Stylized Table Tennis Robots Skill Learning with Incomplete Human Demonstrations

TL;DR

This paper introduces an RL-based approach for training stylized table tennis robots that learn from incomplete human demonstrations and adapt to different ball velocities, improving realism and versatility.

Contribution

It presents a novel RL algorithm that learns stylized skills from incomplete demonstrations and employs data augmentation for velocity adaptation.

Findings

Robust learning of stylized table tennis skills from incomplete data

Effective adaptation to varying ball velocities

Successful policy evaluation across different simulators

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.