camera is not just cost (which is absolutely massive when scaled to the millions annually) but it’s also processing speeds. If you solely focus on everything hinging on vision than everything you do goi g forward will revolve around perfecting vision.
If you rely on lidar for safety than you’re handicapping yourself in terms of vision while simultaneously bogging down the entire processing network as the two systems compare every frame with one another to concur that they’re right.
LiDAR is not bad by any means, but in terms of future proofing autonomy it is like a training wheel that demands more energy, cost and processing power which could otherwise be used more efficiently on purely vision.
We’ll see in the long run but I imagine that LiDAR will not be used in autonomous vehicles in 5+ years as all switch to the vision based approach.

[MindFieldMusic]

This is a topic I'm really interested in. I have a fair bit of experience with Waymo, Tesla, and even Cruise. My 2cents: I'm glad Cruise is off the roads. It was a really uncomfortable experience. It couldn't even stop at a stop sign without slamming on the brakes. Waymo is much better. Very smooth like a professional driver, but very limited service area. You both mentioned that you haven't tried the latest version of FSD, and I would suggest experiencing it. The latest version is very good for a generalized solution. Of course it's not as good as Waymo, but it can also go many places that Waymo can't.

[sjwright]

23:08 This guest seems to have some fundamental misconceptions around how Tesla accrues training data. He seems to think that FSD needs to be engaged in order for it to learn. The opposite is true. Their system is trained while humans are driving. When a human takes over from FSD, this is treated as a strong signal to pay attention to how a human driver behaves. You tried to correct his misconception but he incorrectly doubled down on it.

[ralphpanhuyzen]

Interesting how in the equation 1. Car - 2. Driving - 3. Traffic (incl. regulations)... AV developers focus on 2. replacing the human driver by some sort of technology, and on Traffic (3.). The Car (1.) is completely left out of the equation, like there is no fundamental difference between maneuvering a Cybertruck and a VW Beetle through dense city traffic. Would be interested to hear your comments on this... Cheers.

[StefanNorberg]

Level 3 is weirdly described imho. The main difference between L3 and L4 is that the ODD is much smaller and the car can leave the ODD rolling using a controlled handover, where the computer is still driving and is liable until complete. Also, Waymo has loads of safety rails around the machine learning and redundancy (such as several sensing modalities and more and better cameras) that Tesla's L2 solution doesn't need (as they can fail, beep and blame the human at all times). I doubt we'll see a pure end-to-end system driving this decade. There are no safety critical pure ML apps at all afaik, not even radiology.

[danieldnbt]

Right off the bat with the SAE levels already with the bad takes lol

[CCxWudz]

I would suggest trying out the latest in self driving before doing an AI self driving podcast where you openly admit you haven’t tried FSD in a year (it was literally heuristics last year vs AI this year)

[rolandkertesz]

Good conversation, but I think you didn’t talk enough about scale. Waymo need to premap a city. And that can’t be automated, cause the system can’t drive there. And waymo miles and tesla fsd miles aren’t even comparable. In a chart you almost can’t see the waymo miles

[jasonk]

Timothy B. Lee's vocal fry is unlistenable. I'll read the transcript.

[butdadmygame]

This is a lotta talk about a technology that is worse than trains.