发表机构
Department of Automation, Tsinghua University; Beijing Key Laboratory of Embodied Intelligence Systems; Institute for Embodied Intelligence and Robotics, Tsinghua University（清华大学自动化系; 北京具身智能系统重点实验室; 清华大学具身智能与机器人研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究仿人机器人轮滑运动，提出基于对抗运动先验的强化学习框架，用于泵式滑行和推式滑行两种步态。通过动作捕捉收集数据并处理成参考运动状态，用独立管道学习步态，经模拟实验评估步态相关指标。
AI 中文摘要
仿人轮滑具有挑战性，因为机器人必须协调全身平衡、滚动接触和速度相关的姿势调节。本文提出了一种基于对抗运动先验的强化学习框架，用于两种仿人轮滑步态：泵式滑行和推式滑行。通过动作捕捉独立收集两个步态数据集，并分别重定向到仿人机器人。然后对重定向的数据进行平滑和重新采样，以生成用于对抗运动先验（AMP）训练的参考运动状态。通过独立的AMP训练管道学习这两种步态，每个管道都有单独的参考数据集、策略和奖励架构。设计了模拟实验来评估步态质量、速度跟踪、转弯和特定步态奖励消融。
英文摘要
Humanoid roller-skating is difficult because the robot must coordinate whole-body balance, rolling contacts, and velocity-dependent posture regulation. This paper presents an adversarial motion prior based reinforcement learning framework for two humanoid roller-skating gaits: Pump Glide skating and Push Glide skating. The two gait datasets are collected independently through motion capture and retargeted to the humanoid robot separately. The retargeted data are then smoothed and resampled into reference motion states for AMP training. The two gaits are learned by independent AMP training pipelines with separate reference datasets, separate policies, and independent reward architectures. Simulation experiments are designed to evaluate gait quality, velocity tracking, turning, and gait-specific reward ablations.
Comments12 pages. Submitted preprint version. Accepted for oral presentation at CLAWAR 2026
