Whole Body Model Predictive Control for Spin-Aware Quadrupedal Table Tennis

2025-10-09

AI Summary

Dynamic table-tennis tasks for quadrupedal robots face three core challenges: high-speed perception, spin-aware ball trajectory prediction, and whole-body agile control. To address these, we propose a physics-informed spin inference method augmented with learned residuals to accurately estimate ball velocity and spin parameters; design a novel whole-body model predictive control (MPC) framework that autonomously generates diverse striking strategies while ensuring full-body coordination; and deploy an external high-speed camera system to establish a low-latency perception–decision–execution closed loop. Implemented on the Boston Dynamics Spot platform, our system achieves, for the first time, robust real-world returns of topspin, backspin, and sidespin balls, and demonstrates sustained human–robot rallies. This work establishes a scalable, integrated paradigm for perception–planning–control in legged robots performing high-speed dynamic interaction tasks.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Motion & Tracking

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Developing table tennis robots that mirror human speed, accuracy, and ability to predict and respond to the full range of ball spins remains a significant challenge for legged robots. To demonstrate these capabilities we present a system to play dynamic table tennis for quadrupedal robots that integrates high speed perception, trajectory prediction, and agile control. Our system uses external cameras for high-speed ball localization, physical models with learned residuals to infer spin and predict trajectories, and a novel model predictive control (MPC) formulation for agile full-body control. Notably, a continuous set of stroke strategies emerge automatically from different ball return objectives using this control paradigm. We demonstrate our system in the real world on a Spot quadruped, evaluate accuracy of each system component, and exhibit coordination through the system's ability to aim and return balls with varying spin types. As a further demonstration, the system is able to rally with human players.

Problem

• Developing quadrupedal robots that play table tennis with human-like agility
• Predicting ball trajectories with spin using physical models and learned residuals
• Achieving full-body coordination through novel model predictive control formulation

Innovation

• Whole body model predictive control for quadrupedal robots
• Physical models with learned residuals infer spin
• Continuous stroke strategies from ball return objectives