Distributed behavior learning of multiple mobile robots based on spiking neural network and steady-state genetic algorithm

摘要

This paper deals with a method of distributed behavior learning of multiple mobile robots. Various types of artificial neural networks are applied for behavior learning of mobile robots in unknown and dynamic environments. In the paper, we propose a method of distributed behavioral learning based on a spiking neural network. The robot learns the forward relationship from sensory inputs to motor outputs and inverse predictive relationship from motor outputs to sensory inputs. However, the behavioral leaning capability of the robot depends strongly on the network structure. Therefore, we use a parallel steady-state genetic algorithm for acquiring the network topology suitable to the environment. Finally, we discuss the effectiveness of the proposed method through simulation results on behavioral learning.