Abstract
In this paper, we propose a behavior-based path planner that can self-learn in an unknown environment. A situated learning algorithm is designed which allows the robot to learn to coordinate several concurrent behaviors and improve its performance by interacting with the environment. Behaviors are implemented using CMAC neural networks. A simulation environment is set up and some simulation experiments are carried out to rest our learning algorithm.
This is a preview of subscription content, log in via an institution to check access.
References
Brooks R A: A robust layered control system for a mobile robot.IEEE Journal on Robotics and Automation, 1986, RA-1: 14–23.
Albus J S. A new approach to manipulator control: The cerebellar model articulation controller (CMAC).Trans. ASME, J. Dynamic Syst. Meas. Contr., 1975, 97: 220–227.
Verschure P Fet al. Distributed adaptive control: The self-organization of structured behavior.Robotics and Autonomous Systems, 1992, 9: 181–196.
Mahadevan S, Connell J. Automatic programming of behavior-based robots using reinforment learning.Artificial Intelligent, 1992, 55: 311–365.
Author information
Authors and Affiliations
Additional information
Supported by the National Project of Key Fundamental Researches and National ‘863’ High-Tech. Program.
Yao Shu is a Ph.D. candidate of Dept. of Computer Science, Tsinghua University. His main interests include neural network, machine learning and robotics.
For the biography ofZhang Bo please see p.111 of this volume.
Rights and permissions
About this article
Cite this article
Yao, S., Zhang, B. Situated learning of a behavior-based mobile robot path planner. J. of Comput. Sci. & Technol. 10, 375–379 (1995). https://doi.org/10.1007/BF02943505
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02943505