Skip to main navigation Skip to search Skip to main content

Urban Vehicle Path Recommendation Method Based on the Improved Adversarial Inverse Reinforcement Learning

  • Na Yang
  • , Chuqing Wang
  • , Jianfeng Wang*
  • , Koji Mizuno
  • , Miao Chen
  • , Zhihao Huo
  • *Corresponding author for this work
  • Automotive Engineering College
  • Nagoya University
  • Weihai Guangtai Airport Equipment Co., Ltd.

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationSafety of Intelligent Connected Electric Vehicles
EditorsWuhong Wang, Hanyang Zhuang, Yeqiang Qian, Weiwei Guo, Yihao Si, Min Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages290-299
Number of pages10
ISBN (Print)9789819589876
DOIs
StatePublished - 2026
Externally publishedYes
Event16th International Conference on Green Intelligent Transportation System and Safety, GITSS 2025 - Shanghai, China
Duration: 9 May 202511 May 2025

Publication series

NameLecture Notes in Electrical Engineering
Volume1514 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference16th International Conference on Green Intelligent Transportation System and Safety, GITSS 2025
Country/TerritoryChina
CityShanghai
Period9/05/2511/05/25

Keywords

  • - Adversarial inverse reinforcement learning
  • Attention mechanism
  • Dijkstra
  • Experiential route
  • Recommendation system

Fingerprint

Dive into the research topics of 'Urban Vehicle Path Recommendation Method Based on the Improved Adversarial Inverse Reinforcement Learning'. Together they form a unique fingerprint.

Cite this