An Upper Confidence Bound for Simultaneous Exploration and Exploitation in Heterogeneous Multi-Robot Systems

TL;DR

This paper introduces a novel upper confidence bound method for coordinating heterogeneous multi-robot systems that balances exploration and exploitation simultaneously, improving efficiency in unknown environments.

Contribution

It presents a new upper confidence bound based on mutual information and a decentralized Monte Carlo tree search for scout-task robot coordination.

Findings

Effective in multi-drone surveillance scenarios

Balances exploration and exploitation without explicit trade-off

Addresses practical coordination challenges in heterogeneous teams

Abstract

Heterogeneous multi-robot systems are advantageous for operations in unknown environments because functionally specialised robots can gather environmental information, while others perform tasks. We define this decomposition as the scout-task robot architecture and show how it avoids the need to explicitly balance exploration and exploitation~by permitting the system to do both simultaneously. The challenge is to guide exploration in a way that improves overall performance for time-limited tasks. We derive a novel upper confidence bound for simultaneous exploration and exploitation based on mutual information and present a general solution for scout-task coordination using decentralised Monte Carlo tree search. We evaluate the performance of our algorithms in a multi-drone surveillance scenario in which scout robots are equipped with low-resolution, long-range sensors and task robots capture detailed information using short-range sensors. The results address a new class of coordination problem for heterogeneous teams that has many practical applications.