Practical AI Autonomous Vehicle Research at Waymo
41 snips
Nov 13, 2025 
Drago Anguelov, Waymo's VP and head of the AI Foundations team, discusses the cutting-edge advancements in driverless technology. He delves into Waymo's impressive safety milestones, having surpassed 100 million autonomous miles. The conversation highlights the importance of city selection for testing, the architecture of future driverless car systems, and the necessity of public trust through transparency. Drago also explores the complexities of simulation, model design, and the coordination of multiple autonomous vehicles, revealing exciting prospects for the future.
AI Snips
Chapters
Transcript
Episode notes
Pick Cities To Grow Capabilities
- Choose test cities by balancing market impact and technical diversity in driving conditions.
- Expand operational domains gradually (urban, highways, snow) to validate capabilities systematically.
AVs Are Purpose-Built Robots
- An autonomous vehicle is a robot on wheels combining cameras, LiDAR, radar, microphones, onboard compute, and redundant actuators.
- Hardware and redundancy are designed from the ground up for safe transportation under failure scenarios.
Structure Of The Driving Stack
- The driving stack needs perception, world representation, prediction, and planning to select actions.
- Companies vary between many modular models and fewer large onboard models, with different end-to-end training choices.