ACMICS: an agent communication model for interacting crowd simulation

Behavioral plausibility is one of the major aims of crowd simulation research. We present a novel approach that simulates communication between the agents and assess its influence on overall crowd behavior. Our formulation uses a communication model that tends to simulate human-like communication capability. The underlying formulation is based on a message structure that corresponds to a simplified version of Foundation for Intelligent Physical Agents Agent Communication Language Message Structure Specification. Our algorithm distinguishes between low- and high-level communication tasks so that ACMICS can be easily extended and employed in new simulation scenarios. We highlight the performance of our communication model on different crowd simulation scenarios. We also extend our approach to model evacuation behavior in unknown environments. Overall, our communication model has a small runtime overhead and can be used for interactive simulation with tens or hundreds of agents.     

Parameter estimation and comparative evaluation of crowd simulations

We present a novel framework to evaluate multi‐agent crowd simulation algorithms based on real‐world observations of crowd movements. A key aspect of our approach is to enable fair comparisons by automatically estimating the parameters that enable the simulation algorithms to best fit the given data. We formulate parameter estimation as an optimization problem, and propose a general framework to solve the combinatorial optimization problem for all parameterized crowd simulation algorithms. Our framework supports a variety of metrics to compare reference data and simulation outputs. The reference data may correspond to recorded trajectories, macroscopic parameters, or artist‐driven sketches. We demonstrate the benefits of our framework for example‐based simulation, modeling of cultural variations, artist‐driven crowd animation, and relative comparison of some widely‐used multi‐agent simulation algorithms.     

Modeling group structures in pedestrian crowd simulation

Grouping is a common phenomenon in pedestrian crowds and plays important roles in affecting crowd behavior. Group modeling is still an open challenging problem and has not been incorporated by existing crowd simulation models. Motivated by the need of group modeling for crowd behavior simulation, this paper presents a unified and well-defined framework for modeling the structure aspect of different groups in pedestrian crowds. Both intra-group structure and inter-group relationships are considered and their effects on the crowd behavior are modeled. Based on this framework, an agent-based crowd simulation system is developed and crowd behavior simulations using two different group structures are presented. The simulation results show that the developed framework allows different group structures to be easily modeled. Besides, different group sizes, intra-group structures and inter-group relationships can have significant impacts on crowd behaviors.     

Crowd simulation for emergency response using BDI agents based on immersive virtual reality

This paper presents a novel methodology involving a Virtual Reality (VR)-based Belief, Desire, and Intention (BDI) software agent to construct crowd simulation and demonstrates the use of the same for crowd evacuation management under terrorist bomb attacks in public areas. The proposed BDI agent framework allows modeling of human behavior with a high degree of fidelity. The realistic attributes that govern the BDI characteristics of the agent are reverse-engineered by conducting human-in-the-loop experiments in the VR-based Cave Automatic Virtual Environment (CAVE). To enhance generality and interoperability of the proposed crowd simulation modeling scheme, input data models have been developed to define environment attributes (e.g., maps, demographics, evacuation management parameters). The validity of the proposed data models are tested with two different evacuation scenarios. Finally, experiments are conducted to demonstrate the effect of various crowd evacuation management parameters on the key performance indicators in the evacuation scenario such as crowd evacuation rate and densities. The results reveal that constructed simulation can be used as an effective emergency management tool.     

建筑物火灾中的人群疏散研究

建筑物火灾是我国频发的安全事故,所以应研究建筑物火灾人群安全疏散问题。由于在建筑物火灾中,人群疏散时出现拥堵,存在不安全因素,造成人员伤亡。针对在现有的研究中未考虑人员行为的影响,提出了智能体(Agent)的人群行为建模技术在建筑物火灾中的人群疏散仿真中的应用方法。仿真结果显示基于Agent的行为模型可以仿真出人员特性及决策过程对人群疏散的影响,弥补现有的人群疏散模型的不足。仿真结果证明,Agent的行为建模技术具有仿真火灾全过程中人员疏散行为的功能,适用于建筑物火灾中的人群优化疏散策略。     

融入情绪模型的人群实时路径规划

目的 人群仿真中高效性和逼真性是群体路径规划的关键问题。已有人群路径规划算法忽略了人群情绪造成的路径选择差异,在大规模实时仿真中仍存在一定的局限性。方法 提出一种融入情绪模型的人群实时路径规划算法(EPP)。使用人格特征理论对人群的情绪进行建模并设定不同情绪所具有的路径选择偏好。在路径建模阶段,通过单次搜索建立全局有向导航图,确定全局层面的可行路径;在路径搜索阶段,提出以期望时间最短为原则的路径规划目标函数,采用局部搜索策略为个体实时规划一条最优或次优的路径。结果 EPP算法可有效地仿真不同场景下大规模人群的路径选择现象;与已有工作的仿真效果和量化指标对比说明了该算法的有效性和高效性;通过不同情绪状态下人群路径选择差异的讨论以及在不同人群运动模型的兼容性实验进一步说明了该算法的健壮性。结论 本文算法具有良好的高效性和健壮性,适用于不同场景下大规模人群路径规划的相关应用。     

基于多尺度时间递归神经网络的人群异常检测

如何在人群密度大、变化快、存在大量遮挡的密集场景中实现可靠的人群事件检测,是领域研究的难点和热点.在密集场景时空建模的基础上提出了一种基于多尺度时间递归神经网络的人群异常事件检测和定位方法.首先对人群场景进行网格化划分,并利用多尺度光流直方图对每个网格的人群动态进行刻画;然后,连接各个局部的人群动态获得整体的人群动态,实现整体人群动态的时间序列建模;最后,利用多尺度时间递归神经网络实现异常事件的检测和定位.其中,多尺度隐含层实现了密集场景中不同规模相邻网格之间的空间联系,节点间的反馈关系则为时间维度上的关系表达提供了有效方案.与多种代表性算法的对比实验,验证了本方法的有效性.     

Logic-based modeling of information transfer in cyber–physical multi-agent systems

In modeling multi-agent systems, the structure of their communication is typically one of the most important aspects, especially for systems that strive toward self-organization or collaborative adaptation. Traditionally, such structures have often been described using logic-based approaches as they provide a formal foundation for many verification methods. However, these formalisms are typically not well suited to reflect the stochastic nature of communication in the cyber–physical setting. In particular, their level of abstraction is either too high to provide sufficient accuracy or too low to be practicable in more complex models. Therefore, we propose an extension of the logic-based modeling language SALMA, which we have introduced recently, that provides adequate high-level constructs for communication and data propagation, explicitly taking into account stochastic delays and errors. In combination with SALMA’s tool support for simulation and statistical model checking, this creates a pragmatic approach for verification and validation of cyber–physical multi-agent systems.     

基于熵度量的人群模型评估方法

人群模型评估是虚拟人群仿真研究的关键问题,现有的研究多通过个体仿真轨迹与真实轨迹之间的误差来评估人群模型.然而人群行为本质上是复杂的随机系统,简单的轨迹对比并不能有效反映模型能力.本文应用熵度量的模型评估方法,通过估计真实人群状态与仿真人群状态的误差分布实现了精确的人群仿真定量评估.同时引入失真情况的判断和处理规则,使得评估方法在仿真失真情况下能够保持准确性.实验结果表明,本文提出的算法及规则能有效地实现人群仿真模型的定量评估并给出模型参数选择的指导.     

Spice: a cognitive agent framework for computational crowd simulations in complex environments

Pedestrian behavior is an omnipresent topic, but the underlying cognitive processes and the various influences on movement behavior are still not fully understood. Nonetheless, computational simulations that predict crowd behavior are essential for safety, economics, and transport. Contemporary approaches of pedestrian behavior modeling focus strongly on the movement aspects and seldom address the rich body of research from cognitive science. Similarly, general purpose cognitive architectures are not suitable for agents that can move in spatial domains because they do not consider the profound findings of pedestrian dynamics research. Thus, multi-agent simulations of crowd behavior that strongly incorporate both research domains have not yet been fully realized. Here, we propose the cognitive agent framework Spice. The framework provides an approach to structure pedestrian agent models by integrating concepts of pedestrian dynamics and cognition. Further, we provide a model that implements the framework. The model solves spatial sequential choice problems in sufficient detail, including movement and cognition aspects. We apply the model in a computer simulation and validate the Spice approach by means of data from an uncontrolled field study. The Spice framework is an important starting point for further research, as we believe that fostering interdisciplinary modeling approaches will be highly beneficial to the field of pedestrian dynamics.     

Simulating watersheds using loosely integrated model components: Evaluation of computational scaling using OpenMI

Complicated research and management questions regarding watershed systems often require the use of more than one simulation model. Therefore, it is necessary to develop a means to integrate multiple simulation models to predict holistic system response. In this paper we explore the use of a component-based approach for the runtime integration of models, implemented as “plug-and-play” software components. The motivation for this work is to quantify performance overhead costs introduced by adopting a component-based paradigm for loosely integrating hydrologic simulation models. We construct a standard rainfall/runoff watershed model using the Open Modeling Interface (OpenMI) Software Development Kit (SDK) where infiltration, surface runoff, and channel routing processes are each implemented as independent model components. We then analyze the performance of this loosely integrated model to quantify computational scaling, using the Hydrologic Engineering Center’s Hydrologic Modeling System (HMS) for comparison. Our results suggest that the overhead introduced by runtime communication of data is not significant when applied for semi-distributed watershed modeling. Our analysis was limited to semi-distributed watershed modeling, however, and future research is needed to understand performance and accuracy for more data demanding hydrologic models.     

基于Agent的Repast仿真分析与实现

基于复杂适应系统(CAS)理论在计算机上建立模型是研究社会复杂系统的一个基本方法.选择一个合适的基于A-gent的建模与仿真平台能降低社会科学工作者的研究难度.Repast是目前使用较多的基于Agent的建模与仿真平台之一,主要应用于社会科学仿真领域.简要介绍了Repast平台的背景,从建模与仿真的两个角度分析了Repast仿真的特点,并介绍了Repast的主要类库.从仿真实现的基本步骤,Repast内含的时间表机制和显示机制,仿真程序框架几方面探讨了Repast仿真模型的设计与实现流程.从CarryDrop模型的实现结果,能看出基于Repast平台能较方便地实现基于Agent的仿真.最后指出Repast平台突出的特点是能充分利用.Net和Java类库的众多功能.     

A Data‐Driven Framework for Visual Crowd Analysis

We present a novel approach for analyzing the quality of multi‐agent crowd simulation algorithms. Our approach is data‐driven, taking as input a set of user‐defined metrics and reference training data, either synthetic or from video footage of real crowds. Given a simulation, we formulate the crowd analysis problem as an anomaly detection problem and exploit state‐of‐the‐art outlier detection algorithms to address it. To that end, we introduce a new framework for the visual analysis of crowd simulations. Our framework allows us to capture potentially erroneous behaviors on a per‐agent basis either by automatically detecting outliers based on individual evaluation metrics or by accounting for multiple evaluation criteria in a principled fashion using Principle Component Analysis and the notion of Pareto Optimality. We discuss optimizations necessary to allow real‐time performance on large datasets and demonstrate the applicability of our framework through the analysis of simulations created by several widely‐used methods, including a simulation from a commercial game.     

基于地面场粒子群优化算法的高密度人群应急疏散建模

针对非常规突发事件环境下高密度人群的拥挤管理和快速疏散问题,提出一种由感知层、传输层、计算层和应用层构成的多层结构人群疏散信息物理系统（E-CPS）体系框架。在E-CPS体系框架计算层中将静态地面场（FF）建模规则引入经典粒子群优化（PSO）模型,提出地面场PSO （FF-PSO）人群疏散模型,该模型同时具备静态场规则简单、计算快和PSO模型快速搜索、快速收敛的优点。此外,FF-PSO模型中构建了一种新的适应度函数,实现了疏散策略的动态选择,并通过数值仿真及实例仿真验证了FF-PSO模型在拥挤管理中的可行性和有效性。国家会展中心（上海）的实例仿真结果表明,考虑拥堵管理比仅考虑距离最短平均每分钟可多疏散66人,疏散时间节省19 min,疏散效率提升13.4%。     

面向战略决策训练的群体行为仿真建模研究

针对当前"面向战略决策训练的群体行为仿真"中存在的:多注重表现,不注重系统本原数学模型的构建等问题进行了阐述,确立了该类型仿真的要点,给出了总体结构模型.并对意识形成模型、人际关系模型和视景表现等模型的构建进行了论述.可以说,为面向战略决策训练的群体行为的仿真建模研究提供了明晰的思路与方法.     

基于递归神经网络局部建模的人群异常事件监测

针对密集人群建模困难、异常事件检测可靠性差等问题,提出了一种基于递归神经网络局部建模的人群异常事件监测与定位方法。该方法首先对人群场景进行网格划分,提取多尺度光流统计直方图特征,并按照一定规则进行特征选择,建立人群动态序列事件表示;然后采用递归神经网络对人群场景进行局部细粒度建模和预测;最后基于前后帧重构误差进行异常事件判定,实现异常事件的监测和定位。公共数据集UCSD上进行的对比实验结果验证了该方法的有效性。     

基于SHML的CPS行为建模及仿真

信息物理融合系统(cyber-physical systems,简称CPS)是深度融合了计算进程和物理进程的统一体,是集计算、通信与控制于一体的下一代智能系统,具有广阔的应用前景.CPS的行为具有混成性、随机性等特征,建模及仿真CPS的动态行为对于开发高质量的CPS系统至关重要.但是目前缺乏面向CPS的领域建模方法及建模CPS的领域建模语言,也迫切需要支持仿真CPS领域模型的仿真工具.针对以上问题,提出一种面向CPS领域的随机混成建模语言(stochastic hybrid modeling language,简称SHML)以支持建模CPS系统的行为.首先,根据CPS的领域特征定义了SHML的元模型作为其抽象语法,并定义了SHML的具体语法和操作语义;其次,基于GEMOC框架实现了SHML的可视化建模工具.此外,集成GEMOC的序列化执行引擎和Scilab的连续行为仿真引擎,实现仿真CPS的混成行为.提出了一种面向CPS领域的建模及仿真方法,设计并实现了一个集成的面向CPS行为的建模与仿真平台,为CPS的建模及仿真提供了一种有效的方法及工具支撑.     

现代战争模拟研究的新方向：社会仿真

随着世界社会经济和科技水平的不断发展,特别是现代信息技术的发展,社会因素对战争的影响越来越突出,因此,战争模拟应该把视野扩展到传统研究之外的社会领域.主要阐述社会仿真概念的基本内涵,建模仿真基本方法,然后重点介绍社会仿真研究领域的基础设施建模研究、大规模群体行为建模研究以及国内外典型的大规模社会仿真系统,最后,介绍在该领域开展的部分研究工作,并指出我国在该领域展开研究工作的重要意义.     

Urban Walkability Design Using Virtual Population Simulation

We present a system to generate a procedural environment that produces a desired crowd behaviour. Instead of altering the behavioural parameters of the crowd itself, we automatically alter the environment to yield such desired crowd behaviour. This novel inverse approach is useful both to crowd simulation in virtual environments and to urban crowd planning applications. Our approach tightly integrates and extends a space discretization crowd simulator with inverse procedural modelling. We extend crowd simulation by goal exploration (i.e. agents are initially unaware of the goal locations), variable‐appealing sign usage and several acceleration schemes. We use Markov chain Monte Carlo to quickly explore the solution space and yield interactive design. We have applied our method to a variety of virtual and real‐world locations, yielding one order of magnitude faster crowd simulation performance over related methods and several fold improvement of crowd indicators.     

基于Multi-agent的建模仿真方法研究

基于Multi-agent的建模仿真方法侧重于研究多个主体之间的相互作用,为描述和研究复杂系统提供了更加符合现实和更加有效的建模框架,是研究复杂系统的一个有效途径.简要介绍了复杂适应系统理论,阐述了该建模仿真方法的仿真平台,指出了该建模仿真方法的主要应用领域.