CHEN, YINGDA (TONGJI UNIVERSITY), LI, KEPING (TONGJI UNIVERSITY), Zhu, Mingchang (Tongji University), XIAO, XUE (TONGJI UNIVERSITY), Zhang, Lun (TONGJI UNIVERSITY)

Multi-Objective Passing Decision and Trajectory Planning Method for Unstructured Road Environments Via Integrated Discrete Modeling

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on April 2, 2026

Abstract

This paper addresses driving behavior modeling and trajectory optimization on low-grade roads lacking lane markings, using a high-precision grid model with 0.2~m resolution. We propose a discrete spatiotemporal framework to characterize unstructured traffic behaviors. Based on psychological safety zone theory, we construct a free driving behavior model capturing lateral positioning preference and speed selection mechanisms. A multi-objective passing decision model integrating safety, efficiency, and coordination is established, with an improved particle swarm optimization (PSO) algorithm for efficient parameter determination. We design a modified A* path planning algorithm with vehicle kinematic constraints and multi-attribute hybrid heuristics, complemented by piecewise cubic polynomial speed planning to ensure smooth transitions. Simulation results demonstrate that our method increases safety gaps by 16.7%--53.7%, reduces travel time by 21.3%--68.4%, and decreases jerk fluctuations by 45.7% compared to existing techniques, significantly improving safety and efficiency during oncoming vehicle passing.