arXiv 2412.033382024-12-31cs.LGcs.AI

AI驱动的日常路径选择

AI-Driven Day-to-Day Route Choice

Department of Data Science and Artificial Intelligence, Monash University（数据科学与人工智能系，莫纳什大学）；Laboratory for Information & Decision Systems, Massachusetts Institute of Technology（信息与决策系统实验室，麻省理工学院）；Chair of Transportation Systems Engineering, Technical University of Munich（交通系统工程教授职位，慕尼黑技术大学）；School of Civil Engineering, The University of Queensland（土木工程学院，昆士兰大学）；Department of Civil Engineering, Monash University（土木工程系，莫纳什大学）；School of Computer Science and Engineering, Southeast University（计算机科学与工程学院，东南大学）

Leizhen Wang, Peibo Duan, Zhengbing He, Cheng Lyu, Xin Chen, Nan Zheng, Li Yao, Zhenliang Ma

DOI：: 10.1016/j.trc.2025.105307

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出由LLM赋能的智能体LLMTraveler，通过配备记忆系统在DTD拥堵博弈中平衡数据与个性特征进行决策，实验证明其能部分复制类人路径选择并生成自然语言解释，为交通政策制定提供有效见解。

摘要：

了解出行者的路径选择有助于决策者在正常和异常情况下制定最佳的运营和规划策略。然而，现有的选择建模方法通常依赖预设假设，难以捕捉出行行为的动态和自适应特性。近期，大型语言模型（LLMs）成为一种有前景的替代方案，展现出在各个领域复制类人行为的卓越能力。尽管具有这种潜力，它们在交通环境中准确模拟人类路径选择行为的能力仍存疑。为满足这一好奇心，本文通过引入一个由LLM赋能的智能体“LLMTraveler”，探讨了LLM在路径选择建模中的潜力。该智能体以LLM为核心，配备了一个记忆系统，能够从过往经验中学习，并通过平衡检索到的数据与个性特征来做出决策。研究通过两个阶段的日常（DTD）拥堵博弈，系统地评估了LLMTraveler复制类人决策的能力：（1）在单一起讫点（OD）对场景中分析其路径切换行为，其展现出的模式与实验室数据相符，但无法由传统模型完全解释；（2）在Ortuzar and Willumsen（OW）网络的多OD场景中测试其建模自适应学习行为的能力，产生的结果可与多项逻辑回归（MNL）和强化学习（RL）模型相媲美。这些实验表明，该框架能够部分复制路径选择中的类人决策，同时为其决策提供自然语言解释。这一能力为交通政策制定提供了有价值的见解，例如模拟出行者对新政策或网络变化的响应。

英文摘要：

Understanding travelers' route choices can help policymakers devise optimal operational and planning strategies for both normal and abnormal circumstances. However, existing choice modeling methods often rely on predefined assumptions and struggle to capture the dynamic and adaptive nature of travel behavior. Recently, Large Language Models (LLMs) have emerged as a promising alternative, demonstrating remarkable ability to replicate human-like behaviors across various fields. Despite this potential, their capacity to accurately simulate human route choice behavior in transportation contexts remains doubtful. To satisfy this curiosity, this paper investigates the potential of LLMs for route choice modeling by introducing an LLM-empowered agent, "LLMTraveler." This agent integrates an LLM as its core, equipped with a memory system that learns from past experiences and makes decisions by balancing retrieved data and personality traits. The study systematically evaluates the LLMTraveler's ability to replicate human-like decision-making through two stages of day-to-day (DTD) congestion games: (1) analyzing its route-switching behavior in single origin-destination (OD) pair scenarios, where it demonstrates patterns that align with laboratory data but cannot be fully explained by traditional models, and (2) testing its capacity to model adaptive learning behaviors in multi-OD scenarios on the Ortuzar and Willumsen (OW) network, producing results comparable to Multinomial Logit (MNL) and Reinforcement Learning (RL) models. These experiments demonstrate that the framework can partially replicate human-like decision-making in route choice while providing natural language explanations for its decisions. This capability offers valuable insights for transportation policymaking, such as simulating traveler responses to new policies or changes in the network.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。