Article

Backtrack: Lightweight Failure Detection and Backtracking Recovery for Frozen VLAs

The authors propose Backtrack, a lightweight failure detection and recovery mechanism for frozen VLAs that requires no recovery demonstrations, policy retraining, or additional inference models. It uses a failure prediction head that adds only 0.48-0.88% to the parameter count to read the VLA's internal representations; when the predicted failure probability exceeds a threshold, it pauses the policy, backtracks the robot arm's recent motion, and hands control back to the original policy for a retry.

Part of the event: Backtrack: A Lightweight Failure Recovery Mechanism for Frozen VLAs

This page provides a summary and source link only.