ATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion Matching

Key points

• 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.1
• ATHLETE combines LAFAN1 locomotion with video-derived striking motions and uses Trajectory-Guided Motion Matching (TGMM) to construct diverse task-conditioned whole-body references.1
• 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.1
• 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.1

Sources (1)

• [1]ATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion Matching
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 01:25 PM

  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.

  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.

Extractive summary: sentences quoted from the sources.