TransRAGfor parallel transportation:toward reliable and trustworthy transportation systems via retrieval-augmented generation  

作　　者：Jing YANG Xingyuan DAI Yisheng LV Levente KOVáCS Fei-Yue WANG 

机构地区：[1]Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China [2]John von Neumann Faculty of Informatics,Obuda University,Budapest H-1034,Hungary [3]Faculty of Innovation Engineering,Macao University of Science and Technology,Macao 999078,China

出　　处：《Frontiers of Information Technology & Electronic Engineering》2025年第1期20-26,共7页信息与电子工程前沿(英文版)

基　　金：supported by the Science and Technology Development Fund of Macao SAR,China(No.0093/2023/RIA2);the National Natural Science Foundation of China(No.U1811463)。

摘　　要：Parallel transportation serves as a holistic paradigm for achieving intelligent traffic management and control,focusing on addressing the complexity of human and social factors.Recently,the emergence and development of foundational models(FMs)have ushered in a new era for the realization of parallel transportation.However,the inherent issues of“hallucinations,”outdated knowledge,and the“black-box”nature of FMs render their generated decisions unreliable and untrustworthy.To address these issues,we propose a TransRAG framework for parallel transportation based on retrieval-augmented generation and chain-of-thought(CoT)prompting.TransRAG is composed of three interacting layers,storage,management,and execution,which work together to deliver personalized and diverse traffic services to users.The external knowledge from the storage layer is incorporated to augment the FM in management layers for computational experiments.

关 键 词：PROMPT services TRANSPORTATION 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]