Counter-ant algorithm for evolving multirobot collaboration

Abstract

The use of multirobot systems, is affecting our society in a fundamental way; from their use in hazardous environments, to their application in automated environmental cleanup. In an unknown environment, one of the most important problem related to multirobot systems, is to decide how to coordinate actions in order to achieve tasks in an optimal way. Ant algorithms are proved to be very useful in solving such distributed control problems. We introduce in this paper a modified version of the known ant algorithm, called Counter-Ant Algorithm (CAA). Indeed, the robots' collaborative behaviour is based on repulsion instead of attraction to pheromone, which is a chemical matter open to evaporation and representing the core of ants' cooperation. In order to test the performance of our CAA, we implement, simulate and test our algorithm in a generic multirobot environment. In practical terms, the subdivision of the cleaning space is achieved in emergent and evolving way. A series of simulations show the usefulness of our algorithm for adaptive and cooperative cleanup.

ARG_FuzzySim: Concluding Failed Multilateral Argumentation-Based Negotiation

“…Secondly, we propose to enrich it in order to be able to represent new forms of negotiations in particular the combined, multilevel and heuristic negotiations. And why not implant our system in the context of multirobot systems [19].…”

Fuzzy counter-ant for avoiding the stagnation of multirobot exploration

“…Let' s consider another view of swarm intelligence inspired from ant colony optimization called Counter-Ant Algorithm (CAA) [17][18][19] . In reality, the robots' collaborative behavior is based on repulsion instead of attraction to pheromone-a chemical evaporating matter-that represents the core of ants' cooperation.…”

“…The main step forward that this work represents relative to our previous work [18,19] is to propose to integrate a fuzzy system inspired by the biological behavior of ants. If we observe the reaction of real ants in two different paths marked by pheromone (an experience for shortest path discovery), we note that ants react according to pheromone quantity in both paths and opt for the path containing the highest pheromone quantity.…”

On the potential contributions of hybrid intelligent approaches to Multicomponent Robotic System development

“…Sometimes the basis for the cooperation is to obtain the maximum reward for the system as a whole. Task decomposition strategies have been implemented by means of ant colony optimization (ACO) [28,39,194,196] or reinforcement learning paradigms [9,53,74,103,167,178,195]. On the other hand, the competitive approach is applied mainly when the roles of other environmental elements are taken into account as in robot soccer [9,54,75,83,167], or when the system is inspired on a general multi-agent approach [74,106].…”