HiLo-Align: A Hierarchical Semantic Alignment Framework for Driving Decision Generation via Virtual-Physical Integration
Loading...
Date
2025
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Autonomous vehicles operating in uncertain urban environments are required to reason over complex multi-agent interactions while adhering to stringent safety requirements. Hierarchical frameworks often use large models for high-level (virtual-layer) planning and deep reinforcement learning for low-level (physical-layer) control. However, semantic and temporal misalignment between layers leads to command errors and delayed response. We propose HiLo-Align, a hybrid hierarchical framework that unifies both layers via a shared semantic space and time scale. By explicitly modeling cross-layer alignment, HiLo-Align improves control coordination and semantic consistency. Experimental results on both simulation and real-world datasets indicate enhanced collision avoidance, generalization, and robustness in high-risk urban environments.
Description
CCS Concepts: Computing methodologies → Machine learning; Reinforcement learning; Semantic networks; Applied computing → Transportation
@inproceedings{10.2312:pg.20251263,
booktitle = {Pacific Graphics Conference Papers, Posters, and Demos},
editor = {Christie, Marc and Han, Ping-Hsuan and Lin, Shih-Syun and Pietroni, Nico and Schneider, Teseo and Tsai, Hsin-Ruey and Wang, Yu-Shuen and Zhang, Eugene},
title = {{HiLo-Align: A Hierarchical Semantic Alignment Framework for Driving Decision Generation via Virtual-Physical Integration}},
author = {Duan, Zehao and Huang, Chengyan and Wang, Lin},
year = {2025},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {10.2312/pg.20251263}
}