Genetic algorithm for a fuzzy spiking neural network of a mobile robot

It is very difficult to design the learning structure of a robot beforehand in an unknown and dynamic environment, because the dynamics of the environment is unknown. Therefore, this paper proposes a fuzzy spiking neural network (FSNN) for behavior learning of a mobile robot. Furthermore, the network structure of the FSNN should be adaptive to the environmental condition. In this paper, we apply a steady-state genetic algorithm for acquiring the suitable network structure through the interaction with the environment. The simulation results show the robot can update the network structure and learn the weights of FSNN according to the spatio-temporal context of the facing environment.