Residual Fault Adaptation for Dexterous In-Hand Manipulation Under Runtime Joint Faults

Linan Deng, Xing Liu, Lin Hong, Feng Hua, Guijun Ma, Zuogong Yue, Fumin Zhang · N/A · 2026

Summary

Dexterous in-hand manipulation requires coordinated control of multiple actuated joints, and a runtime joint fault can abruptly disrupt the contact configuration required for successful manipulation.

Abstract Summary

Dexterous in-hand manipulation requires coordinated control of multiple actuated joints, and a runtime joint fault can abruptly disrupt the contact configuration required for successful manipulation. In this work, we propose residual fault adaptation (RFA), a teacher-anchored framework for compensating for hidden command-channel faults. RFA retains a frozen healthy teacher to provide nominal behavior and trains a recurrent residual policy to infer corrective actions from proprioceptive and command-response history. During training, fault-injection domain randomization (FIDR) varies the fault mode, affected joint, severity, and onset time, while adaptive sampling increases the frequency of fault modes associated with lower recent performance. A frozen Direct FIDR policy provides a distributional reference only on fault-active training samples and is absent from deployment. The deployed controller receives neither fault labels nor controller-switching signals. Simulation experiments on the dexterous hand indicate that RFA can improve manipulation performance relative to the healthy policy under a fixed mixed-fault protocol. Real-robot experiments with software-injected faults further demonstrate zero-shot deployment of the learned adaptation policy.

Key Points

Dexterous in-hand manipulation requires coordinated control of multiple actuated joints, and a runtime joint fault can abruptly disrupt the contact configuration required for successful manipulation.
In this work, we propose residual fault adaptation (RFA), a teacher-anchored framework for compensating for hidden command-channel faults.
RFA retains a frozen healthy teacher to provide nominal behavior and trains a recurrent residual policy to infer corrective actions from proprioceptive and command-response history.
During training, fault-injection domain randomization (FIDR) varies the fault mode, affected joint, severity, and onset time, while adaptive sampling increases the frequency of fault modes associated with lower recent performance.
A frozen Direct FIDR policy provides a distributional reference only on fault-active training samples and is absent from deployment.

Residual Fault Adaptation

Overview of RFA during training and deployment is shown in Fig. 1 , which summarizes the separation between training-only fault variables and deployed information. Training proceeds in three stages: healthy-policy pretraining, Direct FIDR reference training, and residual-policy training, with the corresponding components detailed in the following subsections.

Fault injection and adaptive sampling operate outside the controller, which receives only proprioceptive and command-response history.

Residual Fault Adaptation — Residual Fault Adaptation for Dexterous In-Hand Manipulation Under Runtime Joint Faults — Fig. 1: Overview of RFA during training and deployment. The healthy policy $\pi_{\mathrm{H}}$ is trained first and then frozen as the healthy teacher. Direct FIDR $\pi_{\mathrm{F}}$ is trained as a training-only reference, after which the recurrent residual policy $\pi_{\mathrm{R}}$ is trained around $\pi_{\mathrm{H}}$. At deployment, only $\pi_{\mathrm{H}}$ and $\pi_{\mathrm{R}}$ are active; an external fault-injection operator maps the nominal candidate target $\hat{\mathbf{q}}_{t+1}$ to the delivered target $\tilde{\mathbf{q}}_{t+1}$ without exposing fault parameters or labels to the controller.

Experiments

RFA is evaluated under matched simulation protocols and in a targeted physical study using a LEAP Hand. The simulation experiments quantify healthy and post-onset task-level outcomes under the fixed mixed-fault protocol and include fault-mode, mechanism, and severity analyses. The physical study characterizes command realization, joint responses, and object rotation.

The simulation experiments use a 16-DoF LEAP Hand in Isaac Lab to rotate the DexCube about the world $z$-axis. Fig.

Experiments — Residual Fault Adaptation for Dexterous In-Hand Manipulation Under Runtime Joint Faults — Fig. 2: Experimental setup of the 16-DoF LEAP Hand.

Sources and Demonstrations

Figures are reproduced from Deng et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.