# 基于强化学习的四足机械臂多地形自适应全身控制

> 原文链接：https://robotics.hellobike.com/papers/2026-10-16-2610-23548
> 频道：papers | 更新日期：2026-10-16 | 标签：arxiv, cs.RO
> 核心摘要：针对复杂地形下四足机械臂末端任务一致性难题，提出强化学习全身控制框架，并在小型平台实地验证。

# 基于强化学习的四足机械臂多地形自适应全身控制

::: v-pre
> 原文链接：[Reinforcement Learning Based Multi-Terrain Adaptive Whole-Body Control for a Quadruped Manipulator](https://arxiv.org/abs/2610.23548)（arXiv 2610.23548 · 发布日期：2026-10-16）

**Reinforcement Learning Based Multi-Terrain Adaptive Whole-Body Control for a Quadruped Manipulator**

针对复杂地形下四足机械臂末端任务一致性难题，提出强化学习全身控制框架，并在小型平台实地验证。

## 核心要点

- 地形扰动和运动-操作强耦合，使小型四足平台在行走中保持末端行为一致仍具挑战。
- 方法结合混合任务表示与任务优先全身学习，协调运动和操作并保持任务一致末端行为。
- 研究开发了轻量四足机械臂平台，用于验证所提框架在小型四足系统上的效果。
- 真实实验在最高30度斜坡、楼梯和可变形地形上成功部署，显示真实环境可行性。

**验证范围与局限**：验证范围为真实世界小型四足机械臂平台，地形包括最高30度斜坡、楼梯和可变形地形。

## 英文摘要 (Abstract)

Legged robots equipped with manipulators offer promising capabilities for loco-manipulation tasks in unstructured environments. However, achieving task-consistent end-effector behavior during locomotion remains challenging due to terrain-induced disturbances and the strong coupling between locomotion and manipulation, particularly for small-scale quadruped platforms. A reinforcement-learning based whole-body control framework is proposed for quadruped loco-manipulation on complex terrain. The proposed framework combines a hybrid task representation with task-prioritized whole-body learning to coordinate locomotion and manipulation while preserving task-consistent end-effector behavior. A lightweight quadruped manipulator platform is further developed to validate the proposed framework on a small-scale quadruped system. Real-world experiments demonstrate successful deployment on complex terrains such as slopes up to 30 degrees, stairs, and deformable terrain. These results demonstrate the feasibility of deploying learned whole-body control policy for quadruped loco-manipulation in real-world environments and highlight the importance of task-consistent whole-body coordination for terrain-adaptive loco-manipulation.

作者：Yanzhou Jin, Fei Suo, Chang Liu, Yasuhisa Hasegawa, Liming Chen, Yusuke Iwasawa, Yutaka Matsuo, Yaonan Zhu
:::

## 原始参考来源 (Sources)

- [arXiv 2610.23548：Reinforcement Learning Based Multi-Terrain Adaptive Whole-Body Control for a Quadruped Manipulator](https://arxiv.org/abs/2610.23548)