This paper deals with a hierarchical control architecture of mobile robots for Cellular Robotic System (CEBOT). The CEBOT is a distributed autonomous robotic system composed of a number of robotic units called “cells.” Since the CEBOT provides variable structure, flexibility and extendibility are required in the control system for the CEBOT. To design the mobile robots for the CEBOT, we have adopted a parallel processing control system, which makes it easy to add new rules according to the change of organization of the system. This paper proposes a method to integrate multiple processes for decision making of the behavior of the mobile robots. We define two relation matrices that denote the relationship between the processes: a priority relation matrix and an interest relation matrix. These matrices are used to adjust the output of the processes and optimize the behavior of mobile robots. That is, the conflicts of inter-processes are solved by coordination between the priority relation matrix and the interest relation matrix. The definition of the priority relation matrix and the interest relation matrix make it possible to realize a learning and adaptation ability for the behavior. To obtain the most suitable priority relation matrix, especially, this paper introduces a learning method for the mobile robots. Several simulation results present the effectiveness of the proposed matrices and the proposed learning method.
[1]
Fumihito Arai,et al.
Concept of cellular robotic system (CEBOT) and basic strategies for its realization
,
1992
.
[2]
Rodney A. Brooks,et al.
A Robust Layered Control Syste For A Mobile Robot
,
2022
.
[3]
Rodney A. Brooks,et al.
Learning to Coordinate Behaviors
,
1990,
AAAI.
[4]
Toshio Fukuda,et al.
Dynamically reconfigurable robotic system
,
1988,
Proceedings. 1988 IEEE International Conference on Robotics and Automation.
[5]
Ronald C. Arkin,et al.
Integration of reactive navigation with a flexible parallel hardware architecture
,
1993,
[1993] Proceedings IEEE International Conference on Robotics and Automation.
[6]
James S. Albus,et al.
Outline for a theory of intelligence
,
1991,
IEEE Trans. Syst. Man Cybern..
[7]
Toshio Fukuda,et al.
Self-Evolutionary Robotic System -Sociobiology and Social Robotics-
,
1992,
J. Robotics Mechatronics.
[8]
Lynne E. Parker,et al.
Adaptive action selection for cooperative agent teams
,
1993
.