Composing Learned Robot Behaviors with Temporal Logic at Runtime

Name: Composing Learned Robot Behaviors with Temporal Logic at Runtime
Uploaded: 2026-10-06T04:35:00.860069+00:00
Duration: 663 s
Description: hint2 guides robot learning by using two hierarchical world models at inference time to satisfy complex Linear Temporal Logic (LTL) instructions. A high-level model predicts long-term progress toward goals, while a low-level model ensures immediate safety constraints are met. This allows the robot to select actions that simultaneously achieve long-horizon planning and local safety.

hint2 guides robot learning by using two hierarchical world models at inference time to satisfy complex Linear Temporal Logic (LTL) instructions. A high-level model predicts long-term progress toward goals, while a low-level model ensures immediate safety constraints are met. This allows the robot to select actions that simultaneously achieve long-horizon planning and local safety.

Open the full episode