Genetic Algorithms Applied to the Searching of the Optimal Path in Image-based Robotic Navigation Environments

This paper describes an optimal-path finding strategy 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.