Robotic Table Tennis: A Case Study into a High Speed Learning System

TL;DR

This paper details a comprehensive robotic table tennis system that combines perception, control, simulation, and autonomous training to achieve high-speed, precise ball returns and autonomous operation.

Contribution

It introduces an integrated system with novel design choices for perception, control, simulation, and autonomous training, enabling high-speed robotic table tennis with zero-shot transfer.

Findings

Achieved hundreds of successful rallies with a human opponent.

Demonstrated precise ball targeting and autonomous training capabilities.

Identified key factors affecting system latency and robustness.

Abstract

We present a deep-dive into a real-world robotic learning system that, in previous work, was shown to be capable of hundreds of table tennis rallies with a human and has the ability to precisely return the ball to desired targets. This system puts together a highly optimized perception subsystem, a high-speed low-latency robot controller, a simulation paradigm that can prevent damage in the real world and also train policies for zero-shot transfer, and automated real world environment resets that enable autonomous training and evaluation on physical robots. We complement a complete system description, including numerous design decisions that are typically not widely disseminated, with a collection of studies that clarify the importance of mitigating various sources of latency, accounting for training and deployment distribution shifts, robustness of the perception system, sensitivity to policy hyper-parameters, and choice of action space. A video demonstrating the components of the system and details of experimental results can be found at https://youtu.be/uFcnWjB42I0.