Very Large-scale Multi-Robot Task Allocation in Challenging Environments via Robot Redistribution

TL;DR

This paper introduces a scalable multi-robot task allocation method for challenging environments that considers robot paths to minimize conflicts, deadlocks, and completion time, outperforming existing approaches in dense clutter scenarios.

Contribution

The proposed method integrates path planning into task allocation using a Voronoi diagram-based roadmap and a redistribution mechanism, enabling efficient handling of hundreds of robots in complex environments.

Findings

Handles hundreds of robots in dense environments

Outperforms competitors in computation time

Reduces conflicts and deadlocks during task execution

Abstract

We consider the Multi-Robot Task Allocation (MRTA) problem that aims to optimize an assignment of multiple robots to multiple tasks in challenging environments which are with densely populated obstacles and narrow passages. In such environments, conventional methods optimizing the sum-of-cost are often ineffective because the conflicts between robots incur additional costs (e.g., collision avoidance, waiting). Also, an allocation that does not incorporate the actual robot paths could cause deadlocks, which significantly degrade the collective performance of the robots. We propose a scalable MRTA method that considers the paths of the robots to avoid collisions and deadlocks which result in a fast completion of all tasks (i.e., minimizing the \textit{makespan}). To incorporate robot paths into task allocation, the proposed method constructs a roadmap using a Generalized Voronoi Diagram. The method partitions the roadmap into several components to know how to redistribute robots to achieve all tasks with less conflicts between the robots. In the redistribution process, robots are transferred to their final destinations according to a push-pop mechanism with the first-in first-out principle. From the extensive experiments, we show that our method can handle instances with hundreds of robots in dense clutter while competitors are unable to compute a solution within a time limit.