Learning Visuomotor Policy for Multi-Robot Laser Tag Game

TL;DR

This paper introduces an end-to-end visuomotor policy for multi-robot laser tag, trained via reinforcement learning and distillation, outperforming classic methods in accuracy and collision avoidance, and deployable on real robots.

Contribution

It presents a novel vision-based policy for multi-robot laser tag, overcoming observability issues and outperforming traditional modular approaches.

Findings

16.7% improvement in hitting accuracy

6% reduction in collisions

Successful real robot deployment

Abstract

In this paper, we study multi robot laser tag, a simplified yet practical shooting-game-style task. Classic modular approaches on these tasks face challenges such as limited observability and reliance on depth mapping and inter robot communication. To overcome these issues, we present an end-to-end visuomotor policy that maps images directly to robot actions. We train a high performing teacher policy with multi agent reinforcement learning and distill its knowledge into a vision-based student policy. Technical designs, including a permutation-invariant feature extractor and depth heatmap input, improve performance over standard architectures. Our policy outperforms classic methods by 16.7% in hitting accuracy and 6% in collision avoidance, and is successfully deployed on real robots. Code will be released publicly.