A Novel Goal-oriented Sampling Method for Improving the Convergence Rate of Sampling-based Path Planning for Autonomous Mobile Robot Navigation

Autonomous Mobile Robots' performance relies on intelligent motion planning algorithms. In autonomous mobile robots, sampling-based path-planning algorithms are widely used. One of the efficient sampling-based path planning algorithms is the Rapidly Exploring Random Tree (RRT). However, the solution provided by RRT is suboptimal. An RRT extension known as RRT* is optimal, but it takes time to converge. To improve the RRT* slow convergence problem, a goal-oriented sampling-based RRT* algorithm known as GS-RRT* is proposed in this paper. The focus of the proposed research work is to reduce unwanted sample exploration and solve the slow convergence problem of RRT* by taking more samples in the vicinity of the goal region. The proposed research work is validated in three different environments with a map size of 384*384 and compared to the existing algorithms: RRT, Goal-directed RRT(G-RRT), RRT*, and Informed-RRT*. The proposed research work is compared with existing algorithms using four metrics: path length, time to find the solution, the number of nodes visited, and the convergence rate. The validation is done in the Gazebo Simulation and on a TurtleBot3 mobile robot using the Robotics Operating System (ROS). The numerical findings show that the proposed research work improves the convergence rate by an average of 33 % over RRT* and 27 % over Informed RRT*, and the node exploration is 26 % better than RRT* and 20% better than Informed RRT*.