Stochastic Cellular Automata Ant Memory model for swarm robots performing efficiently the garbage collection task

Abstract

Collective intelligence has attracted attention of many researchers seeking to understand different real-world problems. In swarm robotics, the study of this area has revolutionized control algorithms, especially when they are aligned with other techniques that allow the easy programming of these robotic equipment. This work proposes a control algorithm for homogeneous and heterogeneous robots teams that perform garbage collection task based on cellular automata ants and Tabu search. Unlike precursor methods, in this work both searching and homing states are stochastic and the deposition and decline pheromone parameters are dynamic over time. From simulations it was possible to show that the new controller is adaptable to different parameters and at the same time is efficient in the garbage collection task for swarm robotics.