Future neuro mobile robots

摘要

Neurocomputing is considered as an approach to robotic processing.nBased on transformations, it autonomously develops operationalncapabilities in adaptive response to information training. The idea ofntraining a mobile robot to carry out a function (instead of programmingnit) seems to have a great appeal, perhaps because of our familiaritynwith training in some robotic applications (e.g. teaching trajectoryngeneration) as an easy and natural way to acquire new skill processingncapabilities. Even though neural networks mobile robotic applicationsnare still fully undeveloped, this paper tries to show that their promisenand potential is evident. We show this by describing which neuralnnetworks have been used (or are suitable to be used) for various mobilenrobot capabilities, and what sort of problems are expected to surfacenout; if any. We then propose a system of interacting neural networks tonbe used as a model for future neuro mobile robots. Finally, experimentsnon Neurobot, a six legged articulated robot testbed, for testing variousnnetworks as well as for providing a perspective on the usefulness ofnintegrating various mobile robot capabilities are presented