基于BP网络的机器人感觉运动系统研究

Research on Sensorimotor System of Robot Based on BP Neural Network

摘要: 生物的诸多技能是在生物个体的生长发育过程中逐渐形成和发展起来的，能否赋予机器人这样一种特性呢？为此，本文基于BP神经网络为机器人建立起一种类似生物的感觉运动系统，使机器人与外界环境之间交互作用，产生自主负趋光行为。实验结果表明机器人在建立的基于BP神经网络的人工感觉运动系统中，能够通过多次的学习，实现自主负趋光行为，并且产生的行为与由生物所产生的行为一致。

Abstract: Many skills of the natural life are gradually formed and developed during growth and development of indi- vidual organisms. Can a machine be endowed with such characteristics? With the aim, this paper builds a sensorimotor system based on BP neural network for robot. The robot communicates with the environment, and learns negative pho- totaxis. Experiment indicates that the robot with a sensorimotor system based on BP neural network can realize negative phototaxis through several steps of learning, which is the same as the natural life.