期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2022
卷号：13
期号：5
DOI：10.14569/IJACSA.2022.0130592
语种：English
出版社：Science and Information Society (SAI)
摘要：This paper describes an optimal-path finding strat-egy based on Genetic Algorithms, applied to mobile robots in static navigation environments. This strategy starts from an image or plan of the environment and is supported by some different image processing algorithms, mainly the image skeletonization. Three different strategies were tested, changing the domain of the optimization target function for the Genetic Algorithm, the first domain was all the points of the environment image less the obstacles or walls, the second domain was similar but using an image with the obstacles dilated, and the final domain was only the points of the skeleton image. The last tested domain is from 99.4% to 99.6% smaller than the others, that implied reductions from 95% to 96% in the overall execution time of the strategy. Likewise, three skeletonization algorithms were tested in order to use the one with less execution time in this proposal. Finally, the proposed path planning strategy was tested on the same environment changing the initial and final points giving as result a valid and optimized path for the mobile robot in all the tested cases, and an overall average optimization time less than 2 minutes. This last, validates this proposal for robotic navigation applications with static obstacles.
