arXiv 2507.073562025-09-18cs.RO

UniTracker：学习用于人形机器人的通用全身运动跟踪器

UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robots

Shanghai Jiao Tong Univeristy（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）；Peking University（北京大学）；Zhejiang University（浙江大学）；Fudan University（复旦大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；ShanghaiTech University（上海科技大学）

Kangning Yin, Weishuai Zeng, Ke Fan, Minyue Dai, Zirui Wang, Qiang Zhang, Zheng Tian, Jingbo Wang, Jiangmiao Pang, Weinan Zhang

备注：: three-stage universal motion tracker for humanoid robots

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出三阶段训练框架 UniTracker，利用 CVAE 学习全局运动潜在表示以解决部分观测下的泛化与漂移问题，并通过快速自适应模块提升难跟踪序列的精度，在仿真和真实人形机器人上均表现出强劲的运动跟踪与部署能力。

摘要：

实现具有表现力且可泛化的全身运动控制，对于将人形机器人部署到真实世界环境中至关重要。在本研究中，我们提出了 UniTracker，这是一个三阶段训练框架，能够在广泛的人类行为中实现鲁棒且可扩展的运动跟踪。在第一阶段，我们利用特权观测训练教师策略，以生成高质量动作。在第二阶段，我们引入条件变分自编码器（CVAE）来建模可直接部署于真实硬件的通用学生策略。CVAE 结构使策略能够学习运动的全局潜在表示，增强了对未见行为的泛化能力，并解决了标准基于 MLP 的策略在部分观测下的局限性。不同于在朝向等全局属性上容易出现漂移的纯 MLP，我们的 CVAE 学生策略通过将部分观测先验与全观测编码器对齐，在训练过程中融入了全局意图。在第三阶段，我们引入了快速自适应模块，在难以直接跟踪的困难运动序列上对通用策略进行微调。这种自适应既可针对单个序列执行，也支持批量模式，进一步展示了本方法的灵活性与可扩展性。我们使用 Unitree G1 人形机器人在仿真和真实世界环境中对 UniTracker 进行了评估，证明了其在运动多样性、跟踪精度和部署鲁棒性方面的强劲表现。

英文摘要：

Achieving expressive and generalizable whole-body motion control is essential for deploying humanoid robots in real-world environments. In this work, we propose UniTracker, a three-stage training framework that enables robust and scalable motion tracking across a wide range of human behaviors. In the first stage, we train a teacher policy with privileged observations to generate high-quality actions. In the second stage, we introduce a Conditional Variational Autoencoder (CVAE) to model a universal student policy that can be deployed directly on real hardware. The CVAE structure allows the policy to learn a global latent representation of motion, enhancing generalization to unseen behaviors and addressing the limitations of standard MLP-based policies under partial observations. Unlike pure MLPs that suffer from drift in global attributes like orientation, our CVAE-student policy incorporates global intent during training by aligning a partial-observation prior to the full-observation encoder. In the third stage, we introduce a fast adaptation module that fine-tunes the universal policy on harder motion sequences that are difficult to track directly. This adaptation can be performed both for single sequences and in batch mode, further showcasing the flexibility and scalability of our approach. We evaluate UniTracker in both simulation and real-world settings using a Unitree G1 humanoid, demonstrating strong performance in motion diversity, tracking accuracy, and deployment robustness.

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。