上海城市规划2026，Vol.187Issue(2)：8-15,8.DOI:10.11982/j.supr.20260202
新质生产力视角下多代理行为模拟赋能城市设计全路径分析
Multi-Agent Behavior Simulation Empowering Full-Path Urban Design Analysis from the Perspective of New Quality Productive Forces
摘要
Abstract
Traditional urban design,relying on static blueprints and experiential judgment,faces challenges in addressing the dynamic transformations and diverse demands of contemporary urban development.This necessitates the introduction of new quality productive forces,characterized by technology-driven approaches,data support,and efficient collaboration,to enable scientific decision-making and digitally intelligent governance.Multi-agent behavior simulation(MABS)captures the dynamic interactions between individuals and their environments and establishes a five-stage optimization framework,comprising data acquisition,interaction mechanism extraction,simulation modeling,dynamic simulation output,and design optimization.This method promotes the integration of research,practice,and education in urban design.At the research level,it reveals the dynamic coupling between space and behavior while expanding application scenarios;at the practical level,it enhances decision-making efficiency through a closed-loop process of"simulation-diagnosis-prediction-verification";and at the educational level,it establishes an evidence-based pedagogical framework integrating"experience+practice+simulation+verification".Overall,by enabling intelligent simulation,comprehensive diagnosis,and precise prediction,MABS facilitates the transformation of urban design from experience-driven to data-driven approaches and from static blueprints to dynamic simulation,providing essential methodological support for the refined and digitally intelligent governance of urban spaces.关键词
多代理行为模拟/城市设计/新质生产力/数智化治理Key words
multi-agent behavior simulation/urban design/new quality productive forces/digital-intelligent governance分类
建筑与水利引用本文复制引用
杨春侠,詹鸣..新质生产力视角下多代理行为模拟赋能城市设计全路径分析[J].上海城市规划,2026,187(2):8-15,8.基金项目
国家社会科学基金后期资助重点项目"城市滨水全民健身新载体数智构建路径研究"(编号24FGLA001)资助. （编号24FGLA001）
