The perception for partner robot using spiking neural network in dynamic environment

Abstract

This paper discusses a perceptual system using spiking neural network for a partner robot from the viewpoint of human visual perception. Recently, various types of robots equip various types of sensors for perceiving the environment. However, the robot is difficult to perceive the necessary information like a human. In this study, we emphasize the importance of human vision for the robot to realize flexible perception. Therefore, we propose a retinal model for a laser range finder, and the information extraction method using a spiking neural network based on perceiving-acting cycle. We apply the proposed method for a human tracking task. As an experimental result, we show the robot can directly perceive the necessary information by the attention mechanism for the flexible perception according to spatiotemporal context based on the spiking neural network.