paper-with-me

Papers

Learning Humanoid Arm Motion via Centroidal Momentum Regularized Multi-Agent Reinforcement Learning

2025-07-05 · Ho Jae Lee, Se Hwan Jeon, Sangbae Kim arxiv

Humans naturally swing their arms during locomotion to regulate whole-body dynamics, reduce angular momentum, and help maintain balance. Inspired by this principle, we present a limb-level multi-agent reinforcement learning (RL) framework that enables coordinated whole-body control of humanoid robots through emergent arm motion. Our approach employs separate actor-critic structures for the arms and legs, trained with centralized critics but decentralized actors that share only base states and centroidal angular momentum (CAM) observations, allowing each agent to specialize in task-relevant behaviors through modular reward design. The arm agent guided by CAM tracking and damping rewards promotes arm motions that reduce overall angular momentum and vertical ground reaction moments, contributing to improved balance during locomotion or under external perturbations. Comparative studies with single-agent and alternative multi-agent baselines further validate the effectiveness of our approach. Finally, we deploy the learned policy on a humanoid platform, achieving robust performance across diverse locomotion tasks, including flat-ground walking, rough terrain traversal, and stair climbing.

📄 PDF Abstract BibTeX arXiv:2507.04140

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

HybridMimic: Hybrid RL-Centroidal Control for Humanoid Motion Mimicking

2026-03-06 · Ludwig Chee-Ying Tay, I-Chia Chang, Yan Gu arxiv

Motion mimicking, i.e., encouraging the control policy to mimic human motion, facilitates the learning of complex tasks via reinforcement learning (RL) for humanoid robots. Although standard RL frameworks demonstrate imp…

Reinforcement Learning

Torque Controlled Locomotion of a Biped Robot with Link Flexibility

2022-10-27 · Nahuel A Villa, Pierre Fernbach, Maximilien Naveau, Guilhem Saurel 외

When a big and heavy robot moves, it exerts large forces on the environment and on its own structure, its angular momentum can varysubstantially, and even the robot's structure can deform if there is a mechanical weaknes…

ADP: Adversarial Dynamics Priors for Physically Grounded Humanoid Locomotion

2026-07-03 · Seokju Lee, Jeongtae Lee, Jeonghyeok Lim, Jeonguk Kang 외 arxiv

In this paper, we propose Adversarial Dynamics Priors (ADP) for perturbation-resilient humanoid locomotion control. Existing motion prior-based methods induce natural motion styles by imitating kinematic motion features,…

A Whole-Body Motion Imitation Framework from Human Data for Full-Size Humanoid Robot

2025-08-01 · Zhenghan Chen, Haodong Zhang, Dongqi Wang, Jiyu Yu 외 arxiv

Motion imitation is a pivotal and effective approach for humanoid robots to achieve a more diverse range of complex and expressive movements, making their performances more human-like. However, the significant difference…

Cost-Matching Model Predictive Control for Efficient Reinforcement Learning in Humanoid Locomotion

2026-03-30 · Wenqi Cai, Kyriakos G. Vamvoudakis, Sébastien Gros, Anthony Tzes arxiv

In this paper, we propose a cost-matching approach for optimal humanoid locomotion within a Model Predictive Control (MPC)-based Reinforcement Learning (RL) framework. A parameterized MPC formulation with centroidal dyna…

Reinforcement Learning