RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction

Understand

Vision-Language-Action (VLA) models have recently advanced robotic manipulation by translating natural-language instructions and visual observations into control actions.

• However, existing VLAs are primarily trained on successful expert demonstrations and lack structured supervision for failure diagnosis and recovery, limiting robustness in open-world scenarios.
• To address this limitation, we propose the Robotic Failure Analysis and Correction (RoboFAC) framework.
• We construct a large-scale failure-centric dataset comprising 9,440 erroneous manipulation trajectories and 78,623 QA pairs across 53 scenes in both simulation and real-world environments, with systematically categorized failure types.