Premium
A framework for defining and learning fuzzy behaviors for autonomous mobile robots
Author(s) -
Barberá Humberto Martínez,
Skarmeta Antonio Gómez
Publication year - 2002
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/int.1000
Subject(s) - computer science , task (project management) , robot , artificial intelligence , field (mathematics) , fuzzy logic , set (abstract data type) , mobile robot , human–computer interaction , simple (philosophy) , reinforcement learning , machine learning , programming language , engineering , philosophy , mathematics , systems engineering , epistemology , pure mathematics
In this paper we show our work on the use of fuzzy behaviors in the field of autonomous mobile robots. Weaddress here how we use learning techniques to efficiently coordinate the conflicts between the differentbehaviors that compete with each other to take control of the robot. We use fuzzy rules to perform such fusion.These rules can be set using expert knowledge, but as this can be a complex task, we show how to automaticallydefine them using genetic algorithms. We also describe the working environment, which includes a customprogramming language (named BG) based on the multi‐agent paradigm. Finally, some resultsrelated to simple goods‐delivery tasks in an unknown environment are presented. © 2002 John Wiley& Sons, Inc.