# 撑住自己：面向强力人形操作的任务条件化环境支撑

> 原文链接：https://robotics.hellobike.com/papers/2026-09-21-2609-25486
> 频道：papers | 更新日期：2026-09-21 | 标签：arxiv, cs.RO
> 核心摘要：针对人形机器人强力操作易扰动平衡，SHS用单手环境支撑引导双强化学习策略，并在Unitree G1上验证。

# 撑住自己：面向强力人形操作的任务条件化环境支撑

::: v-pre
> 原文链接：[Brace Yourself: Task-Conditioned Environmental Bracing for Forceful Humanoid Manipulation](https://arxiv.org/abs/2609.25486)（arXiv 2609.25486 · 发布日期：2026-09-21）

**Brace Yourself: Task-Conditioned Environmental Bracing for Forceful Humanoid Manipulation**

针对人形机器人强力操作易扰动平衡，SHS用单手环境支撑引导双强化学习策略，并在Unitree G1上验证。

## 核心要点

- 强力操作中的交互力会扰动全身平衡，限制人形机器人的操作能力。
- SHS优化任务条件化支撑配置，引导两项同步强化学习策略协同执行。
- 方法无需人体运动数据或在线全身轨迹规划，可一手支撑一手操作。
- 在Unitree G1上接触力达60 N，并较无支撑和任务无关支撑提升表现。

**验证范围与局限**：验证范围为Unitree G1上的强力操作及不同任务区域；摘要未说明更多机器人或任务类型。

## 英文摘要 (Abstract)

Forceful manipulation is challenging for humanoid robots because interaction forces can disturb whole-body balance. We introduce the Supporting Hand Strategy (SHS), which enables a humanoid to brace against the environment with one hand while performing forceful manipulation with the other. SHS optimises a task-conditioned support configuration that guides two synchronous reinforcement-learning policies, without human motion data or online whole-body trajectory planning. On a Unitree G1, SHS achieved usable contact forces up to 60 N, compared with a maximum sustained force of 13.5 N without environmental bracing, while substantially improving force tracking over a task-independent support configuration. The same policies generalised to different task regions without retraining. SHS therefore provides a simple mechanism for substantially extending humanoid forceful-manipulation capability.

作者：Zongyuan Zhang, Christopher Lehnert, Will Neil Browne, Jonathan M. Roberts
:::

## 原始参考来源 (Sources)

- [arXiv 2609.25486：Brace Yourself: Task-Conditioned Environmental Bracing for Forceful Humanoid Manipulation](https://arxiv.org/abs/2609.25486)