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

2025-05-02

AI Summary

Addressing the challenge of high-speed, high-precision robotic table tennis strokes across multiple playing styles (loop, drive, and chop), this paper proposes a lightweight five-degree-of-freedom manipulator platform coupled with an optimal trajectory generation method that jointly parameterizes end-effector pose and velocity. A terminal-constrained optimal control problem (OCP) is formulated based on state constraints at impact time, and a fixed-horizon model predictive control (MPC) framework is designed to enable millisecond-level online replanning and closed-loop response. For the first time, multi-style stroke dynamics are unified within a single model on low-inertia, high-torque hardware—explicitly balancing swing acceleration, spin control, and trajectory robustness. Experimental results demonstrate an average ball exit velocity of 11 m/s and an overall success rate of 88% across all three stroke types.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Achieving precise robotic table tennis hits with varied styles and spins
• Designing lightweight high-torque arm for rapid acceleration and control
• Implementing MPC to adapt swing trajectories for dynamic ball tracking

Innovation

• Custom lightweight high-torque five-DOF arm
• Optimal control problem for swing trajectories
• Fixed-horizon MPC for real-time adjustments