Recova
Recova

Introducing Recova

Robots that
recover.

Agent-guided failure recovery.
From simulation to the real world.

Explore the research

Recova: Agent-Guided Failure Recovery for Autonomous Robotic Manipulation

Isabella Liu1, An-Chieh Cheng1, Johan Bjorck3, Zhiding Yu3, Hongxu Yin3, Jan Kautz3, Linxi Fan3, Yuke Zhu2,3, Sifei Liu3

1 University of California, San Diego

2 University of Texas at Austin

3 NVIDIA

Overview

We present Recova, an agent-in-the-loop framework for failure recovery in robot manipulation. An agent first constructs a digital twin of the robot's workstation and explores the task in simulation, collecting successful trajectories, identifying failure modes, and developing recovery strategies. This experience initializes real-world deployment: successful and recovery trajectories train task and recovery policies, while agent-generated code offers an alternative way to transfer recovery behaviors.

During execution, Recova monitors rollouts, detects failures, and invokes recovery, requesting human assistance only when autonomous recovery fails. Human-assisted recoveries refine the recovery policy, and successful rollouts refine the task policy, forming a continuous learning loop that improves recovery and task success while reducing human intervention, enabling longer periods of reliable, unattended operation.

Recova workflow Recova builds and explores a digital twin. Simulation recovery knowledge prepares recovery skills. A transparent, outlined Real robot rollouts group contains the base policy, recovery skills, and Human. Failures invoke recovery skills, which restore the scene and resume the base policy. For unresolved failures, Recova requests human assistance, shown by an upward arrow from Recova to Human. Human recovery demonstrations improve recovery skills. A circular success-data loop improves the base policy. Illustrative line charts show increasing recovery success and decreasing human intervention. Real robot rollouts Build &explore Delegate Sim recovery knowledge Failure Unresolved Resume Success data Recovery demonstration Digital twin Base policy Recovery skills Human Recova Recovery success Humanintervention

DAgger data collection

Recova orchestrates policy rollouts across four stations, invokes recovery policies when needed, and hands control to a human operator for corrections when autonomous recovery cannot restore the scene.

RecovaCheck progress
Detect failures
Delegate task / recovery policies
Run task policy
Invoke recovery
Request a human
Collect data0 rollouts saved

Station 1Waiting to start a rollout.

00:00/12:30
Human interventionsLoading…10×

Drag the timeline to scrub all five views. Numbered markers identify human interventions for each station; select a marker to jump to it. Yellow camera outlines indicate a policy running, red indicates intervention, and green indicates task completion. Matching numbers connect each station in the main video to its top camera. Select a number to highlight that camera and Recova's recorded decision. Times refer to the original recording, ending at 12:30.

Digital twins

Recova builds a digital twin from real-world observations and attempts to solve the task in simulation. During iterative rollouts, we collect successful trajectories to train the base policy and analyze failures, prompting our agent to develop skills that recover from them.

Loading the digital twin…

GREEN CIRCLE

Drag to orbit · Scroll to zoom

Top camera
0:002× speed

Recovery skills

Recova discovers recovery skills as it attempts tasks in a simulated digital twin. During simulation rollouts, we collect successful trajectories and analyze failures, prompting our agent to develop skills that recover from them. These recovery skills then transfer to the real world in one of two ways: they are either executed directly as code-as-policy programs or used to generate simulated trajectories for training a recovery policy.

Simulation benchmarks

MolmoSpaces

View all reported numbers

LIBERO-Pro

View all reported numbers

Citation

@misc{recova2026project,
  title = {Recova: Agent-Guided Failure Recovery for Autonomous Robotic Manipulation},
  url   = {https://recova-bot.github.io/},
  year  = {2026},
  note  = {Project page; paper citation forthcoming}
}

Acknowledgements

We thank Cristaldo Campos, Jimmy Wu, and Tingwu Wang for their help with the real robot infrastructure and filming the demo.