Fast learning of biomimetic oculomotor control with nonparametric regression networks
- 7 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 3847-3854 vol.4
- https://doi.org/10.1109/robot.2000.845331
Abstract
Accurate oculomotor control is one of the essential pre-requisites of successful visuomotor coordination. Given the variable nonlinearities of the geometry of binocular vision as well as the possible nonlinearities of the oculomotor plant, it is desirable to accomplish accurate oculomotor control through learning approaches. We investigate learning control for a biomimetic active vision system mounted on a humanoid robot. By combining a biologically inspired cerebellar learning scheme with a state-of-the-art statistical learning network, our robot system is able to acquire high performance visual stabilization reflexes after about 40 seconds of learning despite significant nonlinearities and processing delays in the system.Keywords
This publication has 6 references indexed in Scilit:
- Learning of oculo-motor control: a prelude to robotic imitationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Cerebellar learning for control of a two-link arm in muscle spacePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Constructive Incremental Learning from Only Local InformationNeural Computation, 1998
- A model of the cerebellum in adaptive control of saccadic gainBiological Cybernetics, 1996
- Feedback-Error-Learning Neural Network for Supervised Motor LearningPublished by Elsevier ,1990
- Neuronlike adaptive elements that can solve difficult learning control problemsIEEE Transactions on Systems, Man, and Cybernetics, 1983