Decision-making and simulation in multi-agent robot system based on PSO-neural network

In multi-agent robot system, each robot must behave by itself according to its states and environments. This paper proposes a method using neural networks and particle swarm optimization (PSO) for the decision-making in the multi-agent robot system. In this paper, a neural network is used for behavior decision controller. The inputs of the neural network are decided by the last actions of other robots. Then the outputs determine the next action that the robot will choose. The weight values imply the adaptiveness of robots in multi-agent robot system. The validity of the decision model is verified through simulation experiments and we could have observed the robots' emergent behaviors during simulation.