arXiv 2509.091062025-10-19cs.RO

LIPM引导的强化学习用于双足机器人的稳定与感知运动

LIPM-Guided Reinforcement Learning for Stable and Perceptive Locomotion in Bipedal Robots

School of Automation and Intelligent Manufacturing (AIM), Southern University of Science and Technology（自动化与智能制造学院，南方科技大学）；Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology（土木与环境工程系，香港科技大学）；Department of Mechanical Engineering, The University of Hong Kong（机械工程系，香港大学）；Zhejiang University-University of Illinois Urbana-Champaign Institute (ZJUI), Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所，浙江大学）；LimX Dynamics, Shenzhen, China（深圳LimX动力有限公司）

Haokai Su, Haoxiang Luo, Shunpeng Yang, Kaiwen Jiang, Wei Zhang, Hua Chen

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出受LIPM启发的奖励设计，结合RFM与双评论家架构，使双足机器人在室外复杂地形中实现稳定、鲁棒且具备感知能力的运动。

摘要：

由于复杂的地形几何形状以及易受外部干扰影响，在非结构化室外环境中实现双足机器人稳定且鲁棒的感知运动仍是一项关键挑战。在本工作中，我们提出一种受线性倒立摆模型（Linear Inverted Pendulum Model，LIPM）启发的新型奖励设计，以实现在野外的感知与稳定运动。LIPM通过调节质心（center of mass，CoM）高度和躯干朝向，为动态平衡提供理论指导。这些因素是地形感知运动的关键，因为它们有助于确保机器人相机拥有稳定的视点。基于这一洞见，我们设计了一个奖励函数，在促进平衡和动态稳定性的同时，鼓励准确的CoM轨迹跟踪。为了在速度跟踪与稳定性之间进行自适应权衡，我们利用Reward Fusion Module（RFM）方法，在需要时优先考虑稳定性。我们采用双评论家架构分别评估稳定性和运动目标，从而提高训练效率和鲁棒性。我们通过在仿真和真实室外环境中对双足机器人进行大量实验来验证所提方法。结果表明，该方法具有优异的地形适应性、干扰抑制能力，并在广泛速度范围和感知条件下保持一致性能。

英文摘要：

Achieving stable and robust perceptive locomotion for bipedal robots in unstructured outdoor environments remains a critical challenge due to complex terrain geometry and susceptibility to external disturbances. In this work, we propose a novel reward design inspired by the Linear Inverted Pendulum Model (LIPM) to enable perceptive and stable locomotion in the wild. The LIPM provides theoretical guidance for dynamic balance by regulating the center of mass (CoM) height and the torso orientation. These are key factors for terrain-aware locomotion, as they help ensure a stable viewpoint for the robot's camera. Building on this insight, we design a reward function that promotes balance and dynamic stability while encouraging accurate CoM trajectory tracking. To adaptively trade off between velocity tracking and stability, we leverage the Reward Fusion Module (RFM) approach that prioritizes stability when needed. A double-critic architecture is adopted to separately evaluate stability and locomotion objectives, improving training efficiency and robustness. We validate our approach through extensive experiments on a bipedal robot in both simulation and real-world outdoor environments. The results demonstrate superior terrain adaptability, disturbance rejection, and consistent performance across a wide range of speeds and perceptual conditions.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。