English

Stylized Table Tennis Robots Skill Learning with Incomplete Human Demonstrations

Robotics 2023-09-19 v1

Abstract

In recent years, Reinforcement Learning (RL) is becoming a popular technique for training controllers for robots. However, for complex dynamic robot control tasks, RL-based method often produces controllers with unrealistic styles. In contrast, humans can learn well-stylized skills under supervisions. For example, people learn table tennis skills by imitating the motions of coaches. Such reference motions are often incomplete, e.g. without the presence of an actual ball. Inspired by this, we propose an RL-based algorithm to train a robot that can learn the playing style from such incomplete human demonstrations. We collect data through the teaching-and-dragging method. We also propose data augmentation techniques to enable our robot to adapt to balls of different velocities. We finally evaluate our policy in different simulators with varying dynamics.

Keywords

Cite

@article{arxiv.2309.08904,
  title  = {Stylized Table Tennis Robots Skill Learning with Incomplete Human Demonstrations},
  author = {Xiang Zhu and Zixuan Chen and Jianyu Chen},
  journal= {arXiv preprint arXiv:2309.08904},
  year   = {2023}
}

Comments

Submitted to ICRA 2024

R2 v1 2026-06-28T12:23:23.453Z