Virus-Evolutionary Genetic Algorithm for Fuzzy Spiking Neural Network of A Mobile Robot in A Dynamic Environment
Hironobu Sasaki, Naoyuki Kubota · 2006 SICE-ICASE International Joint Conference · 2006
Recently, embodied cognition for robotics has been discussed, and various types of artificial neural networks are applied for behavior learning of mobile robots in unknown and dynamic environments. In this research, the behavioral learning based on a spiking neural network to realize high adaptability of a mobile robot is proposed. The robot learn the forward relationship from sensory inputs to motor outputs as well as the predictive relationship from motor outputs to the sensory inputs. However, the behavioral leaning capability of the robot depends strongly on the network structure. Therefore, a VEGA to acquire the network structure suitable to the changing environment is applied. Finally, the effectiveness of the proposed method through experimental results on behavioral learning for collision avoidance and target tracing behavior is discussed