Large Language Model for Participatory Urban Planning

📄 arXiv: 2402.17161v1 📥 PDF

作者: Zhilun Zhou, Yuming Lin, Depeng Jin, Yong Li

分类: cs.AI, cs.MA

发布日期: 2024-02-27

备注: arXiv admin note: text overlap with arXiv:2402.01698


💡 一句话要点

提出基于大语言模型的多代理协作框架以优化参与式城市规划

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 城市规划 参与式设计 大语言模型 多代理系统 居民反馈 鱼缸讨论 土地使用计划 可持续发展

📋 核心要点

  1. 传统参与式城市规划依赖经验丰富的专家,导致过程耗时且成本高,难以满足居民多样化的需求。
  2. 本文提出了一种基于大语言模型的多代理协作框架,通过模拟规划师和居民的互动,生成土地使用计划。
  3. 实验结果显示,该方法在居民满意度和包容性方面表现优异,并在服务可达性和生态指标上超越了人类专家。

📝 摘要(中文)

参与式城市规划是现代城市规划的主流,强调居民的积极参与。然而,传统方法依赖经验丰富的规划专家,往往耗时且成本高昂。本文提出了一种基于大语言模型(LLM)的多代理协作框架,能够模拟规划师和多样化居民的互动,生成考虑居民需求的土地使用计划。通过在北京的两个真实区域进行实验,结果表明该方法在居民满意度和包容性指标上达到了最先进的性能,并在服务可达性和生态指标上超越了人类专家。

🔬 方法详解

问题定义:本文旨在解决传统参与式城市规划中专家依赖性强、效率低下的问题,尤其是如何有效整合居民的多样化需求。

核心思路:通过构建基于大语言模型的代理系统,模拟规划师与居民之间的互动,促进居民反馈的有效整合,从而优化土地使用计划。

技术框架:整体框架包括三个主要模块:首先由规划师生成初步土地使用计划;其次在居民社区中进行讨论,居民根据个人背景提供反馈;最后,规划师根据反馈调整计划。

关键创新:本研究的创新点在于采用了鱼缸讨论机制,部分居民讨论而其他居民倾听,提高了讨论效率,突破了传统方法的局限。

关键设计:在设计中,采用了多样化的居民代理,确保反馈的多样性;同时,设置了明确的讨论流程和反馈机制,以便规划师能够高效地进行计划调整。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,所提方法在居民满意度和包容性指标上达到了最先进的性能,具体表现为在服务可达性和生态指标上超越了人类专家,提升幅度显著,验证了方法的有效性和实用性。

🎯 应用场景

该研究的潜在应用领域包括城市规划、社区发展和公共政策制定等。通过提高居民参与度和满意度,能够更好地满足社区需求,促进可持续发展,未来可能对城市治理模式产生深远影响。

📄 摘要(原文)

Participatory urban planning is the mainstream of modern urban planning that involves the active engagement of residents. However, the traditional participatory paradigm requires experienced planning experts and is often time-consuming and costly. Fortunately, the emerging Large Language Models (LLMs) have shown considerable ability to simulate human-like agents, which can be used to emulate the participatory process easily. In this work, we introduce an LLM-based multi-agent collaboration framework for participatory urban planning, which can generate land-use plans for urban regions considering the diverse needs of residents. Specifically, we construct LLM agents to simulate a planner and thousands of residents with diverse profiles and backgrounds. We first ask the planner to carry out an initial land-use plan. To deal with the different facilities needs of residents, we initiate a discussion among the residents in each community about the plan, where residents provide feedback based on their profiles. Furthermore, to improve the efficiency of discussion, we adopt a fishbowl discussion mechanism, where part of the residents discuss and the rest of them act as listeners in each round. Finally, we let the planner modify the plan based on residents' feedback. We deploy our method on two real-world regions in Beijing. Experiments show that our method achieves state-of-the-art performance in residents satisfaction and inclusion metrics, and also outperforms human experts in terms of service accessibility and ecology metrics.