# 手指即腿：用仿人手学习自支撑运动与操作

> 原文链接：https://robotics.hellobike.com/papers/2026-09-15-2609-17172
> 频道：papers | 更新日期：2026-09-15 | 标签：arxiv, cs.RO
> 核心摘要：该研究用强化学习让仿人手以手指同时支撑、移动和交互，并在仿真与硬件上验证。

# 手指即腿：用仿人手学习自支撑运动与操作

::: v-pre
> 原文链接：[Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand](https://arxiv.org/abs/2609.17172)（arXiv 2609.17172 · 发布日期：2026-09-15）

**Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand**

该研究用强化学习让仿人手以手指同时支撑、移动和交互，并在仿真与硬件上验证。

## 核心要点

- 问题在于行走机器人手需用同一组手指移动身体、承重并与环境交互。
- 方法保留手指设计和位置控制器，采用考虑不等长手指的强化学习，并用硬件测量校准仿真器。
- 仿真中，该奖励设计比原用于四足机器人的调参奖励使手移动更快。
- 硬件上，任务策略实现无缆爬行、转向、跌倒恢复、无视觉键盘命令和视觉反馈推物。

**验证范围与局限**：验证包括校准仿真和自包含硬件平台上的爬行、转向、跌倒恢复、键盘与推物任务。

## 英文摘要 (Abstract)

A walking robotic hand must use the same fingers to move its body, support its weight, and interact with the environment. We show how an anthropomorphic hand can learn these skills while retaining its finger design and position controller. Onboard power and computation make the platform self-contained. Our reinforcement learning approach accounts for the hand's unequal fingers, with training in a simulator calibrated from hardware measurements. In simulation, the hand moves faster with our reward formulation than with tuned rewards originally designed for quadrupeds. On hardware, task-specific policies enable untethered crawling, steering, and fall recovery. While supporting its own weight, the hand also executes successive keyboard commands without vision and pushes an object to targets using overhead visual feedback. These results demonstrate a compact mobile manipulator that reuses its fingers for locomotion and interaction, without a separate locomotion mechanism.

作者：Amirhossein Kazemipour, Hehui Zheng, Robert Kevin Katzschmann
:::

## 原始参考来源 (Sources)

- [arXiv 2609.17172：Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand](https://arxiv.org/abs/2609.17172)