259
个编辑
更改
跳到导航
跳到搜索
第160行：
第160行： − − ==here== 第169行：
第167行： − + 第177行：
第175行： − 帕蒂尔斯算法最重要的区辨特征是它利用了导航场的概念来指导代理。这不同于指导字段; 指导字段是代理周围的一个区域，代理可以在其中“看到” / 检测信息。导航区域通常用于避开障碍物，特别是动态障碍物(移动的障碍物)。每个主体都有自己的指导领域。另一方面，导航场是一个向量场，它为每个代理计算最小代价路径，使每个代理到达自己的目标位置。+ 第185行：
第183行： − 只有当从环境中的每一个自由(无障碍)位置到目标位置之一的路径存在时，导航场才能正确使用。使用环境中静态对象的坐标、每个代理的目标位置和每个代理的导航字段计算导航字段。为了保证每个主体达到自己的目标，导航域必须不受局部最小值的限制，除非在特定目标处存在汇。+ 第193行：
第191行： − 计算导航字段的运行时间是 math o (m * n * log (mn)) / math，其中 m n 是网格维度(类似于 Dijkstra 的算法)。因此，该算法仅依赖于网格分辨率，而不依赖于环境中的代理数量。但是，这种算法的内存开销很大。+ + + − + 第203行：
第203行： − 基于 ai 的群体模拟技术之一是通过对个体动机和决策的高级模拟来建立群体行为模型。一般来说，这意味着每个代理都被分配了一组变量来衡量不同的特征或状态，比如压力、性格或不同的目标。这导致更现实的群体行为，虽然可能是更密集的计算比简单的技术。+ − + − + + − 为群体行动者创造个人主义行为的一种方法是通过使用人格特质。每个代理人可能会根据一个公式调整他们个性的某些方面，这个公式将侵略性或冲动性等方面与控制代理人行为的变量联系起来。发现这种联系的一个方法是通过一个主观的研究，在这个研究中代理人被随机分配这些变量的值，参与者被要求描述每个代理人的这些性格特征。然后可以进行回归，以确定这些特征和代理变量之间的相关性。然后，人格特征可以被调整，并对主体行为产生适当的影响。+ 第221行：
第222行： − 采用 OCEAN 人格模型定义了人格特质与人群模拟参数之间的映射关系。自动调整人群参数与个性特征提供了方便的场景创作与异质性的人群。+ − + 第231行：
第232行： − 高应激状态下的人群行为可以用一般适应综合征理论来模拟。主体行为受到来自其所处环境的各种压力源的影响，分为时间压力、面积压力、位置压力和人际压力四个原型，每个原型都有相关的数学模型。+ 第239行：
第240行： − 时间压力是指与达到一个特定目标的时间限制有关的压力源。例如，设有限时步行信号的十字路口或在车门关闭前登上火车。这个原型是按照以下公式建模的:+ 第247行：
第248行： − 数学 i t max (t e-t a，0) / 数学+ 第255行：
第256行： − + 第263行：
第264行： − 面积压力是指由于环境条件而产生的压力。例如某个地区的噪音或热量。这种应激源的强度在某一特定地区是恒定的，其模型如下:+ 第271行：
第272行： − 数学 i a 开始{ cases } c & text { if } p a in a 0 & text { if } p a not in a end { cases } / math+ 第279行：
第280行： − 数学显示"inline"i a / math 是面积压力的强度，数学显示"inline"p a / math 是代理在面积数学 a / math 中的位置，而数学 c / math 是一个常量。+ 第287行：
第288行： − 位置压力源是指与当地压力源相关的压力源。这种应激源的强度随着应激源的接近而增加。一个例子就是火灾或者动态物体，比如攻击者。它可以用下面的公式来模拟:+ 第295行：
第296行： − 数学 i lVert p a-p s rVert / math+ 第303行：
第304行： − 数学 i / 数学是压力源的强度，数学 p / 数学是代理人的位置，数学 p / 数学是压力源的位置。或者，在一个大的区域(比如火灾)产生高压力的压力源可以用正态分布 / 标准差 / 数学模型来模拟:+ 第311行：
第312行： − 数学 i p / 数学 n }(p a-p s，σ) / 数学+ 第319行：
第320行： − 人际压力源是由于邻近施压者拥挤而产生的压力源。它可以用下面的公式来模拟:+ 第327行：
第328行： − 数学 i max (n c-n p，0) / 数学+ 第335行：
第336行： − 数学 i / math 是人际压力源的强度，math n c / math 是单位空间内当前邻居的数量，math n p / math 是特定代理人单位空间内邻居的优先数字。+ 第343行：
第344行： − 感知到的压力遵循史蒂芬定律，并以下面的公式为模型:+ 第351行：
第352行： − 数学(i) i ^ n / math+ 第359行：
第360行： − + 第367行：
第368行： − 一个代理人的压力反应可以通过以下公式找到:+ 第375行：
第376行： − 数学{ dS over dt } begin { cases } alpha & text { if } psi s (- alpha leq { d psi dt } leq alpha) & text { if } psi s end { cases } / math+ 第383行：
第384行： − 其中，数学 s / math 是压力反应的上限，其最大值为 math beta / math，而 math alpha / math 是代理人的压力反应可能发生变化的最大速率。+ 第391行：
第392行： − 值得注意的人工智能模拟例子可以在新线电影公司的《指环王》电影中看到，在这部电影中，成千上万的人工智能角色互相争斗。这个人群模拟是用 Weta Digital 的 Massive 软件完成的。+ − + 第417行：
第418行： − 群体的建模技术从整体或网络的方法，以了解个人或行为方面的每个代理人不同。例如，社会力量模型描述了个体在社会互动和身体互动之间寻求平衡的需求。一种结合了这两个方面，并且能够根据情况进行调整的方法，将更好地描述自然的人类行为，总是包含一些不可预测性的措施。随着多智能体模型的使用，理解这些复杂的行为已经成为一个更容易理解的任务。使用这种类型的软件，系统现在可以在极端条件下进行测试，并在几秒钟内模拟长时间的条件。+ 第435行：
第436行： − + 第457行：
第458行： − + 第475行：
第476行： − 代理人的速度+ 第483行：
第484行： − 为了用单个代理人模拟相关参数的影响，方程定义为:+ 第555行：
第556行： − + 第571行：
第572行： − 在疏散场景中，这样做会有所帮助。以发生火灾时建筑物的疏散为例。考虑到个别代理人的特点和他们的团队表现，决定人群如何离开建筑的结果对于建筑的布局至关重要。+ 第589行：
第590行： − 一般来说，首先需要假定的是，并不是每个人都了解环境，或者哪里有危险，哪里没有危险。根据这个假设，我们可以创建三种类型的代理。第一种类型是训练有素的领导者，这种代理人了解环境，能够将知识传播给其他代理人，这样他们就知道如何从环境中退出。下一种类型的代理是未经训练的领导者---- 这种代理者不了解环境，然而，当代理者探索环境并从其他类型的领导者那里获得信息时，代理者能够传播有关环境的知识。最后一种类型的代理是跟随者，这种类型的代理只能从其他领导者那里获取信息，不能与其他代理共享信息。+ 第605行：
第606行： − 有两种类型的搜索算法试验了这种实现。有随机搜索和深度优先搜索。随机搜索是指每个代理人在环境中朝任何方向前进，并试图找到一条出路。深度优先搜索是指代理程序尽可能沿着一条路径搜索，然后返回，如果它们所经过的路径不包含退出，则尝试另一条路径。如果发现深度优先搜索比随机搜索的速度快15倍。+ 第623行：
第624行： − + 第631行：
第632行： − + 第639行：
第640行： − +
→here： 翻译1
然而，粒子系统确实有一些缺点。使用粒子系统模拟那些会根据领导的指令统一行动的人群中的主体，可能是个坏主意，因为确定哪些粒子属于主体，哪些不属于主体是非常困难的。
然而，粒子系统确实有一些缺点。使用粒子系统模拟那些会根据领导的指令统一行动的人群中的主体，可能是个坏主意，因为确定哪些粒子属于主体，哪些不属于主体是非常困难的。
--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]） crowd that the director will move on command 不确定是否是“根据领导的指令统一行动的人群”这个意思
--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]） crowd that the director will move on command 不确定是否是“根据领导的指令统一行动的人群”这个意思
=== Algorithm by Patil and Van Den Berg, Patil 和 Van Den Berg的算法===
=== Algorithm by Patil and Van Den Berg, Patil 和 Van Den Berg的算法===
This algorithm was designed for relatively simplistic crowds, where each agent in the crowd only desires to get to its own goal destination while also avoiding obstacles. This algorithm could be used for simulating a crowd in Times Square.
This algorithm was designed for relatively simplistic crowds, where each agent in the crowd only desires to get to its own goal destination while also avoiding obstacles. This algorithm could be used for simulating a crowd in Times Square.
Patil 和 Van Den Berg的算法是针对相对简单化的群体设计的，群体中的每个代理人只希望到达自己的目的地，同时避开障碍物。这个算法可以用来模拟时代广场的人群。
Patil 和 Van Den Berg的算法是针对相对简单的群体设计的，群体中的每个主体只希望到达自己的目的地，同时避开障碍物。这个算法可以用来模拟'''时代广场Times Square'''的人群。
Patils algorithm's most important and distinctive feature is that it utilizes the concept of navigation fields for directing agents. This is different from a guidance field; a guidance field is an area around the agent in which the agent is capable of "seeing"/detecting information. Guidance fields are typically used for avoiding obstacles, dynamic obstacles (obstacles that move) in particular. Every agent possesses its own guidance field. A navigation field, on the other hand, is a vector field which calculates the minimum cost path for every agent so that every agent arrives at its own goal position.
Patils algorithm's most important and distinctive feature is that it utilizes the concept of navigation fields for directing agents. This is different from a guidance field; a guidance field is an area around the agent in which the agent is capable of "seeing"/detecting information. Guidance fields are typically used for avoiding obstacles, dynamic obstacles (obstacles that move) in particular. Every agent possesses its own guidance field. A navigation field, on the other hand, is a vector field which calculates the minimum cost path for every agent so that every agent arrives at its own goal position.
Patils 算法最重要且具有区分性的特征是它利用了'''导航场Navigation Fields'''的概念来指导主体。这不同于'''指导场Guidance Field'''; 指导场是主体周围的一个区域，主体可以在其中“看到”或检测到信息。指导场通常用于避开障碍物，特别是动态障碍物(移动的障碍物)。每个主体都有自己的指导场。另一方面，导航场是一个'''向量场vector field'''，它为每个主体计算'''最小代价路径minimum cost path'''，使每个主体到达自己的目标位置。
The navigation field can only be used properly when a path exists from every free (non-obstacle) position in the environment to one of the goal positions. The navigation field is computed using coordinates of the static objects in the environment, goal positions for each agent, and the guidance field for each agent. In order to guarantee that every agent reaches its own goal the navigation field must be free of local minima, except for the presence of sinks at the specified goals.
The navigation field can only be used properly when a path exists from every free (non-obstacle) position in the environment to one of the goal positions. The navigation field is computed using coordinates of the static objects in the environment, goal positions for each agent, and the guidance field for each agent. In order to guarantee that every agent reaches its own goal the navigation field must be free of local minima, except for the presence of sinks at the specified goals.
只有当从环境中的每一个'''自由(无障碍)位置free (non-obstacle) position'''到某一目标位置的路径存在时，导航场才能被正确使用。导航场是使用环境中静态对象的坐标、每个主体的目标位置和指导场计算的。为了保证每个主体达到自己的目标，导航场必须不受'''局部极小值local minima'''的限制，除非在特定目标处存在'''汇sinks'''。
The running time of computing the navigation field is <math>O(m*n*log(mn))</math>, where m × n is the grid dimension (similar to Dijkstra's algorithm). Thus, the algorithm is only dependent on the grid resolution and not dependent on the number of agents in the environment. However, this algorithm has a high memory cost.
The running time of computing the navigation field is <math>O(m*n*log(mn))</math>, where m × n is the grid dimension (similar to Dijkstra's algorithm). Thus, the algorithm is only dependent on the grid resolution and not dependent on the number of agents in the environment. However, this algorithm has a high memory cost.
计算导航场的运行时间的公式是
<math>O(m*n*log(mn))</math>，
其中 m × n 是网格维数(类似于 Dijkstra 的算法)。因此，该算法仅依赖于网格分辨率，而不依赖于环境中的主体数量。但是，这种算法的内存开销很大。（--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]） 或者翻译“比较占内存。”？）
=== Individual behavior modelling ===
=== Individual behavior modelling 个体行为建模===
One set of techniques for AI-based crowd simulation is to model crowd behavior by advanced simulation of individual agent motivations and decision-making. Generally, this means each agent is assigned some set of variables that measure various traits or statuses such as stress, personality, or different goals. This results in more realistic crowd behavior though may be more computationally intensive than simpler techniques.
One set of techniques for AI-based crowd simulation is to model crowd behavior by advanced simulation of individual agent motivations and decision-making. Generally, this means each agent is assigned some set of variables that measure various traits or statuses such as stress, personality, or different goals. This results in more realistic crowd behavior though may be more computationally intensive than simpler techniques.
One set of techniques for AI-based crowd simulation is to model crowd behavior by advanced simulation of individual agent motivations and decision-making. Generally, this means each agent is assigned some set of variables that measure various traits or statuses such as stress, personality, or different goals. This results in more realistic crowd behavior though may be more computationally intensive than simpler techniques.
One set of techniques for AI-based crowd simulation is to model crowd behavior by advanced simulation of individual agent motivations and decision-making. Generally, this means each agent is assigned some set of variables that measure various traits or statuses such as stress, personality, or different goals. This results in more realistic crowd behavior though may be more computationally intensive than simpler techniques.
基于AI的群体建模的技术之一，是通过对个体动机和决策的高级模拟来为群体行为模型。一般来说，这意味着每个主体都被分配了一组变量来衡量不同的特征或状态，比如压力、人格或不同的目标。这导致更现实的群体行为，虽然可能计算量更大，而不是使用简单的技术。
==== Personality-based models ====
==== Personality-based models 基于人格的模型====
One method of creating individualistic behavior for crowd agents is through the use of personality traits.<ref>{{cite book |doi=10.1145/2019406.2019413 |chapter=Simulating heterogeneous crowd behaviors using personality trait theory |title=Proceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation – SCA '11 |pages=43–52 |year=2011 |last1=Guy |first1=Stephen J. |last2=Kim |first2=Sujeong |last3=Lin |first3=Ming C. |last4=Manocha |first4=Dinesh |isbn=978-1-4503-0923-3 }}</ref> Each agent may have certain aspects of their personality tuned based on a formula that associates aspects such as aggressiveness or impulsiveness with variables that govern the agents' behavior. One way this association can be found is through a subjective study in which agents are randomly assigned values for these variables and participants are asked to describe each agent in terms of these personality traits. A regression may then be done to determine a correlation between these traits and the agent variables. The personality traits can then be tuned and have an appropriate effect on agent behavior.
One method of creating individualistic behavior for crowd agents is through the use of personality traits.<ref>{{cite book |doi=10.1145/2019406.2019413 |chapter=Simulating heterogeneous crowd behaviors using personality trait theory |title=Proceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation – SCA '11 |pages=43–52 |year=2011 |last1=Guy |first1=Stephen J. |last2=Kim |first2=Sujeong |last3=Lin |first3=Ming C. |last4=Manocha |first4=Dinesh |isbn=978-1-4503-0923-3 }}</ref> Each agent may have certain aspects of their personality tuned based on a formula that associates aspects such as aggressiveness or impulsiveness with variables that govern the agents' behavior. One way this association can be found is through a subjective study in which agents are randomly assigned values for these variables and participants are asked to describe each agent in terms of these personality traits. A regression may then be done to determine a correlation between these traits and the agent variables. The personality traits can then be tuned and have an appropriate effect on agent behavior.
One method of creating individualistic behavior for crowd agents is through the use of personality traits. Each agent may have certain aspects of their personality tuned based on a formula that associates aspects such as aggressiveness or impulsiveness with variables that govern the agents' behavior. One way this association can be found is through a subjective study in which agents are randomly assigned values for these variables and participants are asked to describe each agent in terms of these personality traits. A regression may then be done to determine a correlation between these traits and the agent variables. The personality traits can then be tuned and have an appropriate effect on agent behavior.
One method of creating individualistic behavior for crowd agents is through the use of personality traits. Each agent may have certain aspects of their personality tuned based on a formula that associates aspects such as aggressiveness or impulsiveness with variables that govern the agents' behavior.
One way this association can be found is through a subjective study in which agents are randomly assigned values for these variables and participants are asked to describe each agent in terms of these personality traits. A regression may then be done to determine a correlation between these traits and the agent variables. The personality traits can then be tuned and have an appropriate effect on agent behavior.
为集群的主体创建个体行为模型的一种方法是使用人格特质。每个主体可能会根据一个公式调整他们个性的某些方面，这个公式将'''侵略性aggressiveness''' 或'''冲动性impulsiveness '''等方面与控制主体行为的变量联系起来。发现这种联系的一个方法是通过一个主观的研究，在这个研究中主体被随机分配这些变量的值，参与者被要求描述每个主体的这些人格特征。然后可以进行回归，以确定这些特征和主体变量之间的相关性。然后，人格特征可以被调整，并对主体行为产生适当的影响。
The OCEAN personality model has been used to define a mapping between personality traits and crowd simulation parameters. Automating crowd parameter tuning with personality traits provides easy authoring of scenarios with heterogeneous crowds.
The OCEAN personality model has been used to define a mapping between personality traits and crowd simulation parameters. Automating crowd parameter tuning with personality traits provides easy authoring of scenarios with heterogeneous crowds.
'''大五人格模型Big Five personality traits/OCEAN personality model'''定义了人格特质与人群模拟参数之间的映射关系。自动调整人群的人格特征参数使得在异质的人群中能够简便地创作场景。
==== Stress-based model ====
==== Stress-based model 基于压力的模型====
The behavior of crowds in high-stress situations can be modeled using [[General adaptation syndrome|General Adaptation Syndrome]] theory.l<ref>{{cite book |doi=10.1145/2159616.2159626 |chapter=Interactive simulation of dynamic crowd behaviors using general adaptation syndrome theory |title=Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games – I3D '12 |pages=55–62 |year=2012 |last1=Kim |first1=Sujeong |last2=Guy |first2=Stephen J. |last3=Manocha |first3=Dinesh |last4=Lin |first4=Ming C. |isbn=978-1-4503-1194-6 |citeseerx=10.1.1.673.3693 }}</ref> Agent behavior is affected by various stressors from their environment categorized into four prototypes: time pressure, area pressure, positional stressors, and interpersonal stressors, each with associated mathematical models.
The behavior of crowds in high-stress situations can be modeled using [[General adaptation syndrome|General Adaptation Syndrome]] theory.l<ref>{{cite book |doi=10.1145/2159616.2159626 |chapter=Interactive simulation of dynamic crowd behaviors using general adaptation syndrome theory |title=Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games – I3D '12 |pages=55–62 |year=2012 |last1=Kim |first1=Sujeong |last2=Guy |first2=Stephen J. |last3=Manocha |first3=Dinesh |last4=Lin |first4=Ming C. |isbn=978-1-4503-1194-6 |citeseerx=10.1.1.673.3693 }}</ref> Agent behavior is affected by various stressors from their environment categorized into four prototypes: time pressure, area pressure, positional stressors, and interpersonal stressors, each with associated mathematical models.
The behavior of crowds in high-stress situations can be modeled using General Adaptation Syndrome theory.l Agent behavior is affected by various stressors from their environment categorized into four prototypes: time pressure, area pressure, positional stressors, and interpersonal stressors, each with associated mathematical models.
The behavior of crowds in high-stress situations can be modeled using General Adaptation Syndrome theory.l Agent behavior is affected by various stressors from their environment categorized into four prototypes: time pressure, area pressure, positional stressors, and interpersonal stressors, each with associated mathematical models.
高压状态下的人群行为可以用'''一般适应综合征理论General Adaptation Syndrome theory'''来模拟。主体行为受到来自所处环境的各种压力源的影响，包括'''时间压力time pressure'''、'''区域压力area pressure'''、'''位置压力positional stressors'''和'''人际压力interpersonal stressors'''四个原型，每个原型都有相关的数学模型。
Time pressure refers to stressors related to a time limit in reaching a particular goal. An example would be a street crossing with a timed walk signal or boarding a train before the doors are closed. This prototype is modeled by the following formula:
Time pressure refers to stressors related to a time limit in reaching a particular goal. An example would be a street crossing with a timed walk signal or boarding a train before the doors are closed. This prototype is modeled by the following formula:
时间压力是和达到特定目标的时间限制有关的压力源。例如，一个设有限时步行信号的十字路口具有的时间压力，或在车门关闭前上车的时间压力。这个原型是按照以下公式建模的:
<math>I_t = max(t_e - t_a, 0)</math>
<math>I_t = max(t_e - t_a, 0)</math>
<math>I_t = max(t_e - t_a, 0)</math>
where <math display="inline">I_t</math> is the intensity of the time pressure as a function of the estimated time to reach the goal <math display="inline">t_e</math> and a time constraint <math>t_a</math>.
where <math display="inline">I_t</math> is the intensity of the time pressure as a function of the estimated time to reach the goal <math display="inline">t_e</math> and a time constraint <math>t_a</math>.
其中 math display"inline"i t / math 是时间压力的强度，作为达到目标数学显示的估计时间的函数"inline"t e / math 和一个时间限制的数学 t a / math。
其中 <math display="inline">I_t</math> 是时间压力强度，它是达到目标的估计时间<math display="inline">t_e</math>和时间限制 <math>t_a</math>的函数。
Area pressure refers to stessors as a result of an environmental condition. Examples would be noise or heat in an area. The intensity of this stressor is constant over a particular area and is modeled by the following formula:
Area pressure refers to stessors as a result of an environmental condition. Examples would be noise or heat in an area. The intensity of this stressor is constant over a particular area and is modeled by the following formula:
区域压力是指由于环境条件而产生的压力。例如某个地区的噪音或热量。这种应激源的强度在某一特定地区是恒定的，其模型如下:
<math>I_a = \begin{cases} c & \text{if }p_a\in A \\ 0 & \text{if }p_a\not\in A \end{cases}</math>
<math>I_a = \begin{cases} c & \text{if }p_a\in A \\ 0 & \text{if }p_a\not\in A \end{cases}</math>
<math>I_a = \begin{cases} c & \text{if }p_a\in A \\ 0 & \text{if }p_a\not\in A \end{cases}</math>
where <math display="inline">I_a</math> is the intensity of the area pressure, <math display="inline">p_a</math> is the position of the agent in an area <math>A</math>, and <math>c</math> is a constant.
where <math display="inline">I_a</math> is the intensity of the area pressure, <math display="inline">p_a</math> is the position of the agent in an area <math>A</math>, and <math>c</math> is a constant.
其中<math display="inline">I_a</math>是区域压力强度，<math display="inline">p_a</math> 是主体在A区的位置，c是一个常数。
Positional stressors refer to stressors associated with a local source of stress. The intensity of this stressor increases as an agent approaches the source of the stress. An example would be a fire or a dynamic object such as an assailant. It can be modeled by the following formula:
Positional stressors refer to stressors associated with a local source of stress. The intensity of this stressor increases as an agent approaches the source of the stress. An example would be a fire or a dynamic object such as an assailant. It can be modeled by the following formula:
位置压力是指与局部压力源相关的压力源。这种压力源的强度随着主体接近压力源的程度而增加。一个例子就是火灾，或运动的物体比如攻击者。它可以用下面的公式来模拟:
<math>I_p = \lVert p_a - p_s \rVert</math>
<math>I_p = \lVert p_a - p_s \rVert</math>
<math>I_p = \lVert p_a - p_s \rVert</math>
where <math>I_p</math> is the intensity of the positional stressor, <math>p_a</math> is the position of the agent and <math>p_s</math> is the position of the stressor. Alternatively, stressors that generate high stress over a large area (such as a fire) can be modeled using a Gaussian distribution with standard deviation <math>\sigma</math>:
where <math>I_p</math> is the intensity of the positional stressor, <math>p_a</math> is the position of the agent and <math>p_s</math> is the position of the stressor. Alternatively, stressors that generate high stress over a large area (such as a fire) can be modeled using a Gaussian distribution with standard deviation <math>\sigma</math>:
其中 <math>I_p</math> 是位置压力源的强度，<math>p_a</math> 是主体的位置，<math>p_s</math> 是压力源的位置。另外，在一个大的区域产生高压力的压力源(如火灾)，可以用一个带有正态分布的标准差<math>\sigma</math>的模型来模拟:
<math>I_p = \mathcal{N}(p_a - p_s, \sigma)</math>
<math>I_p = \mathcal{N}(p_a - p_s, \sigma)</math>
<math>I_p = \mathcal{N}(p_a - p_s, \sigma)</math>
Interpersonal stressors are stressors as a result of crowding by nearby agents. It can be modeled by the following formula:
Interpersonal stressors are stressors as a result of crowding by nearby agents. It can be modeled by the following formula:
人际压力源是由于邻近主体的'''拥挤crowding'''程度而产生的压力源。它可以用下面的公式来模拟:
<math>I_i = max(n_c - n_p, 0)</math>
<math>I_i = max(n_c - n_p, 0)</math>
<math>I_i = max(n_c - n_p, 0)</math>
where <math>I_i</math> is the intensity of the interpersonal stressor, <math>n_c</math> is the current number of neighbors within a unit space and <math>n_p</math> is the preferred number of neighbors within a unit space for that particular agent.
where <math>I_i</math> is the intensity of the interpersonal stressor, <math>n_c</math> is the current number of neighbors within a unit space and <math>n_p</math> is the preferred number of neighbors within a unit space for that particular agent.
其中<math>I_i</math>表示人际压力源的强度，<math>n_c</math> 表示单位空间内当前邻居的数量，<math>n_p</math> 表示单位空间内该特定主体理想的邻居数量。
The perceived stress follows Steven's Law and is modeled by the formula:
The perceived stress follows Steven's Law and is modeled by the formula:
感知到的压力遵循'''史蒂芬定律Steven's Law '''，并可以用下面的公式模拟:
<math>\psi(I) = kI^n</math>
<math>\psi(I) = kI^n</math>
<math>\psi(I) = kI^n</math>
where <math>\psi(I)</math> is the perceived stress for a stress level <math>I</math>, <math>k</math> is a scale factor, and <math>n</math> is an exponent depending on the stressor type.
where <math>\psi(I)</math> is the perceived stress for a stress level <math>I</math>, <math>k</math> is a scale factor, and <math>n</math> is an exponent depending on the stressor type.
其中 math psi (i) / math 是压力级别数学 i / math 的感知压力，math k / math 是刻度因子，math n / math 是根据压力类型的指数。
其中<math>\psi(I)</math>是感知到的压力水平，<math>I</math>是客观的压力水平，<math>k</math> 是一个比例系数，<math>n</math>是一个取决于压力源类型的指数。
An agent's stress response can be found with the following formula:
An agent's stress response can be found with the following formula:
一个主体的压力反应可以通过以下公式找到:
<math>{dS \over dt} = \begin{cases} \alpha & \text{if } \psi > S \\ (-\alpha \leq {d\psi \over dt} \leq \alpha) & \text{if } \psi = S\\ -\alpha & \text{if } \psi < S\end{cases}</math>
<math>{dS \over dt} = \begin{cases} \alpha & \text{if } \psi > S \\ (-\alpha \leq {d\psi \over dt} \leq \alpha) & \text{if } \psi = S\\ -\alpha & \text{if } \psi < S\end{cases}</math>
<math>{dS \over dt} = \begin{cases} \alpha & \text{if } \psi > S \\ (-\alpha \leq {d\psi \over dt} \leq \alpha) & \text{if } \psi = S\\ -\alpha & \text{if } \psi < S\end{cases}</math>
where <math>S</math> is the stress response capped at a maximum value of <math>\beta</math> and <math>\alpha</math> is the maximum rate at which an agent's stress response can change.
where <math>S</math> is the stress response capped at a maximum value of <math>\beta</math> and <math>\alpha</math> is the maximum rate at which an agent's stress response can change.
其中，<math>S</math>是压力反应，它受到最大<math>\beta</math>值的限制，<math>\alpha</math>是主体的压力反应可以改变的最大速率。
Examples of notable crowd AI simulation can be seen in New Line Cinema's The Lord of the Rings films, where AI armies of thousands of characters battle each other. This crowd simulation was done using Weta Digital's Massive software.
Examples of notable crowd AI simulation can be seen in New Line Cinema's The Lord of the Rings films, where AI armies of thousands of characters battle each other. This crowd simulation was done using Weta Digital's Massive software.
值得注意的AI模拟例子可以在'''新线电影公司New Line Cinema'''的《指环王Lord of the Rings》系列电影中看到。在这部电影中，成千上万的AI角色互相争斗。这个人群模拟是用 Weta Digital 的 Massive 软件完成的。
=== Sociology ===
=== Sociology 社会学===
''Crowd simulation'' can also refer to simulations based on [[group dynamics]] and [[crowd psychology]], often in public safety planning. In this case, the focus is just the behavior of the crowd, and not the visual realism of the simulation. Crowds have been studied as a scientific interest since the end of the 19th Century. A lot of research has focused on the collective social behavior of people at social gatherings, assemblies, protests, rebellions, concerts, sporting events and religious ceremonies. Gaining insight into natural human behavior under varying types of stressful situations will allow better models to be created which can be used to develop crowd controlling strategies.
''Crowd simulation'' can also refer to simulations based on [[group dynamics]] and [[crowd psychology]], often in public safety planning. In this case, the focus is just the behavior of the crowd, and not the visual realism of the simulation. Crowds have been studied as a scientific interest since the end of the 19th Century. A lot of research has focused on the collective social behavior of people at social gatherings, assemblies, protests, rebellions, concerts, sporting events and religious ceremonies. Gaining insight into natural human behavior under varying types of stressful situations will allow better models to be created which can be used to develop crowd controlling strategies.
Modeling techniques of crowds vary from holistic or network approaches to understanding individualistic or behavioral aspects of each agent. For example, the Social Force Model describes a need for individuals to find a balance between social interaction and physical interaction. An approach that incorporates both aspects, and is able to adapt depending on the situation, would better describe natural human behavior, always incorporating some measure of unpredictability. With the use of multi-agent models understanding these complex behaviors has become a much more comprehensible task. With the use of this type of software, systems can now be tested under extreme conditions, and simulate conditions over long periods of time in the matter of seconds.
Modeling techniques of crowds vary from holistic or network approaches to understanding individualistic or behavioral aspects of each agent. For example, the Social Force Model describes a need for individuals to find a balance between social interaction and physical interaction. An approach that incorporates both aspects, and is able to adapt depending on the situation, would better describe natural human behavior, always incorporating some measure of unpredictability. With the use of multi-agent models understanding these complex behaviors has become a much more comprehensible task. With the use of this type of software, systems can now be tested under extreme conditions, and simulate conditions over long periods of time in the matter of seconds.
群体的建模技术从整体或网络的方法，以了解个人或行为方面的每个主体不同。例如，社会力量模型描述了个体在社会互动和身体互动之间寻求平衡的需求。一种结合了这两个方面，并且能够根据情况进行调整的方法，将更好地描述自然的人类行为，总是包含一些不可预测性的措施。随着多智能体模型的使用，理解这些复杂的行为已经成为一个更容易理解的任务。使用这种类型的软件，系统现在可以在极端条件下进行测试，并在几秒钟内模拟长时间的条件。
Helbing proposed a model based on physics using a particle system and socio-psychological forces in order to describe human crowd behavior in panic situation, this is now called the Helbing Model. His work is based on how the average person would react in a certain situation. Although this is a good model, there are always different types of people present in the crowd and they each have their own individual characteristics as well as how they act in a group structure. For instance, one person may not react to a panic situation, while another may stops walking and interfere in the crowd dynamics as a whole. Furthermore, depending on the group structure, the individual action can change because the agent is part of a group, for example, returning to a dangerous place in order to rescue a member of that group. Helbing's model can be generalized incorporating individualism, as proposed by Braun, Musse, Oliveira and Bodmann.
Helbing proposed a model based on physics using a particle system and socio-psychological forces in order to describe human crowd behavior in panic situation, this is now called the Helbing Model. His work is based on how the average person would react in a certain situation. Although this is a good model, there are always different types of people present in the crowd and they each have their own individual characteristics as well as how they act in a group structure. For instance, one person may not react to a panic situation, while another may stops walking and interfere in the crowd dynamics as a whole. Furthermore, depending on the group structure, the individual action can change because the agent is part of a group, for example, returning to a dangerous place in order to rescue a member of that group. Helbing's model can be generalized incorporating individualism, as proposed by Braun, Musse, Oliveira and Bodmann.
Helbing 提出了一个基于物理学的模型，使用粒子系统和社会心理力量来描述人群在恐慌情况下的行为，这个模型现在被称为 Helbing 模型。他的工作基于普通人在特定情况下的反应。虽然这是一个很好的模式，但是在人群中总是有不同类型的人，他们每个人都有自己的个性以及他们在群体结构中的行为方式。例如，一个人可能不会对恐慌情况做出反应，而另一个人可能会停下脚步，干扰整个人群的动态。此外，取决于群体结构，个体行为可能会发生变化，因为代理人是群体的一部分，例如，为了拯救该群体的一个成员而返回到一个危险的地方。海尔宾的模式可以是由布劳恩、缪斯、奥利维拉和博德曼提出的广义合并个人主义。
Helbing 提出了一个基于物理学的模型，使用粒子系统和社会心理力量来描述人群在恐慌情况下的行为，这个模型现在被称为 Helbing 模型。他的工作基于普通人在特定情况下的反应。虽然这是一个很好的模式，但是在人群中总是有不同类型的人，他们每个人都有自己的个性以及他们在群体结构中的行为方式。例如，一个人可能不会对恐慌情况做出反应，而另一个人可能会停下脚步，干扰整个人群的动态。此外，取决于群体结构，个体行为可能会发生变化，因为主体是群体的一部分，例如，为了拯救该群体的一个成员而返回到一个危险的地方。海尔宾的模式可以是由布劳恩、缪斯、奥利维拉和博德曼提出的广义合并个人主义。
IdFamily – Identifier of the family. A family is a predefined group formed by agents who know each other
IdFamily – Identifier of the family. A family is a predefined group formed by agents who know each other
Idfamily-家族标识符。家族是由相互认识的代理人组成的一个预定义的组
Idfamily-家族标识符。家族是由相互认识的主体组成的一个预定义的组
# DE – Dependence level of the agent which mimics the need for help. Values [0,1]
# DE – Dependence level of the agent which mimics the need for help. Values [0,1]
v<sub>i</sub> – Speed of the agent
v<sub>i</sub> – Speed of the agent
主体的速度
To model the effect of the dependence parameter with individual agents, the equation is defined as:
To model the effect of the dependence parameter with individual agents, the equation is defined as:
为了用单个主体模拟相关参数的影响，方程定义为:
Consequently, the greater the parameter of agent , the bigger will be which points to the agent and has the high level of . When both agents are close enough to each other, the one with high (agent in this example) adopts the value of agent (<math>DE_j = DE_i</math>). This means that the evacuation ability of agent is shared with agent and both start moving together.
Consequently, the greater the parameter of agent , the bigger will be which points to the agent and has the high level of . When both agents are close enough to each other, the one with high (agent in this example) adopts the value of agent (<math>DE_j = DE_i</math>). This means that the evacuation ability of agent is shared with agent and both start moving together.
因此，智能体的参数越大，指向智能体的参数就越大，具有较高的智能体水平。当两个代理彼此足够接近时，具有较高值的代理(本例中的代理)采用代理的值(math DE j DE i / math)。这意味着代理人的撤离能力是与代理人共享的，两者一起开始移动。
因此，智能体的参数越大，指向智能体的参数就越大，具有较高的智能体水平。当两个代理彼此足够接近时，具有较高值的代理(本例中的代理)采用代理的值(math DE j DE i / math)。这意味着主体的撤离能力是与主体共享的，两者一起开始移动。
The places where this would be helpful would be in an evacuation scenario. Take for example, an evacuation of a building in the case of a fire. Taking into account the characteristics of individual agents and their group performances, determining the outcome of how the crowd would exit the building is critically important in creating the layout of the building.
The places where this would be helpful would be in an evacuation scenario. Take for example, an evacuation of a building in the case of a fire. Taking into account the characteristics of individual agents and their group performances, determining the outcome of how the crowd would exit the building is critically important in creating the layout of the building.
在疏散场景中，这样做会有所帮助。以发生火灾时建筑物的疏散为例。考虑到个别主体的特点和他们的团队表现，决定人群如何离开建筑的结果对于建筑的布局至关重要。
In general, the first thing that has to be assumed is that not everyone has knowledge about the environment or where there are and aren't hazards. From this assumption we can create three types of agents. The first type is a trained leader, this agent knows about the environment and is able to spread knowledge to other agents so they know how to exit from an environment. The next type of agent is an untrained leader, this agent does not know about the environment, however, as the agent explores the environment and gets information from other types of leaders, the agent is able to spread the knowledge about the environment. The last type of agent is a follower, this type of agent can only take information from other leaders and not be able to share the information with other agents.
In general, the first thing that has to be assumed is that not everyone has knowledge about the environment or where there are and aren't hazards. From this assumption we can create three types of agents. The first type is a trained leader, this agent knows about the environment and is able to spread knowledge to other agents so they know how to exit from an environment. The next type of agent is an untrained leader, this agent does not know about the environment, however, as the agent explores the environment and gets information from other types of leaders, the agent is able to spread the knowledge about the environment. The last type of agent is a follower, this type of agent can only take information from other leaders and not be able to share the information with other agents.
一般来说，首先需要假定的是，并不是每个人都了解环境，或者哪里有危险，哪里没有危险。根据这个假设，我们可以创建三种类型的代理。第一种类型是训练有素的领导者，这种主体了解环境，能够将知识传播给其他主体，这样他们就知道如何从环境中退出。下一种类型的代理是未经训练的领导者---- 这种代理者不了解环境，然而，当代理者探索环境并从其他类型的领导者那里获得信息时，代理者能够传播有关环境的知识。最后一种类型的代理是跟随者，这种类型的代理只能从其他领导者那里获取信息，不能与其他代理共享信息。
There were two types of searching algorithms tried out for this implementation. There was the random search and the depth first search. A random search is where each of the agents go in any direction through the environment and try to find a pathway out. The depth first search is where agents follow one path as far as it can go then return and try another path if the path they traversed does not contain an exit. If was found that depth first search gave a speed up of 15 times versus a random search.
There were two types of searching algorithms tried out for this implementation. There was the random search and the depth first search. A random search is where each of the agents go in any direction through the environment and try to find a pathway out. The depth first search is where agents follow one path as far as it can go then return and try another path if the path they traversed does not contain an exit. If was found that depth first search gave a speed up of 15 times versus a random search.
有两种类型的搜索算法试验了这种实现。有随机搜索和深度优先搜索。随机搜索是指每个主体在环境中朝任何方向前进，并试图找到一条出路。深度优先搜索是指代理程序尽可能沿着一条路径搜索，然后返回，如果它们所经过的路径不包含退出，则尝试另一条路径。如果发现深度优先搜索比随机搜索的速度快15倍。
Spatial situation is a situation that has a region where the environment affects the local agents. For instance, a crowd waiting in line for a ticket booth would be displaying a spatial situation. Other examples may be a bus stop or an ATM where characters act upon their environment. Therefore, we would consider 'bus stop' as the situation if the behavior of the agents are to be getting on or off a bus.
Spatial situation is a situation that has a region where the environment affects the local agents. For instance, a crowd waiting in line for a ticket booth would be displaying a spatial situation. Other examples may be a bus stop or an ATM where characters act upon their environment. Therefore, we would consider 'bus stop' as the situation if the behavior of the agents are to be getting on or off a bus.
空间情境是指环境影响局部行为者的区域情境。例如，一个排队等候售票亭的人群将展示一个空间的情况。其他的例子可能是一个总线站或者一个 ATM，在那里字符作用于他们的环境。因此，如果代理人的行为是上车或下车，我们可以把“公交车站”看作是一种情况。
空间情境是指环境影响局部行为者的区域情境。例如，一个排队等候售票亭的人群将展示一个空间的情况。其他的例子可能是一个总线站或者一个 ATM，在那里字符作用于他们的环境。因此，如果主体的行为是上车或下车，我们可以把“公交车站”看作是一种情况。
Non-Spatial situation has no region in the environment because this only involves the behavior of the crowd. The relationship of the local agents is an important factor to consider when determining behavior. An example would be a group of friends walking together. Typical behavior of characters that are friends would all move along with each other. This means that 'friendship' would be the situation among the typical behavior of walking together.
Non-Spatial situation has no region in the environment because this only involves the behavior of the crowd. The relationship of the local agents is an important factor to consider when determining behavior. An example would be a group of friends walking together. Typical behavior of characters that are friends would all move along with each other. This means that 'friendship' would be the situation among the typical behavior of walking together.
Non-Spatial 的情况没有区域的环境，因为这只涉及到人群的行为。在决定行为时，局部代理人之间的关系是一个重要的因素。一个例子是一群朋友一起散步。作为朋友的角色的典型行为都会互相影响。这意味着“友谊”是一起散步的典型行为之一。
Non-Spatial 的情况没有区域的环境，因为这只涉及到人群的行为。在决定行为时，局部主体之间的关系是一个重要的因素。一个例子是一群朋友一起散步。作为朋友的角色的典型行为都会互相影响。这意味着“友谊”是一起散步的典型行为之一。
The structure of any situation is built upon four components, Behavior functions, Sensors, States, and Event Rules. Behavior functions represent what the characters behaviors are specific to the situation. Sensors are the sensing capability for agents to see and respond to events. States are the different motions and state transitions used only for the local behaviors. Event rule is the way to connect different events to their specific behaviors. While a character is being put into a situation, these four components are considered at the same time. For spatial situations, the components are added when the individual initially enters the environment that influences the character. For non-spatial situations, the character is affected only once the user assigns the situation to the character. The four components are removed when the agent is taken away from its situations region or the situation itself is removed. The dynamic adding and removing of the situations lets us achieve scalable agents.
The structure of any situation is built upon four components, Behavior functions, Sensors, States, and Event Rules. Behavior functions represent what the characters behaviors are specific to the situation. Sensors are the sensing capability for agents to see and respond to events. States are the different motions and state transitions used only for the local behaviors. Event rule is the way to connect different events to their specific behaviors. While a character is being put into a situation, these four components are considered at the same time. For spatial situations, the components are added when the individual initially enters the environment that influences the character. For non-spatial situations, the character is affected only once the user assigns the situation to the character. The four components are removed when the agent is taken away from its situations region or the situation itself is removed. The dynamic adding and removing of the situations lets us achieve scalable agents.
任何情况的结构都建立在四个组件之上: 行为函数、传感器、状态和事件规则。行为函数表示特定情况下的特定行为。传感器是一种感知能力，可以让代理人看到并对事件做出反应。状态是仅用于局部行为的不同运动和状态转移。事件规则是将不同的事件与其特定的行为联系起来的方法。当一个角色被置于一个情境中时，这四个部分同时被考虑。对于空间情景，当个体最初进入影响角色的环境时，添加组件。对于非空间情境，只有当用户将情境赋值给角色时，角色才会受到影响。当代理人被带离其情况区域或情况本身被移除时，这四个组件被移除。动态地添加和删除这些情况使我们能够实现可伸缩的代理。
任何情况的结构都建立在四个组件之上: 行为函数、传感器、状态和事件规则。行为函数表示特定情况下的特定行为。传感器是一种感知能力，可以让主体看到并对事件做出反应。状态是仅用于局部行为的不同运动和状态转移。事件规则是将不同的事件与其特定的行为联系起来的方法。当一个角色被置于一个情境中时，这四个部分同时被考虑。对于空间情景，当个体最初进入影响角色的环境时，添加组件。对于非空间情境，只有当用户将情境赋值给角色时，角色才会受到影响。当主体被带离其情况区域或情况本身被移除时，这四个组件被移除。动态地添加和删除这些情况使我们能够实现可伸缩的代理。
== Human-like behaviors and crowd AI ==
== Human-like behaviors and crowd AI ==