PSO-based strategy for the segregation of heterogeneous robotic swarms

Abstract

A robotic swarm is a particular type of multi-robot system that employs a large number of simpler agents in order to cooperatively perform different types of tasks. A topic that has received much attention in recent years is the idea of segregation. This concept is important, for example, in tasks that require maintaining robots with similar features or objectives arranged in cohesive groups, while robots with different characteristics remain separated in their own groups. In this paper, we propose a decentralized methodology to segregate heterogeneous groups of robots that are randomly distributed on the environment. Our approach to segregate robots consists of extending the Optimal Reciprocal Collision Avoidance (ORCA) algorithm with a navigation strategy inspired on the Particle Swarm Optimization (PSO). A series of simulations in different scenarios shows that the groups were able to successfully converge to a segregated state in all the evaluated cases. Furthermore, the methodology allowed for a faster convergence of the groups when compared to the state-of-the-art technique.