Learning to coordinate behaviors for real-time path planning of autonomous systems

We present a neural network (NN) system which learns the appropriate simultaneous activation of primitive behaviors in order to execute more complex robot behaviors. The NN implementation is part of an architecture for the execution of mobile robot tasks which are composed of several primitive behaviors in a simultaneous or concurrent fashion. We use a supervised learning technique with a human trainer generating appropriate training for the simultaneous activation of behavior in a simulated environment. The NN implementation has been tested within OPMOR, a simulation environment for mobile robots and several results are presented. The performance of the neural network is adequate. Portions of this work has been implemented in the EEC ESPRIT 2483 PANORAMA Project.<<ETX>>

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

[2]  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.

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

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

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

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

[7]  Luis Moreno,et al.  Trajectory tracking for a mobile robot-An application to contour following , 1991, Proceedings IECON '91: 1991 International Conference on Industrial Electronics, Control and Instrumentation.

[8]  Ronald C. Arkin,et al.  The Learning Of Reactive Control Parameters Through Genetic Algorithms , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

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