面向人形机器人的专业网球风格：自适应运动规划与跟踪
Towards Professional Tennis Styles for Humanoid Robots with Adaptive Motion Planning and Tracking
浏览论文内容
中文总结 AI 辅助
本研究提出AdaPT框架，从广播视频学习专业网球风格，通过自适应机制弥合仿真到现实的差距，在Unitree G1和Dobot Atom人形机器人上验证了有效性，为相关系统提供了见解。
中文摘要 AI 辅助
人形机器人近期在现实球类运动中展现出可观能力，但在保持强任务性能的同时实现专业运动风格仍具挑战。本研究提出AdaPT（Adaptive Motion Planning and Tracking，自适应运动规划与跟踪）框架，直接从广播视频学习专业网球发球与对打风格。该分层设计的核心思路是：规划器生成风格化运动学动作，跟踪器执行动作时尽可能少干扰规划。尽管在仿真中有效，但存在显著的现实差距：真实机器人上跟踪性能不可避免下降，自回归规划部分忽略该下降，且感知噪声会进一步加剧问题。为解决这些问题，我们的自适应机制通过学习跟踪随机执行速度来提升跟踪鲁棒性，同时通过学习到的运动-速度适配器调节规划器以缓解复合误差。在Unitree G1上的真实实验表明，我们的自适应机制在弥合现实差距方面有效。我们还将AdaPT策略部署在1.7米高的全尺寸Dobot Atom人形机器人上，在无运动捕捉的情况下展示了野外发球效果。此外，真实实验为未来人形球类运动系统揭示了算法与工程层面的见解。视频与代码可在项目网站获取。
英文摘要
Humanoid robots have recently demonstrated promising capabilities in real-world ball sports. However, achieving professional motion styles while maintaining strong task performance remains challenging. In this work, we propose AdaPT, an Adaptive Motion Planning and Tracking framework that learns professional tennis serving and rally styles directly from broadcast videos. This hierarchical design is motivated by the key insight that the planner generates stylistic kinematic motions, while the tracker executes them with minimal interference with planning. Despite its effectiveness in simulation, a substantial sim-to-real gap emerges: tracking performance inevitably degrades on real robots, and this degradation is partially overlooked by autoregressive planning and further compounded by noisy perception. To address these issues, our adaptation mechanism improves tracking robustness by learning to track randomized execution speeds, while conditioning the planner on a learned motion-speed adapter to mitigate compounding errors. Real-world experiments on the Unitree G1 demonstrate the effectiveness of our adaptation mechanism in bridging the sim-to-real gap. We further deploy AdaPT policies on the full-size Dobot Atom humanoid robot (1.7m) and demonstrate in-the-wild serving without motion capture. Beyond these results, our real-world experiments reveal both algorithmic and engineering insights for future humanoid ball-sports systems. Videos and code are available on our \href{https://humanoidtennis.github.io/AdaPT/}{project website}.
发表机构
- Noitom Robotics（诺亦腾机器人）
- Shanghai AI Laboratory（上海人工智能实验室）
- Shanghai Jiao Tong University（上海交通大学）
- Dobot Robotics（越疆机器人）
机构由 AI 辅助整理，请以论文原文为准。
