|
Vol: 48(62) No: 1 / March 2003 Neural Mechanisms of Learning and Control in Mobile Robotic Systems M. Dragoicea Department of Automatic Control and Systems Engineering, Politehnica University Bucharest, Independentei 313, 77206 Bucharest, Romania, phone: (421) 402 9167, e-mail: ma-dragoicea@ics.pub.ro I. Dumitrache Department of Automatic Control and Systems Engineering, Politehnica University Bucharest, Independentei 313, 77206 Bucharest, Romania, e-mail: idumitrache@ics.pub.ro Keywords: mobile robots, cognitive models, perception, behavior, neural networks control, autonomous navigation. Abstract Today AI roboticists often turn to biological sciences being that animals can provide existence proofs of different aspects of intelligence. By focusing on the way living creatures \"do\" something (i.e. analyzing \"inputs\" and \"outputs\" of their behavior) roboticists can gain insights into how to organize \"intelligence\". This paper proposes a strategy for mobile robot control that naturally integrates intelligent techniques for autonomous navigation. A new application of artificial neural networks for autonomous navigation of mobile robots in a reactive way is depicted here. In the perception of the sensory information of different modalities that defines the mobile robot environment, the major learning strategy seems to be biologically characterized by sensory information categorization and classification. Therefore neural networks models of self-organizing type were used in order to establish and adapt a place representation through a progressive learning process in which fast learning takes place. References [1] Murphy, R. R., 2000, Introduction to AI Robotics, MIT Press. [2] I. Dumitrache, Intelligent control of industrial robots, Mediamira Press, Cluj, 1996. [3] Dragoicea, M., Dumitrache, I., Cuculescu, D.S., 2003, Multi-behavioral model based autonomous navigation of the mobile robots, International Journal Automation Austria, Vol. 11, Nr.1, pp:1-20, ISSN 1562-2703 [4] Doya, K., 1999, What are the computations of the cerebellum, the basal ganglia and the cerebral cortex, Neural Networks, Vol. 12, 961-977. [5] Doya, K., 2000, Complementary roles of basal ganglia and cerebellum in learning and motor control, Current Opinion in Neurobiology, Vol. 10, 732-739. [6] O\'Keefe, J., Nadel, L., 1978, The hippocampus as a cognitive map, Oxford University Press, Oxford. [7] Maguire, E.A., Burges, N., et.al., 1998, Knowing where and getting there: A human navigation network, Science(280), 921-924. [8] Taube, J.S., Muller, R.U., et.al., 1990, Head-direction cells recorded from the postsubiculum in freely moving rats. I. Description and quantitative analysis, J. Neuroscience (10), 420-435. [9] Chen, L.L., Lin, L., et. al., 1994, Head-direction cells in the rat posterior cortex: II. Contributions of visual and ideothetic information to the directional firing, Exp Brain Res (101), 23-34. [10] Blair, H.T., Sharp, P., 1995, Anticipatory head direction signals in anterior thalamic: evidence for a thalamocortical circuit that integrates angular head motion to compute head direction, J. Neuroscience (15), 6260-6270. [11] Nehmzow, U., 2000, Mobile Robotics: A Practical Introduction, Springer, London. [12] Dumitrache, I., Dragoicea, M., 2002, Design of a reactive implementation for autonomous navigation of the mobile robots, Robotics National Conference CNR\'2002, Craiova Ed. Universitaria, pp: 111 - 118. [13] Arbib, M., Schema Theory. The handbook of brain theory and neural networks, MIT Press. [14] Carpenter, G. A., Grossberg, S., 1987, ART2: Self-organization of stable category recognition codes for analog input patterns, Applied Optics, 26, 4919-4930. [15] Fausett, Lauren, 1994, Fundamentals of neural networks. Architectures, algorithms, and applications, Prentice Hall. |