.png){kind=icon}
.png){kind=icon}
Return
Reverse Search Heuristic Sampling-Based Path Planning Algorithm With Path Smoothing for Autonomous Vehicles
.png){kind=icon}
PRE
AI
DOI：10.1109/tase.2026.3719664.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Path planning is a critical component of autonomous driving, particularly in complex unstructured environments characterized by the absence of clearly defined drivable corridors and the presence of irregular obstacles. A widely adopted two-stage framework under such conditions involves generating an initial path followed by its optimization. In this paper, a bi-directional rapidly-exploring random tree (RRT) based path planning algorithm, namely reverse search heuristic RRT* (RH-RRT*), is proposed to generate an initial path composed of Reeds-Shepp (RS) curves. Unlike traditional bi-directional tree-based path planning algorithms that directly connect two trees, RH-RRT* employs a reverse search tree as heuristic information. This design achieves a faster convergence speed. The RS curves inherently suffer from curvature discontinuities, posing challenges for vehicle tracking control. Therefore, a fast optimization-based smoothing algorithm is applied to the initial path to ensure kinematic feasibility and smoothness. Extensive simulations and real-world experiments demonstrate that the proposed algorithms outperform existing methods in terms of planning efficiency, path smoothness and tracking performance. We will release our codes for the research community at https://github.com/zzb-zzb-zzb/RH-RRTstar.git Note to Practitioners—The motivation of this work is to develop a two-stage path planning algorithm for autonomous vehicles in unstructured environments. The first stage of the algorithm is RH-RRT*, which is specially designed for the asymptotically optimal sampling-based planning problem that uses RS curves to connect two motion states. The second stage of the algorithm is an optimization-based path smoothing problem designed to eliminate the curvature discontinuities in RS curves. Sampling-based methods excel in exploratory capability for complex unstructured scenarios, while optimization-based methods offer precise path refinement to satisfy strict kinematic constraints. Leveraging the advantages of both sampling and optimization, the overall algorithm generates smooth and kinematically feasible paths.
Keywords:
Path planning
rapidly-exploring random tree
path smoothing
autonomous vehicles
Journal
IF:
6.4
Papers:
4.9K
Citations:
1.6W