Conference paper
Differential evolution to enhance localization of mobile robots
Technical University of Denmark1
Engineering Design and Product Development, Department of Management Engineering, Technical University of Denmark2
Department of Management Engineering, Technical University of Denmark3
Automation and Control, Department of Electrical Engineering, Technical University of Denmark4
Department of Electrical Engineering, Technical University of Denmark5
This paper focuses on the mobile robot localization problems: pose tracking, global localization and robot kidnap. Differential Evolution (DE) applied to extend Monte Carlo Localization (MCL) was investigated to better solve localization problem by increasing localization reliability and speed. In addition, a novel mechanism for effective robot kidnap detection was proposed.
Experiments were performed using computer simulations based on the odometer data and laser range finder measurements collected in advance by a robot in real-life. Experimental results showed that integrating DE enables MCL to provide more accurate robot pose estimations in shorter time while using fewer particles.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2011 |
Pages: | 241-247 |
Proceedings: | 2011 IEEE International Conference on Fuzzy Systems |
Journal subtitle: | Fuzz-ieee |
ISBN: | 1424473152 , 1424473160 , 1424473179 , 9781424473151 , 9781424473168 and 9781424473175 |
ISSN: | 10987584 and 15445615 |
Types: | Conference paper |
DOI: | 10.1109/FUZZY.2011.6007721 |
ORCIDs: | Ravn, Ole |
Accuracy Filtering algorithms Mobile robots Monte Carlo localization Monte Carlo methods Prediction algorithms Robot sensing systems differential evolution evolutionary computation global localization laser range finder measurements mobile robot mobile robot localization enhancement mobile robots odometer data particle filter path planning pose estimation pose tracking robot kidnap detection robot pose estimations