多智能体车间调度系统研究

现在制造业所面临的动态需求使得其必须具有更加灵活的应变机制，这使得车间调度问题变得越来越复杂。本文采取多智能体系统技术（MAS）设计了一个包含四个智能体（agent）的多智能体车间调度系统，分别为车间调度智能体、任务分配智能体、车间资源智能体以及拍卖智能体。通过这四个智能体的通信、交互和合作，系统可以给出一个满足当前制造需求的调度最优结果。     

多智能体运输调度系统协商机制的研究

针对大型企业运输调度问题,采用多智能体技术,提出了一个多智能体运输调度系统模型,将汽车资源构造为具有自主能力的汽车智能体,从而提高了系统问题求解的能力,并对系统中多智能体之间的协商机制进行了探讨。     

基于递阶强化学习的多智能体AGV 调度系统

递阶强化学习是解决状态空间庞大的复杂系统智能体决策的有效方法。具有离散动态特性的AGV调度系统需要实时动态的调度方法，而具有MaxQ递阶强化学习能力的多智能体通过高效的强化学习方法和协作，可以实现AGV的实时调度。仿真实验证明了这种方法的有效性。     

基于多Agent柔性制造单元的生产调度研究

针对基于制造单元的作业车间的生产调度问题进行了研究,结合多代理的智能性、灵活性和遗传算法的智能优化能力,建立基于多智能体的柔性制造单元的作业车间的调度系统模型.然后,提出了集成多智能体和遗传算法的动态调度策略和调度协商机制;最后,应用此方法完成了常规调度和异常调度的仿真算例.结果表明所开发系统可以解决基于加工单元的制造...     

多智能体协作方法及其应用研究

将复杂系统分解成由多个智能体构成的合作多智能体系统，建立了多智能体系统的决策模型，能动态实时地计算每一时刻智能体的决策局势，适应环境的动态变化．采用多智能体方法对半导体生产进行调度，提高了半导体生产线设备的利用率，缩短了单位工件的加工时间．     

基于多智能体的动态车间调度系统

在分析车间生产调度特点的基础上,提出了基于多智能体的动态车间生产调度模型。把车间生产调度系统分为调度代理、任务代理和资源代理等。代理之间采用了基于改进的合同网的关系网模型,为解决车间加工动态调度问题提供了一种新的方法。     

基于多智能体的流程工业动态调度研究

根据流程工业某车间的生产过程,建立基于多智能体的生产调度系统模型,分析各智能体之间的关系,利用多智能体之间基于博弈论的协商机制,提出一个双边单议题多阶段的谈判模型,解决以工序流量或产品产量为目标的调度问题。对某隔膜烧碱生产线调度实例进行仿真,结果验证了该系统的可行性和有效性。     

概率驱动的动态多目标多智能体协同调度进化优化

在多智能体系统中,协作任务往往动态变化,且存在多个冲突的优化目标,因此动态多目标多智能体协同调度问题已经成为亟须解决的关键问题之一。针对动态环境下多智能体协同调度需求,提出了概率驱动的动态预测策略,旨在有效利用历史环境概率分布,预测决策解在新环境的概率分布,从而生成新的多智能体调度方案,实现调度算法在动态环境下的快速响应。具体来讲,设计了基于元素的概率分布表达,以表示解的构成元素在动态环境的适应性,并根据优化算法迭代最优解逐步更新概率分布以趋近实际分布;构建了基于融合的概率分布预测机制,考虑到环境变化的连续性和相关性,当环境变化时,通过融合历史概率分布预测新环境的概率分布,为新环境优化提供先验知识;提出了基于启发式的新解采样机制,结合概率分布和启发式信息,生成解方案以更新过时种群。将概率驱动的动态预测策略嵌入新型的多目标进化算法,获得概率驱动的动态多目标进化算法。在10个动态多目标多智能体协同调度问题实例上,实验结果表明,所提算法在解最优性和多样性上显著优于已有多目标进化算法,所提的概率驱动的动态预测策略能够提高多目标进化算法对动态环境的适应能力。     

智能运输调度系统求解机制研究与实现

运输调度问题模型类型多、结构复杂、求解工作量大,应用智能运输调度系统可提高运输调度工作效率和调度水平,降低物流运输成本。本文研究了智能运输调度系统的核心部件——智能求解机制。通过分析典型运输调度模型的结构特征,对模型类参数进行结构化归类及编码,提出一种面向智能运输调度系统的求解机制,重点研究了模型类的自动识别机制。本文提出的求解机制具有开放、可重构、智能建模、智能求解等特点,仿真分析和初步应用的效果令人满意。     

基于AGVs路径规划的物流智能调度系统设计与实现

为了解决现有物流调度系统低效缓慢、容错率低的问题,设计了基于自动导引运输车(AGV,automated guided vechicle)和路径规划优化算法的物流智能调度系统;系统搭配了AGV的物流调度硬件,又结合了路径规划理论,开发了基于Petri网络的智能路径规划算法;通过算法性能对比得知,路径规划算法设计了最优调度路径,确保了较高的准确率和工作效率;系统测试结果显示,基于AGVs路径规划的物流智能调度系统能够在各种物流环境或者库房基地完成调度任务,很好地解决了物流企业在忙碌期的繁杂调度问题;基于AGVs路径规划的物流智能调度系统提高了物流调度的自动化程度,保证了物流调度和道路运输的效率,有效推动了商业模式和市场规范的发展。     

ACE-RL-Checkers: decision-making adaptability through integration of automatic case elicitation,reinforcement learning,and sequential pattern mining

In agents that operate in environments where decision-making needs to take into account, not only the environment, but also the minimizing actions of an opponent (as in games), it is fundamental that the agent is endowed with the ability of progressively tracing the profile of its adversaries, in such a manner that this profile aids in the process of selecting appropriate actions. However, it would be unsuitable to construct an agent with a decision-making system based only on the elaboration of such a profile, as this would prevent the agent from having its “own identity,” which would leave the agent at the mercy of its opponent. Following this direction, this study proposes an automatic Checkers player, called ACE-RL-Checkers, equipped with a dynamic decision-making module, which adapts to the profile of the opponent over the course of the game. In such a system, the action selection process is conducted through a composition of multilayer perceptron neural network and case library. In this case, the neural network represents the “identity” of the agent, i.e., it is an already trained static decision-making module. On the other hand, the case library represents the dynamic decision-making module of the agent, which is generated by the Automatic Case Elicitation technique. This technique has a pseudo-random exploratory behavior, which allows the dynamic decision-making of the agent to be directed either by the opponent’s game profile or randomly. In order to avoid a high occurrence of pseudo-random decision-making in the game initial phases—in which the agent counts on very little information about its opponent—this work proposes a new module based on sequential pattern mining for generating a base of experience rules extracted from human expert’s game records. This module will improve the agent’s move selection in the game initial phases. Experiments carried out in tournaments involving ACE-RL-Checkers and other agents correlated to this work, confirm the superiority of the dynamic architecture proposed herein.     

基于MAS的企业GDSS设计

由于企业决策支持系统GDSS的分布性和协同性,采用基于多层次MAS的企业GDSS可提高决策效率、缩短决策周期。本文讨论了以多重层次结构设计的系统的通信方式、总体结构、功能划分、动态特性,设计了基于多个agent群的企业GDSS结构模型,分析了各agent群的结构和实现,最后给出了系统的实现过程。     

Multi-Agent Dynamic Area Coverage Based on Reinforcement Learning with Connected Agents

Dynamic area coverage with small unmanned aerial vehicle (UAV) systems is one of the major research topics due to limited payloads and the difficulty of decentralized decision-making process. Collaborative behavior of a group of UAVs in an unknown environment is another hard problem to be solved. In this paper, we propose a method for decentralized execution of multi-UAVs for dynamic area coverage problems. The proposed decentralized decision-making dynamic area coverage (DDMDAC) method utilizes reinforcement learning (RL) where each UAV is represented by an intelligent agent that learns policies to create collaborative behaviors in partially observable environment. Intelligent agents increase their global observations by gathering information about the environment by connecting with other agents. The connectivity provides a consensus for the decision-making process, while each agent takes decisions. At each step, agents acquire all reachable agents’ states, determine the optimum location for maximal area coverage and receive reward using the covered rate on the target area, respectively. The method was tested in a multi-agent actor-critic simulation platform. In the study, it has been considered that each UAV has a certain communication distance as in real applications. The results show that UAVs with limited communication distance can act jointly in the target area and can successfully cover the area without guidance from the central command unit.     

基于Agent的网络分布式动态防护体系

从系统科学的观点出发，提出了网络分布式动态防护体系的概念，研究了其基于系统工程与面向Agent的设计思想和方法。据此设计了基于Agent的分布式动态防护体系，论述了数据获取、信息处理、决策响应与辅助等Agent的功能原理及其动态协作关系。该体系具有本质的智能性和动态性，能有效检测并阻断多种入侵，实现了分布动态防护。     

基于Q-learning的不确定环境BDI Agent最优策略规划研究

BDI模型能够很好地解决在特定环境下的Agent的推理和决策问题,但在动态和不确定环境下缺少决策和学习的能力。强化学习解决了Agent在未知环境下的决策问题,却缺少BDI模型中的规则描述和逻辑推理。针对BDI在未知和动态环境下的策略规划问题,提出基于强化学习Q-learning算法来实现BDI Agent学习和规划的方法,并针对BDI的实现模型ASL的决策机制做出了改进,最后在ASL的仿真平台Jason上建立了迷宫的仿真,仿真实验表明,在加入Q-learning学习机制后的新的ASL系统中,Agent在不确定环境下依然可以完成任务。     

SYROCO: A novel multi-agent shop-floor control system

Shop-floor control is known to be a hard problem because it must supervise manufacturing operations execution according to plans, respect delays and deal with real-time system perturbations. Modern shop-floor control systems must be reactive, i.e., be able to quickly and timely react to perturbations, be they external or internal perturbations to the system to be controlled.This paper proposes a novel approach to shop-floor control. Especially, its aim is to solve dynamic production control problems in real-time (due to workstation breakdowns, urgent orders...), to automate as much as possible the control process in order to adapt the system to production plan modifications and to rationalize decision-making by a means of strong hierarchical structure.To achieve this, the system is based on a two-fold hybrid multi-agent platform. First, control is hierarchically distributed and decision-making is centralized, thus this type of system mediates between centralized and hierarchical architecture types. Centralization allows to avoid the competition between agents for solving a problem while hierarchical distribution allows each agent to take care of only one product. Second, a complete schedule is completed at the beginning of the process, but it can be partially (or totally) modified during the process. Thus, significant gains in terms of response times and reactivity capabilities are obtained thanks to this hybrid approach.     

Framework of agent-based intelligence system with two-stage decision-making process for distributed dynamic scheduling

The advent of multiagent systems, a branch of distributed artificial intelligence, introduced a new approach to problem solving through agents interacting in the problem solving process. In this paper, a collaborative framework of a distributed agent-based intelligence system is addressed to control and resolve dynamic scheduling problem of distributed projects for practical purposes. If any delay event occurs, the self-interested activity agent, the major agent for the problem solving of dynamic scheduling in the framework, can automatically cooperate with other agents in real time to solve the problem through a two-stage decision-making process: the fuzzy decision-making process and the compensatory negotiation process. The first stage determines which behavior strategy will be taken by agents while delay event occurs, and prepares to next negotiation process; then the compensatory negotiations among agents are opened related with determination of compensations for respective decisions and strategies, to solve dynamic scheduling problem in the second stage. A prototype system is also developed and simulated with a case to validate the problem solving of distributed dynamic scheduling in the framework.     

基于大数据流的Multi-Agent系统模型研究

在智能决策支持系统(IDSS)中,由于许多推理模型和方法以巨大的数据量为基础,决策响应速度成为系统的瓶颈。结合软件开发实际,提出了一种基于速度优化的Multi-Agent模型,将系统Agent分为智能交互界面Agent、数据分析处理Agent、数据访问控制Agent三类,通过各Agent的分工与协作来实现系统数据的快速交互;并在ERP采购成本分析子系统中进行建模研究,结果表明该模型能大大缩短系统决策响应时间。     

Bargaining on an Internet Agent-based Market: Behavioral vs. Optimizing Agents

In this paper, we analyze an Internet agent-based market where non-cooperative agents using behavioral rules negotiate the price of a given product in a bilateral and sequential manner. In this setting, we study the optimal decision-making process of a buying agent that enters the market. Our approach is based on Negotiation Analysis (Raiffa, 1982; Sebenuis, 1992) and we consider that the optimizing buying agent maximizes her discounted expected utility using subjective probabilities. The optimal decision-making process of the buying agent is treated as a stochastic control problem that can be solved by dynamic programming. Three types of behavioral agents are studied, namely conceder agents, boulware agents and imitative agents. A set of simulations is undertaken in order to predict the average outcome in a negotiation process for different parameters of the optimizing buying agent and for the three possible selling agents' behaviors. Finally, we compare the performance of the optimizing agent with that of behavioral buying agents.     

基于CNP的多Agent车间调度系统设计与实现

Agent具有智能性、自治性及合作能力等许多优良的特性,为解决现代制造系统的车间敏捷调度问题提供了一条新的有效途径。在提出的调度系统体系结构的基础上,基于合同网协议（Contract Net Protocol,CNP）,应用KQML语言和采用CORBA通信机制,设计了多Agent车间调度系统（Multi-agents Scheduling System,MASS）,具有一定的通用性和可扩充性．实验结果表明该调度系统的优越性。