Strategy and Skill Learning for Physics-based Table Tennis Animation

SIGGRAPH 2024

Jiashun Wang1 Jessica Hodgins1,2 Jungdam Won3
1Carnegie Mellon Universty 2The AI Institute 3Seoul National University
Paper Appendix Code

A human plays with the agent via VR.

The agent plays with another agent with different strategies and skills.

The agent strikes the ball to the target with the target skill command.

Ball Control Policy

Imitation Policy

Mocap Data

BibTeX

@inproceedings{wang2024strategy,
      title={Strategy and Skill Learning for Physics-based Table Tennis Animation},
      author={Wang, Jiashun and Hodgins, Jessica and Won, Jungdam},
      booktitle={ACM SIGGRAPH 2024 Conference Papers},
      pages={1--11},
      year={2024}
    }