ATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion Matching
Overview
ATHLETE combines LAFAN1 locomotion with video-derived striking motions using TGMM to enable reactive humanoid tennis. It achieves 90.00% and 86.67% hit rates for forehand and backhand shots, enabling multi-shot rallies with human players without reference-motion inputs at deployment.
Generated from attributed reports · Updated 24 minutes ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Artifact availability · code: available
“id tennis skills from reusable locomotion data and video demonstrations. Result videos and code can be found at https://anonymous.4open.science/w/ATHLETE2027/.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion Matching
ATHLETE is a framework for learning reactive humanoid tennis from generic locomotion data and ordinary tennis videos. It combines LAFAN1 locomotion with video-derived striking motions using Trajectory-Guided Motion Matching (TGMM) to construct diverse whole-body references. These are refined through physics-based teacher-student learning and PPO fine-tuning, achieving 90.00% and 86.67% hit rates for forehand and backhand shots, respectively, and enabling multi-shot rallies with human players.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).