Distributed Coverage Control of Multi-Agent Systems with Load Balancing in Non-convex Environments

TL;DR

This paper introduces a distributed coverage control method for multi-agent systems operating in non-convex environments, focusing on load balancing and cost minimization through novel partitioning and search algorithms.

Contribution

It proposes a new coverage formulation with a rotational partition strategy and a circular search algorithm for optimal deployment in non-convex regions.

Findings

Effective load balancing among agents.

Approximate optimal configurations with small tolerance.

Numerical simulations confirm approach efficacy.

Abstract

It is always a challenging task to service sudden events in non-convex and uncertain environments, and multi-agent coverage control provides a powerful theoretical framework to investigate the deployment problem of mobile robotic networks for minimizing the cost of handling random events. Inspired by the divide-and-conquer methodology, this paper proposes a novel coverage formulation to control multi-agent systems in the non-convex region while equalizing the workload among subregions. Thereby, a distributed coverage controller is designed to drive each agent towards the desired configurations that minimize the service cost by integrating with the rotational partition strategy. In addition, a circular search algorithm is proposed to identify optimal solutions to the problem of lowering service cost. Moreover, it is proved that this search algorithm enables to approximate the optimal configuration of multi-agent systems with the arbitrary small tolerance. Finally, numerical simulations are implemented to substantiate the efficacy of proposed coverage control approach.