Preprint
Sep 2026
RoboRecover: Benchmarking Robot Policy Recovery under Execution Deviations
Results show that initial-state performance does not determine recovery performance and policies exhibit different recovery strengths across scenarios, and RoboRecover establishes recovery from execution-induced intermediate states as a distinct dimension of robot policy evaluation.
Yang Li, Chen Zhao, Zhuo-Ran Wang et al.
· 1 citation