Cerebellar Control of Robot Arms

Abstract

D ecades of research into the str ucture and function of the cerebellum have led to a clear understanding of many of its cells, as well as how lear ning takes place.Furthermore, there are many theories on what signals the cerebellum operates on, and how it works in concert with other parts of the ner vous system.Nevertheless, the application of computational cerebellar models to the control of robot dynamics remains in its infant state.To date, a few applications have been realized, but limited to the control of traditional robot structures which, strictly speaking , do not require adaptive control for the tasks that are perfor med since their dynam ic structures are relatively simple.The currently emerging family of light-weight robots (H irzinger, G. (1996) In Proceedings of the 2nd International C onference on Advanced Robotics, Intelligent Automation, and Active System s, V ienna, Austria) poses a new challenge to robot control: owing to their complex dynamics, traditional methods, depending on a full analysis of the dynamics of the system, are no longer applicable since the joints inuence each other's dynamics during movement.Can arti cial cerebellar models compete here?In this paper, we present a succinct introd uction of the cerebellum , and discuss where it could be applied to tackle problems in robotics.W ithout conclusively answering the above question, an over view of several applications of cerebellar models to robot control is given.