期刊名称:International Journal of Advanced Robotic Systems
印刷版ISSN:1729-8806
电子版ISSN:1729-8814
出版年度:2005
卷号:2
期号:3
DOI:10.5772/5786
语种:English
出版社:SAGE Publications
摘要:The specialized hairs and slit sensillae of spiders (Cupiennius salei) can sense the airflow and auditory signals in a low-frequency range. They provide the sensor information for reactive behavior, like e.g. capturing a prey. In analogy, in this paper a setup is described where two microphones and a neural preprocessing system together with a modular neural controller are used to generate a sound tropism of a four-legged walking machine. The neural preprocessing network is acting as a low-pass filter and it is followed by a network which discerns between signals coming from the left or the right. The parameters of these networks are optimized by an evolutionary algorithm. In addition, a simple modular neural controller then generates the desired different walking patterns such that the machine walks straight, then turns towards a switched-on sound source, and then stops near to it.