Ye, Lei (Chongqing University), Chen, Yulan (Chongqing University), Han, Qingwen (Chongqing University), Zeng, Lingqiu (Chongqing University), Huang, Ziyun (Chongqing University)

A Road Hazard Feature-Based Mesoscopic Trajectory Planning Method under MEC Architecture

Scheduled for presentation during the Regular Session "S11c-Motion Planning, Trajectory Optimization, and Control for Autonomous Vehicles" (WE-LA-T11), Wednesday, November 19, 2025, 16:00−16:20, Broadbeach 1&2

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 October 19, 2025

Abstract

Mesoscopic trajectory planning is a crucial issue in the field of Intelligent Connected Vehicles. With the introduction of device-edge-cloud architecture, roadside facilities, e.g., sensors, LiDAR, and Multi-access Edge Computing (MECs), can provide global traffic information of road sections and corresponding computing resources. Therefore, particular attention directed to generating a trajectory that considers the global hazard features of a road section. In this paper, a road hazard feature-based mesoscopic trajectory planning method is proposed, while a multiple linear regression model is used to predict road hazard feature changing. Then, an improved Ant Colony Optimization (ACO) algorithm, hazard-oriented ACO (H-ACO), which incorporates road hazard features into an ant tracking strategy, is proposed for novel regional trajectory planning. A joint simulation is done based on SUMO and NS3 platforms. The simulation results confirm the effectiveness and stability of the proposed algorithm.