Optimal path planning in cluttered environment using RRT*-AB

Rapidly exploring Random Tree Star (RRT*) has gained popularity due to its support for complex and high-dimensional problems. Its numerous applications in path planning have made it an active area of research. Although it ensures probabilistic completeness and asymptotic optimality, its slow convergence rate and large dense sampling space are proven problems. In this paper, an off-line planning algorithm based on RRT* named RRT*-adjustable bounds (RRT*-AB) is proposed to resolve these issues. The proposed approach rapidly targets the goal region with improved computational efficiency. Desired objectives are achieved through three novel strategies, i.e., connectivity region, goal-biased bounded sampling, and path optimization. Goal-biased bounded sampling is performed within boundary of connectivity region to find the initial path. Connectivity region is flexible enough to grow for complex environment. Once path is found, it is optimized gradually using node rejection and concentrated bounded sampling. Final path is further improved using global pruning to erode extra nodes. Robustness and efficiency of proposed algorithm is tested through experiments in different structured and unstructured environments cluttered with obstacles including narrow and complex maze cases. The proposed approach converges to shorter path with reduced time and memory requirements than conventional RRT* methods.