Efficient and Reactive Planning for High Speed Robot Air Hockey

TL;DR

This paper presents a method for high-speed, reactive planning enabling general-purpose robotic arms to perform air hockey tasks efficiently, demonstrating real-time performance and competitive gameplay in simulation.

Contribution

It introduces a novel planning approach tailored for high-speed reactive tasks, specifically applied to air hockey with general-purpose robotic manipulators.

Findings

Robots can perform fast-hitting movements in air hockey.

Two robots can play against each other in simulation.

The approach achieves real-time reactive planning.

Abstract

Highly dynamic robotic tasks require high-speed and reactive robots. These tasks are particularly challenging due to the physical constraints, hardware limitations, and the high uncertainty of dynamics and sensor measures. To face these issues, it's crucial to design robotics agents that generate precise and fast trajectories and react immediately to environmental changes. Air hockey is an example of this kind of task. Due to the environment's characteristics, it is possible to formalize the problem and derive clean mathematical solutions. For these reasons, this environment is perfect for pushing to the limit the performance of currently available general-purpose robotic manipulators. Using two Kuka Iiwa 14, we show how to design a policy for general-purpose robotic manipulators for the air hockey game. We demonstrate that a real robot arm can perform fast-hitting movements and that the two robots can play against each other on a medium-size air hockey table in simulation.