George Hotz: Comma.ai, OpenPilot, and Autonomous Vehicles
Lex Fridman Podcast
The Importance of Clustering in Driver Behavior Analysis
Good drivers are clustered together while bad drivers are scattered. Learn from the good drivers and let the net automatically learn the majority policy. However, there may be multiple clusters of good drivers, each requiring different policies. The hope is to discover universally good policies. Context dependency and scene analysis play a role in selecting the right policy. The ultimate goal is for the distribution to be unbiased. The advice for Tesla is to improve and navigate auto pilot.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
