Stigmergic Autonomous Navigation in Collective Robotics

Abstract

Unknown environments, noisy information and no human assistance provide several challenges and difficulties in autonomous robot navigation, especially when multiple robots operate together. Dealing with autonomous navigation in collective robotics requires sophisticated computational techniques, being the biologically-inspired approaches the most frequently adopted. One of them, named Swarm Intelligence, explores features of social insects like those of ants. This Chapter proposes two strategies for multi-robot communication based on stigmergy, that is, the ants communication by means of pheromones. In the deterministic strategy, the robots deposit artificial pheromones in the environment according to innate rules. On the other hand, in the strategy called evolutionary, the robots have to learn how and where to lay artificial pheromones. Each robot is controlled by an autonomous navigation system (ANS) based on Learning Classifier System, which evolves during navigation from no a priori knowledge, and should learn to avoid obstacles and capture targets disposed on the environment. Aiming to validate the ANS in collective scenarios and also to investigate the stigmergic communication strategies, several experiments are simulated. The results show that the robot’s communication by artificial pheromones implies a higher effectiveness in accomplishing the navigation tasks and the minimization of distances traveled between targets.