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。     

A modelling language for cooperative plans in highly dynamic domains

Cooperative behaviour is one of the challenges most pronounced in the RoboCup Middle Size League. Especially the dynamic nature of the domain, which calls for swift adaptation by each robot and the team as a whole, is a distinctive property of the league. The ability to establish highly responsive teamwork while facing unreliable communication and sensory noise is a key to successful soccer teams. Moreover, modelling such responsive, cooperative behaviour is difficult. In this work, we specify a novel model for cooperative behaviour geared towards highly dynamic domains, focussing on the language syntax and semantics. In our approach, agents estimate each other’s decision and correct these estimations once they receive contradictory information. We provide a comprehensive approach for agent teamwork featuring intuitive modelling capabilities for multi-agent activities, abstractions over activities and agents, and a clear operational semantics. Moreover, we briefly present a graphical modeling tool for cooperative strategies, which is based directly on the theory laid out, together with a practical framework for executing said strategies. We show experimentally the responsiveness and coherence of the resulting team play.     

基于知识情感等级BDI主体的决策行为模型研究

为了将知识、信念、愿望和意图以及害怕、焦虑和自信对决策行为的影响的强烈程度进行形式化,把无穷值的卢卡斯维茨逻辑的真值取值范围从[0,1]扩展到[-1,1]。知识情感等级BDI主体的决策行为通过添加了具体条件的不同背景的不同测度来决定;知识情感等级BDI主体模型清晰地表示了主体的知识状态、心智状态和情感状态的不确定性;此模型可以轻易地向其他类型的主体进行推广。在给出了知识情感等级BDI模型的语言、语义以及此模型的不同背景之间的相互关系之后,对知识情感等级BDI主体的军事决策行为进行了实例分析。此研究旨在为分布式人工智能和军事仿真提供形式支持。     

Towards True Dynamic Workflow for Emergency Response

Emergency management is a process by which all individuals, groups, and communities manage hazards in an effort to avoid or ameliorate the impact of disasters resulting from the hazards. Emergency response workflow is dynamic because there are lots of uncertainties with the course of hazard development and rescue effort. Existing dynamic workflow modeling technologies are not su±cient to describe the complex emergency response processes which are context aware and data-driven. In this paper, we propose an intelligent agent based approach to supporting the emergency response process management. The approach integrates BDI (Belief-Desire-Intention) agents with WIFA workflow model, which was developed in our previous work, to a powerful tool for truly dynamic workflow modeling and enactment. A BDI agent is an intelligent agent. Beliefs represent the informational state of the agent - in other words its beliefs about the world. Desires (or goals) represent the motivational state of the agent. They represent objectives or situations that the agent would like to accomplish or bring about. Intentions represent the deliberative state of the agent: what the agent has chosen to do. Intentions are desires to which the agent has to some extent committed. Workflows represent sequences of actions that an agent can perform to achieve one or more of its intentions. Based on this approach, we developed an emergency response training tool which is customizable for individual organization use and scalable to incident response settings from rural to urban domestically and foreign outposts for military applications, and can operate at a holistic exercise level.     

WDM环形自愈网

简要介绍了WDM环形自愈网的特点、故障的判定、隔离以及环形自愈网自激产生的条件及解决的办法     

整合Agent与语义Web服务

目前的语义web服务方法和标准提供了很多由Agent平台操纵的基础设施，这有利于Agent与语义web服务的结合。本文分析了语义web服务与Agent之间的关系，提出Agent的主要角色是用来封装用户的意图，协调用户的目标，并最终调用web服务.我们利用当前的Agent技术与语义web服务技术，设计出自己的平台，整合了Agent BDI模型与语义Web服务。     

一种无线传感器网络的多Agent系统模型

针对无线传感器网络缺乏普遍的理论模型,提出一种多Agent系统模型,包括形式化语言、模型、语义以及相应的公理和模型约束.该模型将无线传感器网络抽象为由具有特定信念、期望、意图和能力等认知成分的Agent组成的认知系统,所有这些认知成分构成多Agent系统认知模型.本文将为独立于内部结构和具体实现来理解、分析和预测无线传感器网络行为提供形式化的理论基础和分析工具.     

基于Agent的Web应用测试研究

随着Web应用技术的发展,产生了一些新的技术特点,如动态行为、多种描述语言、新的数据处理机制、执行的不确定性等,这给软件测试者提出了严峻的挑战。为适应这些新特点,提出了一种基于agent的Web应用测试方法,借助Be-liefs-Desires-Intentions(BDI)模型生成agent,结合控制流图和状态树对程序结构分析,获得测试序列集。实验结果显示测试序列能够在agent中实现,并体现出方法的灵活性和可扩展性。     

多Agent的并行思智算法

给出了多Agent的并行思智算法,同时针对应用领域,提出了面向过程的Agent并行思智算法和面向任务的A-gent并行思智算法,通过实例对所提出的算法进行了验证。说明该算法是有意义的。