Failure recoveryIntermediate
Recova: Agent-Guided Failure Recovery for Autonomous Robotic Manipulation
This preprint presents Recova, an agent-guided framework that jointly develops task execution and failure recovery in a reconstructed digital twin and refines both through real-robot data collection. It attains 78.8% mean success on LIBERO-Pro and 64.9% on MolmoSpaces, versus 71.7% and 38.0% for the strongest baselines; on four real-robot tasks it reaches 87.5% success and cuts observed human intervention from 87.5% to 0% over four collection rounds. The work matters because it turns failures into reusable recovery skills and reduces the human supervision needed to keep manipulation policies running.