Implementing reinforcement learning in the chaotic KIV model using mobile robot AIBO

We use the biologically inspired dynamic neural network architecture KIV to achieve robust goal-oriented navigation in a physical environment with obstacles. KIV operates on the principle of chaotic neurodynamics, in the style of brains. It performs the task of multi-sensory fusion, recognition, and decision-making in real time. We use the Sony AIBO robot to demonstrate the operation of our algorithm. AIBO's video camera and infra sensors have been complemented with an external camera for monitoring of the robot's position. The performance of the autonomous system is evaluated using goal-oriented navigation.

[1]  S. Muthu,et al.  Applying KIV dynamic neural network model for real time navigation by mobile robot EMMA , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[2]  R. Jindra.  Mass action in the nervous system W. J. Freeman, Academic Press, New York (1975), 489 pp., (hard covers). $34.50 , 1976, Neuroscience.

[3]  Donald O. Walter,et al.  Mass action in the nervous system , 1975 .

[4]  Robert Kozma,et al.  Navigation and Cognitive Map Formation Using Aperiodic Neurodynamics , 2004 .

[5]  Terrance L. Huntsberger,et al.  Biologically Inspired Autonomous Rover Control , 2001, Auton. Robots.

[6]  Robert Kozma,et al.  Learning spatial navigation using chaotic neural network model , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[7]  Edward Tunstel.  Ethology as an Inspiration for Adaptive Behavior Synthesis in Autonomous Planetary Rovers , 2001, Auton. Robots.

[8]  Stefan Schaal,et al.  Navigation and Cognitive Map Formation Using Aperiodic Neurodynamics , 2004 .

[9]  Péter Érdi,et al.  Learning environmental clues in the KIV model of the cortico-hippocampal formation , 2004, Neurocomputing.

[10]  Homayoun Seraji,et al.  Behavior-based robot navigation on challenging terrain: A fuzzy logic approach , 2002, IEEE Trans. Robotics Autom..

[11]  Robert Kozma,et al.  Spatial navigation model based on chaotic attractor networks , 2004, Connect. Sci..

[12]  Erann Gat,et al.  Behavior control for robotic exploration of planetary surfaces , 1994, IEEE Trans. Robotics Autom..

[13]  Péter Érdi,et al.  The KIV model - nonlinear spatio-temporal dynamics of the primordial vertebrate forebrain , 2003, Neurocomputing.

[14]  Robert Kozma,et al.  Basic principles of the KIV model and its application to the navigation problem. , 2003, Journal of integrative neuroscience.

[15]  Robert Kozma,et al.  Navigation in a challenging Martian environment using multi-sensory fusion in KIV model , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.