@inproceedings{b2d7b449c80e4d45ab87c65bc4214b39,
title = "Urban Vehicle Path Recommendation Method Based on the Improved Adversarial Inverse Reinforcement Learning",
abstract = "Adversarial inverse reinforcement learning (AIRL) algorithms have been used to learn path selection patterns from GPS trajectories. However, their performance can be limited in traffic environments with complex road networks and sparse data. This paper proposes a path recommendation model based on improved adversarial inverse reinforcement learning. By integrating an attention mechanism into the AIRL framework, the model enhances learning efficiency and adaptability. The learned model outputs are utilized as path costs for the Dijkstra algorithm to determine optimal routes. Experimental evaluations on a real-world taxi GPS dataset from Wuhan demonstrate that the proposed model effectively balances path preference learning and travel cost optimization, offering a more intelligent and efficient solution for path recommendation systems.",
keywords = "- Adversarial inverse reinforcement learning, Attention mechanism, Dijkstra, Experiential route, Recommendation system",
author = "Na Yang and Chuqing Wang and Jianfeng Wang and Koji Mizuno and Miao Chen and Zhihao Huo",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 16th International Conference on Green Intelligent Transportation System and Safety, GITSS 2025 ; Conference date: 09-05-2025 Through 11-05-2025",
year = "2026",
doi = "10.1007/978-981-95-8988-3\_23",
language = "英语",
isbn = "9789819589876",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "290--299",
editor = "Wuhong Wang and Hanyang Zhuang and Yeqiang Qian and Weiwei Guo and Yihao Si and Min Li",
booktitle = "Safety of Intelligent Connected Electric Vehicles",
address = "德国",
}