FailSafe: a simulation-trained VLM spots VLA failures and issues 7-DoF fixes at IROS 2026

DJiafei · x · 2026-09-26

The author announces FailSafe at IROS 2026 (Oral Sep 28, 15:51; Poster Pod B10), presented by a co-author. FailSafe addresses VLAs that can't recover from failed actions, especially when frozen: a companion VLM trained only in simulation performs corrective decoding, detecting impending failures and issuing executable 7-DoF fixes for more reliable manipulation.

Original post →

More from Embodied

Embodied channel →