RSP-UV: real-time sampling-based path planning method for unmanned vehicles

Abstract The Rapidly-exploring Random Trees Star (RRT*) is widely used in unmanned vehicle path planning. However, it suffers from excessive sampling randomness, long search time and not capable of dynamic obstacle avoidance. This is not only fatal to safety, but also detrimental to smooth driving. We propose a real-time sampling-based path planning method for unmanned vehicles (RSP-UV) that systematically solves these problems. To address the problem of excessive sampling randomness, we formulate a partitioned sampling strategy and limit the density of sampling points. It reduces the sampling time to a certain extent. Additionally, we design a fuzzy controller to adjust the scale factor of the Dynamic Window Approach (DWA) evaluation function to optimise the local path and improve the dynamic obstacle avoidance efficiency. Fusing the improved RRT* and the improved DWA, the global path output from the improved RRT* is used as the bootstrap path for the improved DWA. Besides, the return path set rule is made to avoid the backtracking phenomenon. This improves the reliability and asymptotic optimality of the final path. Simulation experiments show that the trajectories planned by RSP-UV outperform the three compared methods, the similar method, ORRT*-DWA and MTAR. Real experiments show that the average path length of RSP-UV is reduced by 2.26%, 3.03%, and 3.33% compared to the other three methods, respectively. The average planning time of RSP-UV is reduced by 7.16%, 2.15% and 8.78% compared to the other three methods, respectively. RSP-UV not only ensures the success of path planning but also excels in real-time and adaptability. The paths formed by RSP-UV are cheaper and safer.