A Path Planning Framework Based on an Improved Weighted Heuristic RRT and Optimization Strategy

This article investigates a local obstacle avoidance (LOA) problem in terms of the planning efficiency and driving safety of low-speed driving unmanned vehicles. A novel improved weighted heuristic RRT (IWH-RRT) method and an opti-mization strategy are proposed to address the LOA problem with constraints. The sampling space optimization (SPO) and vehicle non-integrity constraint detection (NICD) are first adopted to improve sampling efficiency and guide RRT tree to expand nodes that satisfy driveability towards the target point. Then a cost function combining node attribute and expanding is designed, and the parent node is reselected for the newly expanded ones to reduce the deviation from the reference line and meet the LOA requirements. Finally, the convex space is approximated according to a driving corridor generated based on the initial path, in which the optimized path is obtained by solving an optimal control problem through QP solver. The proposed framework is compared with the baselines and state-of-the-art algorithms in simulation, and real-world experiments are designed afterward. The results verify that our method has good engineering feasibility and real-time capacity in generating smooth, safe and road-shape-liked paths for LOA problems.