Path Planning for Mobile Robots Based on Hybrid Sampling and Space-Optimized RRT

Abstract

To enhance the efficiency and safety of mobile robot path planning, this letter proposes a hybrid sampling and space-optimized RRT (HB-RRT) method. First, a hybrid sampling strategy combining Gaussian sampling with parallel sampling is employed to replace conventional random sampling. During the sampling process, the sampling space is dynamically optimized by adjusting the sampling region to the improve efficiency. Then, a potential field-guided expansion strategy with adaptive step size is introduced to reduce excessive exploration and limit expansion in collision-prone areas by leveraging environmental and node information. The expansion exchange strategy is refined to improve stability, and a direct connection method is adopted to rapidly generate an initial path. Furthermore, a path optimization method is designed to refine the initial path. Finally, a series of experiments are conducted to validate the proposed method against baseline and state-of-the-art algorithms. The results show that the proposed method improves planning efficiency and reduces path cost in generating smooth paths.