The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Bringing AI Up to Speed with Autonomous Racing w/ Madhur Behl - #494
Jun 21, 2021
Madhur Behl, an Assistant Professor at the University of Virginia, dives into the thrilling world of autonomous racing and AI. He shares insights on how training AI for high-speed environments differs from traditional driving tasks. The conversation covers the unique challenges of perception and planning in racing, as well as the innovative techniques of sensor fusion versus vision-only approaches. Behl also hints at their upcoming race at the Indianapolis Motor Speedway, where his team aims for a million-dollar prize with their fully autonomous vehicle.
AI Snips
Chapters
Transcript
Episode notes
Racing vs. Urban Driving
- Autonomous racing and urban driving share core robotics challenges (perception, planning, control).
- Racing focuses on agility at the limits of control, potentially enhancing safety by preparing for extreme scenarios.
Perception Challenges at High Speeds
- High speeds in racing create perception challenges: blurred images, sensor skew, and synchronization issues.
- Limited data exists on sensor performance at these speeds, requiring sensor-specific solutions.
F1 Game as Simulator
- Madhur Behl's team uses a photorealistic Formula One game as a simulator.
- They tap into the game's data stream for images and ground truth data to train AI.