Patch Exploration-Based Route Planning for Autonomous Vehicles
28th IEEE International Conference on Intelligent Transportation Systems (ITSC 2025), Gold Coast, Australia, Nov 18, 2025
DOI: 10.1109/ITSC60802.2025.11423437
Summary in three lines
- PE-RRT* attaches a geometric patch to each node of a sampling-based route-planning tree.
- The patches adapt to obstacle density, guide tree expansion and simplify the path during pruning.
- Simulation across several scenarios shows more efficient search.
Abstract
Route planning is a crucial component of autonomous driving, making it essential to develop efficient planning methods tailored to different scenarios. To address the limitations of the existing RRT* methods, we propose a Patch Exploration RRT* (PE-RRT*). First, separating hyperplanes and half-spaces are utilized to construct patch for each node in the tree structure, allowing adaptation to the environmental density. Additionally, during the sampling process, the patches guide the expansion of the random tree, enabling rapid searches and efficient use of sampled points. Moreover, the patches are applied for route pruning, simplifying the route representation. Simulation results demonstrate that the proposed method achieves high search efficiency across various scenarios.
Related news
How to cite
H. Meng, J. Zhang, X. Huang, E. Javanmardi, and M. Tsukada, “Patch Exploration-Based Route Planning for Autonomous Vehicles,” in 28th IEEE International Conference on Intelligent Transportation Systems (ITSC 2025), Gold Coast, Australia, 2025, doi: 10.1109/ITSC60802.2025.11423437.
BibTeX
@inproceedings{Meng2025b,
title = {Patch Exploration-Based Route Planning for Autonomous Vehicles},
author = {Huan Meng and Jinhui Zhang and Xiaobing Huang and Ehsan Javanmardi and Manabu Tsukada},
doi = {10.1109/ITSC60802.2025.11423437},
year = {2025},
date = {2025-11-18},
urldate = {2025-11-18},
booktitle = {28th IEEE International Conference on Intelligent Transportation Systems (ITSC 2025)},
address = {Gold Coast, Australia},
abstract = {Route planning is a crucial component of autonomous driving, making it essential to develop efficient planning methods tailored to different scenarios. To address the limitations of the existing RRT* methods, we propose a Patch Exploration RRT* (PE-RRT*). First, separating hyperplanes and half-spaces are utilized to construct patch for each node in the tree structure, allowing adaptation to the environmental density. Additionally, during the sampling process, the patches guide the expansion of the random tree, enabling rapid searches and efficient use of sampled points. Moreover, the patches are applied for route pruning, simplifying the route representation. Simulation results demonstrate that the proposed method achieves high search efficiency across various scenarios.},
keywords = {ITS},
pubstate = {published},
tppubtype = {inproceedings}
}