智慧公路数字化转型中AI大模型的创新应用

王江锋; 舒玉东; 李云飞; 罗冬宇; 齐崇楷

doi:10.16503/j.cnki.2095-9931.2025.04.008

交通运输研究 ›› 2025, Vol. 11 ›› Issue (4) : 93-103. DOI: 10.16503/j.cnki.2095-9931.2025.04.008

专刊：交通运输数字化转型

智慧公路数字化转型中AI大模型的创新应用

王江锋 ¹^,^* ,
舒玉东 ² ,
李云飞 ¹ ,
罗冬宇 ³ ,
齐崇楷 ¹

作者信息 +

Innovative Application of AI Large Language Model in Smart Highways

WANG Jiangfeng ¹ ,
SHU Yudong ² ,
LI Yunfei ¹ ,
LUO Dongyu ³ ,
QI Chongkai ¹

Author information +

文章历史 +

摘要

数字化转型背景下，公路建设正在由传统基建向数字新基建发展，AI大模型可有效推动数字新基建从感知智能向认知智能跨越，赋能智慧公路高质量发展。首先，分析公路数字化转型面临的挑战，在此基础上，对AI大模型在公路数字化转型中的应用情况、发展历程进行了梳理。然后，围绕交通流预测、交通事件检测、自动驾驶、交通状态监测等智慧公路典型应用场景，综述了AI大模型的研究进展，并给出了智慧公路典型应用场景AI大模型参考框架。最后，从技术创新、数据治理、人才培养、政策法规、产业发展等方面就AI大模型在智慧公路中的应用发展提出建议。

Abstract

Under the background of digital transformation, highway construction is evolving from traditional infrastructure to digital new infrastructure. AI (Artificial Intelligence) LLM (Large Language Model) can effectively facilitate the leap from perceptual intelligence to cognitive intelligence, empowering the high-quality development of smart highways. Firstly, based on an analysis of the challenges faced by the digital transformation of highways, this paper reviewed the application and development history of AI LLM in the digital transformation of highways. Then, focusing on typical application scenarios of smart highways such as traffic flow prediction, traffic event detection, autonomous driving, and traffic status monitoring, this paper summarized the research progress of AI LLM and provides a reference framework for AI LLM in typical application scenarios of smart highways. Finally, from the perspectives of technological innovation, data governance, talent cultivation, policies and regulations, and industrial development, etc., several reference development suggestions for the application and development of AI LLM in smart highways were provided.

导出引用

王江锋, 舒玉东, 李云飞, 等. 智慧公路数字化转型中AI大模型的创新应用[J]. 交通运输研究. 2025, 11(4): 93-103 https://doi.org/10.16503/j.cnki.2095-9931.2025.04.008

WANG Jiangfeng, SHU Yudong, LI Yunfei, et al. Innovative Application of AI Large Language Model in Smart Highways[J]. Transport Research. 2025, 11(4): 93-103 https://doi.org/10.16503/j.cnki.2095-9931.2025.04.008

中图分类号： U491.1

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析

[1]	傅志寰, 翁孟勇, 张晓璇, 等. 我国智慧公路发展战略研究[J]. 中国工程科学, 2023, 25(6):150-159.

[2]	汪林, 高剑, 郭宇奇, 等. 我国智慧公路建设现状及发展建议[J]. 交通运输研究, 2024, 10(2):43-52.

[3]	伍朝辉. 新质生产力发展视域下对智慧公路的认识与思考[J]. 交通运输研究, 2024, 10(2):20-32.

[4]	ITS America. Digital infrastructure strategy report[R/OL]. Washington, D.C.: Department of Transport, 2023.

[5]	European Commission. State of the digital decade 2025 report[R]. Brussels: European Commission, 2025. https://digital-strategy.ec.europa.eu/en/library/state-digital-decade-2025-report.

[6]	袁宇, 刘东利, 王亚洁. 新一代智能交通系统探析[J]. 中国交通信息化, 2025(4):30-33.

[7]	马静. 交通大模型与智慧公路[J]. 中国公路, 2024(24):58-61.

[8]	周臻, 顾子渊, 曲小波, 等. 城市多模式交通大模型MT-GPT:点线面的分层技术与应用场景[J]. 中国公路学报, 2024, 37(2):253-274.

[9]	WANG P, WEI X, HU F, et al. TransGPT:Multi-modal generative pre-trained transformer for transportation[C]// Proceedings of 2024 International Conference on Computational Linguistics and Natural Language Processing(CLNLP). Yinchuan, China: IEEE, 2024:96-100.

[10]	CHITTA K, PRAKASHA, GEIGER A. NEAT:neural attention fields for End-to-End Autonomous Driving[C]// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision(ICCV). Montreal,Canada: IEEE, 2021: 15773-15783.

[11]	XU J, ANVO NR, TAHA-ABDALGADIR H, et al. Highway digital twin-enabled Autonomous Maintenance Plant: A perspective[J]. Data-Centric Engineering, 2024, 5: 24. DOI: 10.1017/dce.2024.34.

[12]	刘志远, 黄凯. 公路行业人工智能技术发展路线图[R]. 北京: 中国公路学会,2025:22-23.

[13]	ZHANG D, YU Y, DONG J, et al. MM-LLMs: recent advances in MultiModal Large Language Models[C]// Proceedings of the Annual Meeting of the Association for Computational Linguistics. Bangkok, Thailand: ACL, 2024: 12401-12430.

[14]	MAHMUD D, HAJMOHAMED H, ALMENTH-ERI S, et al. Integrating LLMs with ITS: Recent advances, potentials, challenges, and future directions[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(5): 5674-5709.

[15]	GUO X, ZHANG Q, JIANG J, et al. Towards explainable traffic flow prediction with large language models[J]. Communications in Transportation Research, 2024, 4:100150. DOI: 10.1016/j.commtr.2024.100150.

[16]	XU Y, LIU M. GPT4TFP: Spatio-temporal fusion large language model for traffic flow prediction[J]. Neurocomputing, 2025, 625(2025): 129562.

[17]	LI Y, WANG C, JIA J. LLaMA-VID:An image is worth 2 tokens in large language models[C]// Proceedings of the 18th European Conference on Computer Vision. Cham, Switzerland: Springer,2024:323-340.

[18]	CHENG Z, LENG S, ZHANG H, et al. Video-LLaMA 2:Advancing spatial-temporal modeling and audio understanding in Video-LLMs[EB/OL]. (2024-01-17)[2024-06-25]. https://arxiv.org/abs/2406.07476.

[19]	邢万勇, 邓永鹏, 刘婷. 大模型在高速公路事件检测中的应用探索[J]. 中国交通信息化, 2024(6):97-100.

[20]	GRIGOREV A, SALEH K, OU Y, et al. Enhancing traffic incident management with large language models: A hybrid machine learning approach for severity classification[J]. International Journal of Intelligent Transportation Systems Research, 2025, 23(1): 259-280.

[21]	吴精乙, 景峻, 贺熠凡, 等. 基于多模态大模型的高速公路场景交通异常事件分析方法[J]. 图学学报, 2024, 45(6):1266-1276.

[22]	刘旖菲, 胡学敏, 陈国文, 等. 2021. 视觉感知的端到端自动驾驶运动规划综述[J]. 中国图象图形学报,2021, 26(1):49-66.

[23]	褚端峰, 王如康, 王竞一, 等. 端到端自动驾驶的研究进展及挑战[J]. 中国公路学报, 2024, 37(10):209-232.

[24]	陈妍妍, 田大新, 林椿眄, 等. 端到端自动驾驶系统研究综述[J]. 中国图象图形学报, 2024, 29(11):3216-3237.

[25]	HU Y, YANG J, CHEN L, et al. Planning-oriented autonomous driving[C]// Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, Canada: IEEE, 2023:17853-17862.

[26]	YIN C, MAO Y, HE Z, et al. Edge computing-enabled secure forecasting nationwide industry PM2.5 with LLM in the heterogeneous Network[J]. Electronics, 2024, 13(13):2581.DOI: 10.3390/electronics13132581.