Neural Network Approaches for Behavioral Control of Autonomous Systems

Abstract An architecture for the execution of mobile robot tasks which are composed of several primitive behavioll in a simultaneous or concurrent fashion has been developed by the authors. Two methods for implementing the fusion supervisor of the architecture based on a heuristic rule-based system and a Backpropagation Neural Network have been developed. Although the methods work well on many environments, they exhibit problems with more complex environments. A distributed neural network approach suggested to overcome the problems experienced with the previous two methods. The system is designed so that it exhibits the advantages of both controllers and minimize their drawbaw. The implementation has been tested with OPMOR, a simulation environment for mobile robots and several results are presented. Portions of this work has been performed under the EEC ESPRIT 2483 PANORAMA Project

[1]  Ben J. A. Kröse,et al.  Neural Networks for Collision Avoidance between Autonomous Mobile Robots , 1989, IAS.

[2]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[3]  E. A. Puente,et al.  OPMOR: optimization of motion control algorithms for mobile robots , 1992, Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation.

[4]  Ronald C. Arkin,et al.  Motor Schema — Based Mobile Robot Navigation , 1989, Int. J. Robotics Res..

[5]  D. Gachet,et al.  A software architecture for behavioral control strategies of autonomous systems , 1992, Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation.

[6]  Tracy L. Anderson,et al.  Animal behavior as a paradigm for developing robot autonomy , 1990, Robotics Auton. Syst..

[7]  Leslie Pack Kaelbling,et al.  Action and planning in embedded agents , 1990, Robotics Auton. Syst..

[8]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[9]  Rodney A. Brooks,et al.  Learning to Coordinate Behaviors , 1990, AAAI.

[10]  Russell J. Clark,et al.  Learning momentum: online performance enhancement for reactive systems , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[11]  Luis Moreno,et al.  A neural network supervisor for behavioral primitives of autonomous systems , 1992, Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation.

[12]  J. F. Shepanski,et al.  Teaching Artificial Neural Systems To Drive: Manual Training Techniques For Autonomous Systems , 1988, Other Conferences.