Predicting the Future Paths and Semantics on Objects

We predict a set of short time horizon future trajectories on all objects. We can use these to anticipate the danger situation here and apply whatever, you know, breaking and steering actions required to avoid a collision. The autopilot vision stack predicts more than just the geometry and kinematics of the world. It also predicts a rich set of semantics which enables safe and human-like driving. Shri will tell us how we run all these cool neural networks on our FSD computer.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.