外观
论文arXiv 2610.1357219 天前
ATHLETE：通过Trajectory-Guided Motion Matching学习反应式人形网球
原文链接：ATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion Matching（arXiv 2610.13572 · 发布日期：2026-10-09）
ATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion Matching
ATHLETE用通用运动数据和普通网球视频生成全身参考，并在真机人形机器人上验证反应式网球击球与多拍对打。
核心要点
- 人形网球需在快速变化球动态下全身协调，专用动捕示范采集成本高。
- 方法结合LAFAN1运动数据和视频提取击球动作，用TGMM构建任务条件全身参考。
- 通过物理教师-学生学习、在线DAgger蒸馏和PPO微调得到部署策略。
- 真机上正反手命中率90.00%和86.67%，并实现与人类多拍对打，提供视频和代码。
验证范围与局限：验证范围为一台真实人形机器人上的正手、反手击球及与人类多拍对打。
英文摘要 (Abstract)
Humanoid tennis requires reactive whole-body coordination under rapidly changing ball dynamics, yet collecting task-specific motion-capture demonstrations that cover diverse approach states, contact locations, and timing conditions is costly. Inspired by how humans acquire new skills by combining reusable motor experience with task-specific demonstrations, we present ATHLETE, a framework for learning reactive humanoid tennis from generic locomotion data and ordinary tennis videos. ATHLETE combines LAFAN1 locomotion with video-derived striking motions and uses Trajectory-Guided Motion Matching (TGMM) to construct diverse task-conditioned whole-body references. These references are transformed into a reactive policy through physics-based teacher--student learning with online DAgger distillation, followed by PPO fine-tuning for the tennis task. The resulting policy responds directly to robot and ball observations without requiring reference-motion inputs at deployment. On a real humanoid robot, ATHLETE achieves forehand and backhand hit rates of $90.00%$ and $86.67%$, respectively, and enables multi-shot rallies with human players. These results demonstrate that ATHLETE can learn dynamic humanoid tennis skills from reusable locomotion data and video demonstrations. Result videos and code can be found at https://anonymous.4open.science/w/ATHLETE2027/.
作者：Zhihao Tian, Zifan Wang, Enzheng Zhu, Xun Yang, Jialong Qin, Mengbo Wang, Junwei Liang
来源
本页事实对应的公开页面，以原文为准。