Robot navigation in simulated pedestrian areas based on swarm intelligence

Abstract

In this paper we present a method that relies on swarm intelligence to confront the problem of navigating in non-structured dynamic environments. The collective behavior of a group of particles is used to find an obstacle-free path that is able to adapt its course as the structure of the environment changes. Of particular importance is the rule that governs collision avoidance in that it not only takes into account the positions of the obstacles, but also their velocities.