基于多Agent的人工鱼群自组织行为算法

在基于认知的人工鱼行为模型的基础上,增加实现鱼群个体间通信及鱼群与环境交互的互操作行为模块,建立面向群体行为的人工鱼体系结构与模型。提出了一种基于多Agent的人工鱼群自组织行为的研究方法：将基于这种体系结构的人工鱼作为Agent,其能感知环境信息,产生意图,规划行为。建立鱼群中Agent的运动、捕食、逃逸模型,通过个体间的相互作用涌现出群体的自组织行为,从而实现对鱼群的逼真模拟。     

鱼集群游动的节能机理研究综述

集群是鱼类生物中一种常见的现象,特定编队的集群运动可以显著提高鱼群的游动效率.鱼集群游动节能机理的研究为机器人集群编队设计和控制提供启发与帮助,得到了研究人员的广泛关注.本文介绍了鱼集群游动节能机理研究的主要方法及最新的研究成果,将研究方法分为鱼群观察分析法、计算流体力学仿真法和实验装置研究法,并基于此对近些年的研究成...     

人工鱼群高级自组织行为研究

在Tu Xiaoyuan和John David Funge研究工作的基础上, 进一步研究人工鱼群的高级自组织行为. 基于个体人工鱼的行为模型, 提出一种基于认知的人工鱼群高级行为自组织方法. 该方法中, 每条人工鱼被看作一个agent. 通过感知外部虚拟环境信息, agent产生行为意图. 人工鱼群的自组织行为通过多个agent间的相互作用涌现形成, 如人工鱼群的运动、捕食、逃逸等行为规划, 从而体现自然鱼群的生物特性, 实现对自然鱼群高级行为的逼真模拟. 我们设计和实现的基于认知的人工鱼群动画系统, 测试验证了所提出的高级行为自组织方法的有效性.     

基于KOD能量特征的群体异常行为识别

在群体异常行为识别过程中, 针对传统特征易受目标遮挡影响导致其对群体行为的弱描述性问题, 提出一种基于KOD（kinetic orientation distance）能量特征的群体异常行为识别方法。该能量特征忽略群体中相互遮挡的个体的局部特征, 从群体行为整体上分别根据群体的运动剧烈程度、群体运动方向一致性和群体中个体的相对位置定义并提取群体动能、方向势能和距离势能构成群体行为高层KOD能量特征, 以此描述群体的运动状态变化, 最后通过构建隐马尔可夫模型实现群体异常行为检测及类型识别。在PETS和UMN公共数据集上进行实验并与传统光流特征进行对比, 实验结果表明, 使用KOD能量特征能够有效地检测出群体异常行为并识别出其类型, 且能够达到92%的准确率。     

人工鱼群高级行为的自组织算法与实现

论文在人工鱼行为模型的基础上,建立面向群体行为的人工鱼体系结构与模型,提出了一种基于多Agent的人工鱼群自组织行为的研究方法：将基于这种体系结构人工鱼作为Agent,其能感知环境信息,产生意图,规划行为,最后通过运动系统产生运动来完成行为和实现意图。在群体的移动过程中,如果两个个体之间的距离小于某个给定的值,则它们互相称为对方的邻居,个体倾向于与自己的“邻居”保持一致。每个个体以固定的速率运动,在给定时刻,个体的运动方向为上一时刻它的“邻居”运动方向的平均,鱼群中的个体一个时步一个时步连续完成同步这种运动。     

双鱼并排游动时水动力性能研究

随着水下仿生机器人的发展,人们开始关注鱼群个体之间的能量传输.鱼类在水中游动时,尾鳍摆动会与水相互作用,形成尾涡.鱼类会从附近尾涡中汲取能量,降低自身消耗.但是,有学者指出鱼群中不同摆动相位差个体之间存在相互干扰,阻碍鱼群前进,增加了自身能量消耗.使用一种在线实时功率检测系统,检测并排游动时两条机器鱼的纯功率、速度等鱼群水动力性能随着机器鱼摆动其相位差变化趋势.同时研究了双鱼之间横向距离对纯功率消耗影响,并结合纯功率和速度计算机器鱼推力.引入效率计算方法,并结合纯功率、速度和推力,计算和拟合效率分布趋势图.     

一种新型二进制编码的量子鱼群算法

本文主要将量子行为引入鱼群算法,通过量子编码来有效的扩大个体的多样性,将群体智能理论和量子理论结合,提出一种基于量子计算概念和理论的量子鱼群算法.与传统鱼群算法相比,该算法重新定义个体位置向量和个体之间的距离,借鉴量子比特的叠加性,采用量子编码来表征个体位置,能够表示出许多可能的线性叠加状态.模拟量子坍塌的随机观察可带来丰富的种群,量子编码的特性也能够简单方便地引导个体位置的更新.因此,它比传统鱼群算法具有更好的种群多样性,更快的收敛速度和全局寻优的能力,并通过仿真计算也表明了此算法的优越性.     

揭示生物集群系统内部信息耦合机制的深度网络模型

生物集群在自然界中广泛存在,如鱼群、鸟群、兽群等,这些集群通过内部的信息耦合能涌现出有序的协同行为.但是,集群内部交互复杂、情况多变,导致微观层面的行为分析还缺乏行之有效的标准工具.对此,以鱼群运动数据为研究对象,借助图注意力网络对鱼群中的单体行为进行自动化建模,目的是提炼出适于复杂系统分析的通用网络工具.首先将单体的感知信息映射到高维状态空间,然后生成软注意力数值以表征单体之间的交互强度,再对所生成的软注意力数值规范化,所得规范结果既可作为多邻居信息耦合的关键指标,又可通过解码器将所抽取的注意力信息稀疏解耦为运动决策.实验结果表明:所生成的注意力数值不但能揭示群体内部的信息耦合关系,还能进一步对隐藏交互强度可视化,从而为鱼群的视觉交互理论提供新的科学证据.所提出分析工具拥有信息耦合可解释、交互强度可显现、系统规模可缩放、状态偏移可泛化等优良特性,有望发展成为复杂系统解耦分析的标准范式,在社会行为分析、机器人集群控制以及智能交通系统安全性评价等方面具有潜在的应用价值.     

群体动力学的群组行为仿真

目的 许多群体动画算法侧重从宏观或微观角度模拟人群运动,而结合两种方法模拟群组动态的算法较少,为解决这个问题,提出一种基于群体动力学的群组行为仿真算法。方法 首先,采用连续模型构建动态势能场,为个体计算运动初始速度;然后,基于群体动力学模拟组内跟随和组间避让行为;在组内跟随行为中采用“Car-following”模型为个体计算跟随加速度;在组间避让行为中提出群组的凸包表示方法,并引入局部势能场;最后,结合动态势能场和局部势能场实现群组行为仿真。结果 在每个仿真循环中动态更新全局势能场信息,对比不同群体规模及网格精度的人群仿真效率。实验结果表明本文算法能用于模拟规模较大的多样性群组运动。在网格分辨率为80×80像素的场景中对5 000个个体的运动进行仿真,平均帧速率为35.7 ms（约28帧/s）,与传统的连续模型相比产生了更多的群组行为。采用快速行进法构建全局动态势能场,即使在粗糙网格中也能得到较为平滑的路径。结论 提出算法适用于多样性群组行为仿真,同时结合全局规划和局部控制,无需额外碰撞检测便能真实地模拟组内跟随和组间避让行为,仿真效果具有高效性和多样性。     

随机扰动下多源群体觅食系统建模与仿真

群集智能是指复杂的集体智能来自简单个体之间以及个体同环境之间的相互作用. 通常对群集智能的研究主要借助于群居生物行为的观察. 蚁群觅食行为是研究简单个体产生复杂行为的一个典型的例子. 首先建立群体觅食宏观序参数模型. 模型考虑了食物源的量和分布以及环境噪声对个体决策的随机影响. 给出2个食物源下系统模型的数值解,表明在较大的噪声影响下,系统有一定的概率会脱离最优解,到达次优解. 在Starlogo仿真平台下的实验结果表明,觅食蚂蚁的数量同任务完成时间以及碰撞频率之间呈现出幂指数关系. 这对自组织系统和群集智能的研究有一定的理论意义,并可以用来指导设计更加有效、适应、可靠的智能系统.     

An optimization algorithm for multimodal functions inspired by collective animal behavior

Interest in multimodal function optimization is expanding rapidly as real-world optimization problems often demand locating multiple optima within a search space. This article presents a new multimodal optimization algorithm named as the collective animal behavior. Animal groups, such as schools of fish, flocks of birds, swarms of locusts, and herds of wildebeest, exhibit a variety of behaviors including swarming about a food source, milling around a central location, or migrating over large distances in aligned groups. These collective behaviors are often advantageous to groups, allowing them to increase their harvesting efficiency to follow better migration routes, to improve their aerodynamic, and to avoid predation. In the proposed algorithm, searcher agents are a group of animals which interact with each other based on the biologic laws of collective motion. Experimental results demonstrate that the proposed algorithm is capable of finding global and local optima of benchmark multimodal optimization problems with a higher efficiency in comparison with other methods reported in the literature.     

鱼群涌现机制下集群机器人运动强化的迁移控制

采用鱼群模型驱动多智能体可以涌现出优良的运动特性,但是,由于机器人与真实鱼类相比具有较大的差异性,使得鱼群模型难以应用于真实机器人系统.为此,提出一种结合深度学习与强化学习的迁移控制方法,首先,使用鱼群运动数据训练深度网络(deep neural network, DNN)模型,以此作为机器人成对交互的基础;然后,连接强化学习的深度确定性策略梯度方法(deep deterministic policy gradient, DDPG)来修正DNN模型的输出,设计集群最大视觉尺寸方法挑选关键邻居,从而将DNN+DDPG模型拓展到多智能体的运动控制.集群机器人运动实验表明:所提出方法能使机器人仅利用单个邻居信息就能形成可靠、稳定的集群运动,与单纯DNN直接迁移控制相比,所提出DNN+DDPG控制框架既可以保存原有鱼群运动的灵活性,又能增强机器人系统的安全性与可控性,使得该方法在集群机器人运动控制领域具有较大的应用潜力.     

布尔 控制 网络 的集 成集 可控

集群运动的自组织控制相较于控制理论方法更具鲁棒性与灵活性,其中具有强大自组织特性的生物种群多表现为单体的等级交互,其特点是交互双方各自影响互不对称,由于信息交互繁杂导致构建等级交互模型仍充满挑战.鉴于此,使用深度学习技术分析红鼻鱼的集群运动实验数据,构建多参数输入的单体等级交互模型,有针对地设计成对交互的深度网络结构,并进行合理训练以获取交互模型,基于视觉压力挑选出关键邻居,将此模型用于该邻居的等级交互,相较于其他邻居选择方式,所提出智能控制方法与真实鱼类的集群运动具有较一致的宏观特性.仿真实验表明:所提出方法能扩展应用到更大规模的集群聚合运动控制中,使得单体仅利用局部信息即可实现大规模的集群运动;该方法具有使用简单、规模灵活、计算快速的特点,在多机器人控制、智能交通系统、饱和集群攻击以及多智能体物流等领域具有广阔的应用前景.     

A collective motion model based on two-layer relationship mechanism for bi-direction pedestrian flow simulation

In crowd dynamic, relations are existed among some pedestrians, which cause frequent interactions during evacuation, creating collective motion phenomena, such as the most common pattern of team-groups. Besides, collective behavior can make a beneficial effect on the evacuation process. Therefore, this paper proposes a collective motion model to simulate bi-direction pedestrian flow. First, a method of group vision sharing is proposed to help pedestrians learn the crowd around. Based on two-layer relationship mechanism proposed, aggregate force and collective collision avoidance force are added into the original social force formula. The aggregate force is the resultant of two forces, one is the attraction among the leader and team members, and the other one is that among members of groups due to the social relations. Simulation results show that the modified model can reproduce the team-groups collective pattern in real world bi-direction pedestrian flow, and can reduce the collision risk with regarding the group as collision avoidance unit. Furthermore, the evacuation efficiency is improved.     

No-beacon collective circular motion of jointly connected multi-agents

In this paper, a decentralized control algorithm is proposed for a group of nonholonomic vehicles to form a class of collective circular motion behavior. Without the guidance of a global beacon, the desired collective behavior occurs provided that the multi-agent system is jointly connected. Moreover, a repulsion mechanism is considered to improve the distribution evenness of the agents’ circular motion phases and hence to avoid collision. The effectiveness of the approach is verified through both theoretical analysis and numerical simulation. Moreover, some interesting variations of the circular motion model are investigated to enrich the collective behaviors.     

A simulation study on autonomous decentralized mechanism in fish behaviour model

The behaviour of a fish school is considered an interesting phenomenon because a fish school behaves differently in various situations. The paper considers a fish school as an autonomous decentralized system and constructs a mathematical model for the autonomous decentralized mechanism. Simulation results show that, by varying the quantity of information exchange among members in school, the present model describes fish behaviour not only for a school with fixed configuration but also for that with variable form. Furthermore, a remarkable difference in fish trajectory is found between the two schools.     

Performance measures of an ant based decentralised routing scheme for circuit switching communication networks

 Swarm intelligence is a new challenging branch of artificial life which takes advantage of the collective behaviour of animals with limited intellectual faculties (insects, flocking birds, schools of fish) to solve algorithmically complex problems. Recently a new routing method based on the way that ants are communicating with each other has been applied to solve routing problems in telecommunication networks. This paper examines the behavior of an ant based decentralised router using an adequate set of commonly acceptable and some newly introduced metrics.     

Explaining the autoinhibition of the SMYD enzyme family: A theoretical study

The SMYD enzymes (SMYD1-5) are lysine methyltransferases that have diverse biological functions including gene expression and regulation of skeletal and cardiac muscle development and function. Recently, they have gained more attention as potential drug targets because of their involvement in cardiovascular diseases and in the progression of different cancer types. Their activity has been suggested to be regulated by a posttranslational mechanism and by autoinhibition. The later relies on a hinge-like movement of the N- and C-lobes to adopt an open or closed conformation, consequently, determining the accessibility of the active site and substrate specificity.In this study we aim to investigate and explain the possibility of the regulatory autoinhibition process of the SMYD enzymes by a thorough computational exploration of their dynamic, energetic, and structural changes by using extended molecular dynamics simulations; normal mode analysis (NMA); and energy correlations. Three SMYD models (SMYD1-3) were used in this study. Our results showed an obvious hinge-like motion between the N- and C-lobes. Also, we identified interaction energy pathways within the 3D structures of the proteins, and hot spots on their surfaces that could be of particular importance for the regulation of their activities via allosteric means. These results can help in a better understanding of the nature of these promising drug targets; and in designing selective drugs that can interfere with (inhibit) the function of a specific SMYD member by disrupting its dynamical and conformational behaviour without disrupting the function of the entire SMYD proteins.     

大脑皮层内神经元集团的能量演变

在能量编码原理的基础上,利用哈密尔顿函数得到了大脑皮层内大规模神经元集群在阈下和阈上互相耦合时神经元电位变化的能量函数.根据神经电生理的实验数据得到了高斯白噪声条件下神经元电位活动的膜电位运动方程.研究结果表明：本文得到的膜电位的均值恰是先前已发表的膜电位运动方程的精确解.在这个基础上,还得到了神经元集群编码的哈密尔顿函数随时间的演变过程,即神经元集群随时间的能量演化过程的定量表达式.