Biomimetic smooth pursuit based on fast learning of the target dynamics

Following a moving target with a narrow-view foveal vision system is one of the essential oculomotor behaviors of humans and humanoids. This oculomotor behavior, called "smooth pursuit", requires accurate tracking control which cannot be achieved by a simple visual negative feedback controller due to the significant delays in visual information processing. In this paper, we present a biologically inspired smooth pursuit controller consisting of two cascaded subsystems: one is an inverse model controller for the oculomotor system; and the other is a learning controller for the dynamics of the visual target. The latter learns how to predict the target motion in head coordinates such that the tracking performance can be improved. We investigate our smooth pursuit system in simulations and experiments on a humanoid robot. By using a fast online statistical learning network, our humanoid oculomotor system is able to acquire a high performance smooth pursuit after about 5 seconds of learning despite significant processing delays in the system.

[1]  P. Kumar,et al.  Theory and practice of recursive identification , 1985, IEEE Transactions on Automatic Control.

[2]  Mitsuo Kawato,et al.  Feedback-Error-Learning Neural Network for Supervised Motor Learning , 1990 .

[3]  Sridhar Mahadevan,et al.  Robot Learning , 1993 .

[4]  Hidenori Kimura,et al.  Visual servoing with hand-eye manipulator-optimal control approach , 1996, IEEE Trans. Robotics Autom..

[5]  Ian D. Reid,et al.  The Active Recovery of 3D Motion Trajectories and Their Use in Prediction , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  H. Komatsu,et al.  Relation of cortical areas MT and MST to pursuit eye movements. II. Differentiation of retinal from extraretinal inputs. , 1988, Journal of neurophysiology.

[7]  Lawrence Stark,et al.  Predictive Control of Eye Tracking Movements , 1962 .

[8]  S. Whittaker,et al.  Learning patterns of eye motion for foveal pursuit. , 1982, Investigative ophthalmology & visual science.

[9]  Stefan Schaal,et al.  Fast and efficient incremental learning for high-dimensional movement systems , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[10]  M. Kawato,et al.  Inverse-dynamics model eye movement control by Purkinje cells in the cerebellum , 1993, Nature.

[11]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[12]  R. Carpenter,et al.  Movements of the Eyes , 1978 .

[13]  D. Robinson.  Control of eye movements , 1981 .

[14]  Lennart Ljung,et al.  Theory and Practice of Recursive Identification , 1983 .

[15]  Minoru Asada,et al.  Adaptive Visual Servoing for Various Kinds of Robot Systems , 1997, ISER.

[16]  Patrick Rives,et al.  Positioning of a robot with respect to an object, tracking it and estimating its velocity by visual servoing , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[17]  Stefan Schaal,et al.  Biomimetic gaze stabilization based on feedback-error-learning with nonparametric regression networks , 2001, Neural Networks.