An Evolutionary Learning Approach for Robot Path Planning with Fuzzy Obstacle Detection and Avoidance in a Multi-agent Environment

Author

Cabreira, Taua M. ; Dimuro, Gracaliz P. ; de Aguiar, Marilton S.

Author_Institution

Programa de Pos-Grad. em Modelagem Computacional, Univ. Fed. do Rio Grande (FURG), Rio Grande, Brazil

fYear

2012

fDate

20-23 Oct. 2012

Firstpage

60

Lastpage

67

Abstract

This paper describes a Fuzzy-Genetic Algorithm Approach for path planning of mobile robots with obstacle detection and avoidance in static and dynamic scenarios. Through the software Net logo, used in simulations of multiagent applications, a seminal model was developed for the given problem. The model, which contains a robot and scenarios with or without obstacles, is responsible for determining the best path used by a robot to achieve the goal state in a shorter number of steps and avoiding collisions. Additionally, a performance evaluation of this model in comparison with A* algorithm is presented.

Keywords

collision avoidance; fuzzy set theory; genetic algorithms; learning (artificial intelligence); mobile robots; multi-agent systems; search problems; A* algorithm; dynamic scenario; evolutionary learning approach; fuzzy genetic algorithm; fuzzy obstacle avoidance; fuzzy obstacle detection; mobile robots; multiagent system; robot path planning; seminal model; software Netlogo; static scenario; Biological cells; Collision avoidance; Genetic algorithms; Path planning; Robots; Sociology; Statistics; Fuzzy Genetic Algorithm; Mobile Robots; Multiagent System; Obstacle Detection and Avoidance; Planning;

fLanguage

English

Publisher

ieee

Conference_Titel

Social Simulation (BWSS), 2012 Third Brazilian Workshop on

Conference_Location

Curitiba

Print_ISBN

978-1-4673-5673-2

Type

conf

DOI

10.1109/BWSS.2012.13

Filename

6462817