A Stable Approach for Modular Learning and its Application to Autonomous Aero-Robot
Mai Bando, and Hiroaki Nakanishi
Department of Aeronautics and Astronautics, Graduate School of Engineering, Kyoto University, Yoshidahonmachi, Sakyo-ku, Kyoto 606-8501, Japan
A control system for an autonomous robot, which consists of several cooperative modules whose combination and structures change dynamically through interaction with environment, is discussed in this paper. We propose a method to design a control system by modular learning based on Lyapunov design method. In our method, modules that have different property and the dynamic relations between modules to achieve the task are learned. Numerical simulations and flight experiment of an autonomous aero-robot demonstrate the effectiveness of the proposed method.
-  R. Brooks, “Intelligence without representation,” Artificial Intelligence, Vol.47, pp. 139-159, 1991.
-  D. Wolpert, and M. Kawato, “Multiple paired forward and inverse models for motor control,” Neural Networks, Vol.11, pp. 1317-1329, 1998.
-  J. Tani, and M. Ito, “Self-Organization of Behavioral Primitives as Multiple Attractor Dynamics: A Robot Experiment,” IEEE Trans. Systems, Man, and Cybernetics PART A: Sytems And Humans, Vol.33, No.4, pp. 481-488, 2003.
-  R. Sutton, and A. Barto, “Reinforcemet Learning,” Cambridge, MA, USA: MIT Press, 1998.
-  K. Doya, K. Samejima, K. Katagiri, and M. Kawato, “Multiple model-based reinforcement learning,” Neural Computation, Vol.14, pp. 1347-1369, 2002.
-  B. Kim, and A. Calise, “Nonlinear Flight Control Using Neural Networks,” Journal of Guidance, Control, and Dynamics, Vol.20, No.1, pp. 26-33, 1997.
-  M. Krstic, I. Kanellakopoulos, and P. Kokotovic, “Nonlinear and Adaptive Control Design,”Wiley-Interscience, 1995.
-  T. Perkins, and A. Barto, “Lyapunov Design for Safe Reinforcement Learning,” Journal of Machine Learning Research, Vol.3, pp. 803-832, 2002.
-  R. Kalman, and J. Bertram, “Control system analysis and design via second method of Lyapunov I: Continuous-time systems,” Transactions of the ASME: Journal of Basic Engineering, pp. 371-393, June, 1960.
-  H. Nakanishi, H. Hashimoto, N. Hosokawa, K. Inoue, and A. Sato, “Autonomous Flight Control System for Intelligent Aero-Robot for Disaster Prevention,” Journal of Robotics and Mechatronics, Vol.15, No.5, pp. 489-497, 2003.
-  M. Bando, H. Nakanishi, and K. Inoue, “A Study on Designing Control System by Modular Learning,” SICE Annual conference 2004, pp. 1071-1074, 2004.
Copyright© 2006 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.