自动化学报2026，Vol.52Issue(3)：411-429,19.DOI:10.16383/j.aas.c250312
基于PIML的微观人群移动建模仿真与干预决策框架
Microscopic Crowd Movement Modeling,Simulation,and Intervention Decision-making Framework Based on Physics-informed Machine Learning
摘要
Abstract
Crowd movement is a critical factor influencing urban public safety and emergency management.How to achieve high-precision modeling,simulation and effective intervention is an urgent issue to be solved.To address these challenges,a physics-informed machine learning-driven framework for microscopic crowd movement modeling,simulation,and intervention decision-making is proposed.Based on the concept of parallel intelligence,the frame-work establishes a four-layer closed-loop architecture comprising data perception,fusion modeling,dynamic simula-tion,and intelligent intervention.This architecture forms a complete chain from modeling and simulation to strategy generation,execution,and feedback refinement.For crowd movement simulation and guidance decision-making problems,two novel methodologies are introduced in the framework:A physics-informed spatiotemporal graph convolutional network-based navigation potential field model and a physics-informed multi-agent deep de-terministic policy gradient algorithm.These methods effectively resolve issues prevalent in conventional methodolo-gies,namely,the insufficient model accuracy,disjointedness between simulation and intervention,and reliance on human experience for decision-making.Finally,simulation experiments conducted on real-world datasets confirm the effectiveness of the framework.关键词
微观人群移动/物理信息机器学习/导航势能场/干预决策/多智能体强化学习Key words
microscopic crowd movement/physics-informed machine learning/navigation potential field/interven-tion decision-making/multi-agent reinforcement learning引用本文复制引用
郭润康,朱正秋,艾川,叶佩军,秦龙,尹全军,王飞跃..基于PIML的微观人群移动建模仿真与干预决策框架[J].自动化学报,2026,52(3):411-429,19.基金项目
国家自然科学基金(72501291),湖南省自然科学基金(2025JJ60477)资助Supported by National Natural Science Foundation of China(72501291)and Natural Science Foundation of Hunan Province(2025JJ60477) （72501291）
