A Study on a Dynamically Reconfigurable Robotic System : Self-organizing Distributed Intelligence System of Learning and Reasoning for Cellular Robotics "CEBOT"

Abstract

We have studied the "cellular robotic system (CEBOT), " which consists of many kinds of units called "cells." CEBOT is required to be able to carry out many sorts of tasks under various surroundings. However, it is impossible for CEBOT to install all sorts of the task execution procedures. Then CEBOT should be able to generate task execution procedures for a new task by reconfigurating itself. In this paper, we propose a new kind of distributed intelligence system which is based on the concept of CEBOT. This proposed intelligence system has the abilities of learning, reasoning, and self-organizing. Similar to the hardware structure of CEBOT, this system consists of various kinds of intelligence units called "knowledge cells." By using the knowledge cells and the proposed algorithms, the system which can generate task procedures is realized. Some simulations are also shown for demonstrating the self-organization and self-evolution abilities of the distributed intelligence system.