A provable spatiotemporal risk reasoning framework for long-tail traffic scenarios in autonomous driving
Authors:
- Qingchao LiuQingchao Liu
- Laiyu ZhangLZLaiyu Zhang
- Yingfeng CaiYCYingfeng Cai
- Hai WangHWHai Wang
- Quan YuanQYQuan Yuan
- Jianqiang WangJWJianqiang Wang
- Long ChenLCLong Chen
- 23 June 2026
- journal article
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 76
Abstract
No abstract availableFunding Information
- National Key Research and Development Program of China (2023YFB2504400)
- Jiangsu University
- National Natural Science Foundation of China (52372413)
- National Natural Science Foundation of China (52225212)
- Natural Science Foundation of Beijing Municipality (L247007)
This publication has 27 references indexed in Scilit:
- Collision risk prediction and takeover requirements assessment based on radar-video integrated sensors data: A system framework based on LLMAccident Analysis & Prevention, 2025
- A traffic dynamic operation risk assessment method using driving behaviors and traffic flow Data: An empirical analysisExpert Systems with Applications, 2024
- Integrating visual large language model and reasoning chain for driver behavior analysis and risk assessmentAccident Analysis & Prevention, 2024
- Fusion and Innovation2024
- Multisource information fusion-based environment perception and dynamic model of underwater vehicle in irregular ocean environmentInformation Fusion, 2023
- Real-time driving risk assessment using deep learning with XGBoostAccident Analysis & Prevention, 2022
- Transfer learning-based highway crash risk evaluation considering manifold characteristics of traffic flowAccident Analysis & Prevention, 2022
- Analyzing driver behavior under naturalistic driving conditions: A reviewAccident Analysis & Prevention, 2021
- Cognitive, sensory and physical factors enabling driving safety in older adultsClinical Psychology Review, 2005
- A framework for multi-source data fusionInformation Sciences, 2004