A Stable Approach for Modular Learning and its Application to Autonomous Aero-Robot

Mai B; o; Hiroaki Nakanishi

doi:10.20965/jrm.2006.p0044

single-rb.php

« previous

JRM Vol.18 No.1 pp. 44-50

doi: 10.20965/jrm.2006.p0044

(2006)

Paper:

Views over last 60 days: 333

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

Received:

May 10, 2005

Accepted:

September 26, 2005

Published:

February 20, 2006

Keywords:

modular learning, reinforcement learning, designing control system, autonomous robot

Abstract

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.

Cite this article as:

M. Bando and H. Nakanishi, “A Stable Approach for Modular Learning and its Application to Autonomous Aero-Robot,” J. Robot. Mechatron., Vol.18 No.1, pp. 44-50, 2006.

Data files:

References

[1] R. Brooks, “Intelligence without representation,” Artificial Intelligence, Vol.47, pp. 139-159, 1991.
[2] D. Wolpert, and M. Kawato, “Multiple paired forward and inverse models for motor control,” Neural Networks, Vol.11, pp. 1317-1329, 1998.
[3] 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.
[4] R. Sutton, and A. Barto, “Reinforcemet Learning,” Cambridge, MA, USA: MIT Press, 1998.
[5] K. Doya, K. Samejima, K. Katagiri, and M. Kawato, “Multiple model-based reinforcement learning,” Neural Computation, Vol.14, pp. 1347-1369, 2002.
[6] 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.
[7] M. Krstic, I. Kanellakopoulos, and P. Kokotovic, “Nonlinear and Adaptive Control Design,”Wiley-Interscience, 1995.
[8] T. Perkins, and A. Barto, “Lyapunov Design for Safe Reinforcement Learning,” Journal of Machine Learning Research, Vol.3, pp. 803-832, 2002.
[9] 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.
[10] 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.
[11] M. Bando, H. Nakanishi, and K. Inoue, “A Study on Designing Control System by Modular Learning,” SICE Annual conference 2004, pp. 1071-1074, 2004.

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

[1] [1] R. Brooks, “Intelligence without representation,” Artificial Intelligence, Vol.47, pp. 139-159, 1991.

[2] [2] D. Wolpert, and M. Kawato, “Multiple paired forward and inverse models for motor control,” Neural Networks, Vol.11, pp. 1317-1329, 1998.

[3] [3] 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.

[4] [4] R. Sutton, and A. Barto, “Reinforcemet Learning,” Cambridge, MA, USA: MIT Press, 1998.

[5] [5] K. Doya, K. Samejima, K. Katagiri, and M. Kawato, “Multiple model-based reinforcement learning,” Neural Computation, Vol.14, pp. 1347-1369, 2002.

[6] [6] 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.

[7] [7] M. Krstic, I. Kanellakopoulos, and P. Kokotovic, “Nonlinear and Adaptive Control Design,”Wiley-Interscience, 1995.

[8] [8] T. Perkins, and A. Barto, “Lyapunov Design for Safe Reinforcement Learning,” Journal of Machine Learning Research, Vol.3, pp. 803-832, 2002.

[9] [9] 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.

[10] [10] 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.

[11] [11] M. Bando, H. Nakanishi, and K. Inoue, “A Study on Designing Control System by Modular Learning,” SICE Annual conference 2004, pp. 1071-1074, 2004.