Title :
An adaptable controller for autonomous robots operating in unexplored environments
Author :
Anderson, Gary T. ; Yang, Youlong ; Cheng, Gang
Author_Institution :
Dept. of Appl. Sci., Arkansas Univ., Little Rock, AR
Abstract :
Several oscillator-based robot controllers were tested for effectiveness in exploring a dynamic environment. The goal of the project was to have a team of three robots explore an arena with variable lighting and obstacle patterns and, as a team, absorb as much light as possible. Reinforcement learning was used to optimize the parameters of a coupled nonlinear oscillator controller for operation in an unknown environment. The performance of this controller was compared to those of a reactive-based controller, an oscillator controller with fixed parameters and an oscillator controller that used sensor-based parameter adjustments. Experiments indicated the reinforcement learning controller offered better performance than the other controllers. The drawback to using reinforcement learning is that a learning period is required for each milieu the robot operates in. If it is necessary to quickly explore an unknown area or a rapidly changing environment, then the controller with a sensor-based parameter adjustment has an advantage
Keywords :
adaptive control; control system analysis; learning (artificial intelligence); mobile robots; multi-robot systems; nonlinear control systems; adaptable controller; autonomous robots; coupled nonlinear oscillator controller; oscillator-based robot controllers; reactive-based controller; reinforcement learning; sensor-based parameter adjustments; unexplored environment operation; Control systems; Learning; Legged locomotion; Mobile robots; Motion control; Oscillators; Robot control; Robot kinematics; Robot sensing systems; Testing;
Conference_Titel :
Systems, Man and Cybernetics, 2004 IEEE International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-7803-8566-7
DOI :
10.1109/ICSMC.2004.1398382