Particle swarm optimization in multi-agents cooperation applications

Abstract

Rapid progress has been achieved in the development of group intelligence. However, most of the present group intelligence is external-driven. This thesis presents a Fully Automatic Multi-Agents Cooperation (FAMAC) strategy that is inner-motivated and enables multi-agents to perform autonomic cooperation independently of external instruction. To further improve the performance of FAMAC, a Multi-level--Multi-step PSO-Network ( PSO-Network) is put forward to replace Neural Networks in the Intelligent Learning and Reasoning Unit (ILRU). Through simulation, it is shown that the inner-motivated group intelligence is achievable and is efficient in prompting the capacity of multi-agents as a united team.