Knowledge transfer between robots with identical tasks execution

Authors:
Jean J. Saade
Affiliations:
ECE Department, American University of Beirut, Beirut, Lebanon
Venue:
CIMMACS'06 Proceedings of the 5th WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics
Year:
2006

Citing 4
Cited 0

An efficient data-driven fuzzy approach to the motion planning problem of a mobile robot

Fuzzy Sets and Systems - Special issue: Fuzzy set techniques for intelligent robotic systems
Soft Computing and Tools of Intelligent Systems Design: Theory and Applications

Soft Computing and Tools of Intelligent Systems Design: Theory and Applications
A genetic-fuzzy approach for mobile robot navigation among moving obstacles

International Journal of Approximate Reasoning
Defuzzification techniques for fuzzy controllers

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper considers the transfer of knowledge expressed in the form of a collection of fuzzy or linguistic inference rules, also called knowledge or rule-base, from one robot (teacher) to another robot (student) in the case where both robots are supposed to perform the same task. Some rules are assumed taught or transferred to the student; i.e., they are known, and others are missing. The objective of this study is to have the student robot uncover the missing rules through self-experience and using the transferred rules. This objective is achieved by devising a novel method that enables the student robot to complete the knowledge-base. The completed rule-base would not necessarily turn out to be identical to the one possessed by the teacher robot. But, once it is used in the execution of the same task, it leads to satisfactory performance from a comparative perspective.