# 运行时关节故障下灵巧手手内操作的残差故障自适应

> 原文链接：https://robotics.hellobike.com/papers/2026-09-15-2609-17404
> 频道：papers | 更新日期：2026-09-15 | 标签：arxiv, cs.RO
> 核心摘要：针对运行时关节故障扰乱灵巧手手内操作，提出RFA残差自适应框架，并在仿真和真机软件注入故障中验证。

# 运行时关节故障下灵巧手手内操作的残差故障自适应

::: v-pre
> 原文链接：[Residual Fault Adaptation for Dexterous In-Hand Manipulation Under Runtime Joint Faults](https://arxiv.org/abs/2609.17404)（arXiv 2609.17404 · 发布日期：2026-09-15）

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

针对运行时关节故障扰乱灵巧手手内操作，提出RFA残差自适应框架，并在仿真和真机软件注入故障中验证。

## 核心要点

- 运行时关节故障会突然破坏成功操作所需的接触配置。
- RFA保留冻结健康教师，并训练循环残差策略从本体感知和命令响应历史推断修正动作。
- 训练中用FIDR随机化故障模式、关节、严重度和发生时间，并自适应采样低性能故障模式。
- 仿真表明RFA在固定混合故障协议下优于健康策略，真机软件注入故障展示零样本部署。

**验证范围与局限**：验证范围为灵巧手仿真实验和软件注入故障的真机实验。

## 英文摘要 (Abstract)

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.

作者：Linan Deng, Xing Liu, Lin Hong, Feng Hua, Guijun Ma, Zuogong Yue, Fumin Zhang
:::

## 原始参考来源 (Sources)

- [arXiv 2609.17404：Residual Fault Adaptation for Dexterous In-Hand Manipulation Under Runtime Joint Faults](https://arxiv.org/abs/2609.17404)