Algoritmo Genético Orientado à Desordem para a Otimização da Exploração de Ambientes por Enxames de Robôs

Abstract

Robotics, as part of the technological landscape, has developed at an accelerated pace. New approaches are constantly sought to address everyday problems through the use of robots, which has led to many solutions but also numerous challenges. As demands become more specific and data volumes increase, there is a growing need for systems that are increasingly focused on technical aspects. Within this context, this work proposes the application and adaptation of an evolutionary algorithm to optimize the parameters of the PheroCom robot swarm coordination model. To this end, entropy was adapted to act as an evaluation metric within the algorithm’s fitness function, serving as a multiplicative index in a penalization system during task execution.This approach enables the identification of configurations that promote a more balanced spatial distribution among robots, improving environmental coverage efficiency while avoiding both excessive concentration and the neglect of certain regions. Experimental results show that entropy, as part of the evaluation criterion, allows for an effective analysis of exploration homogeneity and promotes a more coherent and distributed occupation of space by the robots. Furthermore, the results also demonstrate satisfactory efficiency when compared to ther eference model.