arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.12656cs.ROcs.AI
收藏

PMG:用于类人运动控制的参数化运动生成器

PMG: Parameterized Motion Generator for Human-like Locomotion Control

Tsinghua University(清华大学);ZERITH Robotics(ZERITH机器人公司);University of Michigan(密歇根大学)

Chenxi Han, Yuheng Min, Zihao Huang, Ao Hong, Hang Liu, Yi Cheng, Houde Liu

AI总结:

PMG通过参数化运动生成技术,实现了高效、自然的人形机器人运动控制,支持高维控制输入并实现仿真到现实的可靠转移。

摘要:

近年来,数据驱动的强化学习和运动跟踪在人形机器人运动领域取得了显著进步,但仍然存在关键的实践挑战。特别是,虽然低层运动跟踪和轨迹跟随控制器已经成熟,但全身参考引导方法难以适应更高层的命令接口和多样的任务环境:它们需要大量高质量的数据集,在速度和姿态领域易碎,并且对机器人特定的校准敏感。为了解决这些限制,我们提出了参数化运动生成器(PMG),这是一种实时运动生成器,基于对人类运动结构的分析,仅使用一组紧凑的参数化运动数据和高维控制命令来合成参考轨迹。结合模仿学习流程和基于优化的仿真到现实的电机参数识别模块,我们在我们的人形原型ZERITH Z1上验证了完整的方法,并证明在单一集成系统中,PMG能够产生自然、类人的运动,精确响应高维控制输入——包括基于VR的远程操作,并实现高效的、可验证的仿真到现实的转移。这些结果确立了一条实用、经过实验验证的道路,朝着自然和可部署的人形控制迈进。网站:https://pmg-icra26.github.io/

英文摘要:

Recent advances in data-driven reinforcement learning and motion tracking have substantially improved humanoid locomotion, yet critical practical challenges remain. In particular, while low-level motion tracking and trajectory-following controllers are mature, whole-body reference-guided methods are difficult to adapt to higher-level command interfaces and diverse task contexts: they require large, high-quality datasets, are brittle across speed and pose regimes, and are sensitive to robot-specific calibration. To address these limitations, we propose the Parameterized Motion Generator (PMG), a real-time motion generator grounded in an analysis of human motion structure that synthesizes reference trajectories using only a compact set of parameterized motion data together with high-dimensional control commands. Combined with an imitation-learning pipeline and an optimization-based sim-to-real motor parameter identification module, we validate the complete approach on our humanoid prototype ZERITH Z1 and show that, within a single integrated system, PMG produces natural, human-like locomotion, responds precisely to high-dimensional control inputs-including VR-based teleoperation-and enables efficient, verifiable sim-to-real transfer. Together, these results establish a practical, experimentally validated pathway toward natural and deployable humanoid control. Website: https://pmg-icra26.github.io/

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。

↑