Data-Efficient Online Learning of Ball Placement in Robot Table Tennis

TL;DR

This paper introduces an online optimization method enabling a pneumatic robot arm with four degrees of freedom to efficiently learn to hit ping-pong balls onto specified targets, demonstrating rapid convergence and sample efficiency.

Contribution

It presents a novel online optimization algorithm for ball placement in robot table tennis that uses black-box and grey-box gradient approximations for rapid learning.

Findings

Achieves target placement within 2-5 iterations.

Demonstrates robustness with both black-box and grey-box gradients.

Shows rapid convergence and high sample efficiency.

Abstract

We present an implementation of an online optimization algorithm for hitting a predefined target when returning ping-pong balls with a table tennis robot. The online algorithm optimizes over so-called interception policies, which define the manner in which the robot arm intercepts the ball. In our case, these are composed of the state of the robot arm (position and velocity) at interception time. Gradient information is provided to the optimization algorithm via the mapping from the interception policy to the landing point of the ball on the table, which is approximated with a black-box and a grey-box approach. Our algorithm is applied to a robotic arm with four degrees of freedom that is driven by pneumatic artificial muscles. As a result, the robot arm is able to return the ball onto any predefined target on the table after about 2-5 iterations. We highlight the robustness of our approach by showing rapid convergence with both the black-box and the grey-box gradients. In addition, the small number of iterations required to reach close proximity to the target also underlines the sample efficiency. A demonstration video can be found here: https://youtu.be/VC3KJoCss0k.