High Speed Robotic Table Tennis Swinging Using Lightweight Hardware with Model Predictive Control

TL;DR

This paper introduces a high-speed robotic table tennis system utilizing lightweight hardware and model predictive control to achieve precise, powerful, and varied hits with high success rates.

Contribution

The paper presents a novel robotic platform with a custom lightweight arm and a model predictive control framework for diverse, high-speed table tennis strokes.

Findings

Achieved an average ball exit velocity of 11 m/s.

Attained an 88% success rate across different swing styles.

Demonstrated high precision and adaptability in hardware-based table tennis.

Abstract

We present a robotic table tennis platform that achieves a variety of hit styles and ball-spins with high precision, power, and consistency. This is enabled by a custom lightweight, high-torque, low rotor inertia, five degree-of-freedom arm capable of high acceleration. To generate swing trajectories, we formulate an optimal control problem (OCP) that constrains the state of the paddle at the time of the strike. The terminal position is given by a predicted ball trajectory, and the terminal orientation and velocity of the paddle are chosen to match various possible styles of hits: loops (topspin), drives (flat), and chops (backspin). Finally, we construct a fixed-horizon model predictive controller (MPC) around this OCP to allow the hardware to quickly react to changes in the predicted ball trajectory. We validate on hardware that the system is capable of hitting balls with an average exit velocity of 11 m/s at an 88% success rate across the three swing types.