Abstract
In this article we present a neurally-inspired self-adaptive active binocular tracking scheme and an efficient mathematical model for online computation of desired binocular-head trajectories. The self-adaptive neural network (NN) model is general and can be adopted in output tracking schemes of any partly known robotic systems. The tracking scheme ingeniously combines the conventional Resolved Velocity Control (RVC) technique and an adaptive compensating NN model constructed using SoftMax basis functions as nonlinear activation function. Desired trajectories to the servo controller are computed online by the use of a suitable linear kinematics mathematical model of the system. Online weight tuning algorithm guarantees tracking with small errors and error rates as well as bounded NN weights.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Brunnström, K., Eklundh, J., and Uhlin, T.: Active fixation for scene exploration, IJCV 17(2) (1996), 137-162.
Chaumette, F., Rives, P., and Espiau, B.: Position of a robot with respect to an object, tracking it and estimating its velocity by visual servoing, in: Proc. of the IEEE Internat. Conf. on Robotics and Automation, 1991, pp. 2248-2253.
Corke, P. and Good, M.: Dynamic effects in visual closed-loop systems, IEEE Trans. Robotics Automat. 12(5) (1996), 671-683.
Corke, P. and Hutchinson, S. A.: Real-time vision, tracking and control, in: Proc. of the IEEE Internat. Conf. on Robotics and Automation, 2000, pp. 622-629.
Craig, J.: Introduction to Robotics: Mechanics and Control, 2nd edn, Addison-Wesley, Reading, MA, 1989.
Ertugrul, M. and Kaynak, O.: Neuro-sliding mode control of robotic manipulators, in: Proc. of the 8th Internat. Conf. on Advanced Robotics, 1997, pp. 951-956.
Fermüller, C. and Aloimonos, Y.: The role of fixation in visual motion analysis, IJCV 11(2) (1993), 165-186.
Gangloff, J. A., de Mathelin, M., and Abba, G.: 6 DOF high speed dynamic visual servoing using GPC controllers, in: Proc. of the IEEE Internat. Conf. on Robotics and Automation, 1998, pp. 2008-2013.
Horn, B. K. P.: Robot Vision, MIT Press, Cambridge, MA, 1986.
Hornik, K., Stinchcombe, M., and White, H.: Multilayer feedforward networks are universal approximators, Neural Networks 2(5) (1989), 359-366.
Huang, T. S. and Netravali, A. N.: Motion and structure from feature correspondence: A review, Proc. IEEE 82(2) (1994), 252-268.
Hutchinson, S., Hager, D., and Corke, P.: A tutorial on visual servo control, IEEE Trans. Robotics Automat. 12(5) (1996), 671-683.
Idan, M., Calise, A. J., and Kutay, A. T.: Adaptive neural network-based approach for active flow control, in: Proc. of ASME FEDSM'01, May-June 2001.
Ishiguro, A., Furuhashi, T., and Okuma, O.: A neural network compensator for uncertainties of robotics manipulators, IEEE Trans. Industr. Electronics 39(6) (1992), 565-569.
Koller, D., Daniilidis, K., and Nagel, H.: Model based object tracking in monocular image sequences of road traffic scenes, IJCV 10(3) (1993), 257-281.
Lewis, F. L., Liu, K., and Yesildirek, A.: Neural net robot controller with guaranteed tracking performance, IEEE Trans. Neural Networks 6(3) (1995), 703-715.
Lewis, F. L., Yesildirek, A., and Liu, K.: Multilayer neural-net robot controller with guaranteed tracking performance, IEEE Trans. Neural Networks 7(2) (1996), 388-399.
Malis, E., Chaumette, F., and Boudet, S.: 2-1/2-d visual servoing, IEEE Trans. Robotics Automat. 15 (1999), 238-250.
Morasso, P. and Sanguineti, V.: Self-organizing body schema for motor planning, J. Motor Behavior 27(1) (1995), 52-66.
Niculescu, S. I. and Annaswamy, A. M.: A simple adaptive controller for positive-real systems with time-delay, in: Proc. of the American Control Conference, June 2000, pp. 3666-3670.
Rougeaux, S. and Kuniyoshi, Y.: Robust tracking by a humanoid vision system, in: Proc. of the IARP, October 1998.
Seshagiri, S. and Khalil, H.: Output feedback control of nonlinear systems using RBF neural networks, IEEE Trans. Neural Networks 11(1) (2000), 69-79.
Song, Q., Xiao, J., and Soh, Y. C.: Robust backpropagation training algorithm for multilayered neural tracking controller, IEEE Trans. Neural Networks 10(5) (1999), 1133-1141.
Sun, F., Sun, Z., and Woo, P. Y.: Neural network-based adaptive controller design of robotic manipulators with an observer, IEEE Trans. Neural Networks 12(1) (2001), 54-67.
Tzafestas, S. G., Dalianis, P. J., and Anthopoulos, A.: On the overtraining phenomenon of back propagation neural networks, Math. Comput. Simulation 40(5/6) (1996), 507-521.
Tzafestas, S. G. and Tzafestas, E. S.: Intelligent industrial and service robotic systems: Architectural, artificial intelligence and prototyping issues, Systems Anal. Modelling Simulation (SAMS) 35 (1999), 131-173.
Tzafestas, S. G. and Tzafestas, E. S.: Learning, reasoning and problem solving in robotics, in: S. Y. Nof (eds), Handbook of Industrial Robotics, Wiley, New York, 1999, pp. 373-392.
Tzafestas, E. S., Nikolaidou, A., and Tzafestas, S. G.: Performance evaluation, and dynamic node-generation criteria for “principal component analysis” neural networks, Math. Comput. Simulation 51(3/4) (2000), 145-156.
Vidyasagar, M.: Nonlinear Systems Analysis, 2nd edn, Prentice-Hall, Englewood Cliffs, NJ, 1993.
Vincze, M.: Dynamics and system performance of visual servoing, in: Proc. of the IEEE Internat. Conf. on Robotics and Automation, 2000, pp. 644-649.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kumarawadu, S., Watanabe, K., Kiguchi, K. et al. Self-Adaptive Output Tracking with Applications to Active Binocular Tracking. Journal of Intelligent and Robotic Systems 36, 129–147 (2003). https://doi.org/10.1023/A:1022620623402
Issue Date:
DOI: https://doi.org/10.1023/A:1022620623402