uFA-FastSLAM: The New Hybrid of Firefly Algorithm and FastSLAM Algorithm

Joint Conference on Green Engineering Technology & Applied Computing 2019

工业技术（总论）;计算机科学

Musridho, R.J.^1 ; Hasan, H.^1^2 ; Haron, H.^1^2

Department of Computer Science, School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, Johor, Johor Bahru, Malaysia^1

Applied Industrial Analytics Research Group, Johor, Johor Bahru, Malaysia^2

关键词: Autonomous Mobile Robot;    Fast-SLAM;    Firefly algorithms;    Light intensity;    Ranking process;    Simultaneous localization and mapping;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/551/1/012053/pdf
DOI  :  10.1088/1757-899X/551/1/012053

来源: IOP

【 摘 要 】

Simultaneous Localization and Mapping (SLAM) is a challenging and fundamental issue in autonomous mobile robots. One of two main solutions of SLAM problem is FastSLAM. In terms of accuracy, FastSLAM is known to degenerate over time. This work hybridized Firefly Algorithm (FA) and FastSLAM to optimize FastSLAM. But in FA, there is a ranking process which ranked the fireflies based on their light intensity. It caused the output needed by particles in FastSLAM came in different sequence. Thus, the FA in this work is modified before it is applied to FastSLAM, the ranking process is deleted. The result has shown that the modified FA, that is unranked Firefly Algorithm (uFA) has been successfully hybridized with FastSLAM.