Multi Sampling-Strategy RRT Path Planning Optimization Using Genetic Algorithm

The paper presents optimization experiment performed on custom implementation of multi-sampling strategy approach for Rapidly exploring Random Tree path planning algorithm. Implementation of algorithm, of which detailed explanation and pseudocode are provided, was developed to perform with increased robustness and intended for dynamic environment navigation task. Genetic Algorithm is used to search for optimal weights for choosing sampling strategy based on mean path length from multiple executions of the algorithm. Optimization experiment is performed on multiple testing boards, results are analyzed and presented, showing strong tendency towards an unstable solution creating statistically shortest path.