基于蒙特卡洛树搜索的仿真足球防守策略研究

针对Robocup仿真足球比赛中本位点区域化跑位的局限性,在三角剖分的阵型设计基础上将蒙特卡洛树搜索算法引入2D仿真中,将球员智能体在球场上的状态定义为博弈树节点,将双方球员的动作选择视为节点间的状态转移,对于球队的防守任务建立蒙特卡洛树模型。利用极坐标方式对球场进行区域分割,结合Q学习与蒙特卡洛树搜索中的信心上限树算法(Upper Confidence Bound Apply to Tree of Monte Carlo)进行球队训练,将训练结果的动作评估值用于优化比赛代码,使得球队的防守能力得到了较大程度的提升。     

RoboCup中基于动作序列模型的动作决策

RoboCup机器人足球比赛是当前人工智能领域的一个研究热点,其目的在于为多智能体系统提供一个标准的研究平台.为了让RoboCup仿真比赛中球员智能体实时地作出合理的动作决策,提出一种基于动作序列模型的决策机制,通过对球员智能体的动作空间分解、建立动作序列并对动作序列进行评价,而让智能体选择出当前最优的动作执行.仿真结果表明应用这种决策机制提高了智能体对环境的适应性.     

多智能体系统的宏观策略及其微观控制

在多智能体系统中,用宏观策略确定整体目标,用微观控制实现其目标,其间是通过多智能体之间的协作完成的。用一个仿真足球队作为多智能体系统的研究对象,首先,从整体方面考虑,通过用集合的方式定义了球队的战术、形势、阵型和球员的状态等,并通过几者之间的关系描述了球队的宏观策略;其次,从局部方面考虑,根据已制定的宏观策略,分别通过用静态和动态的控制方式,定义了每一个智能体的动作选择机制。仿真实验证明了动态控制的有效性。     

基于多智能体协同的角色互换策略的研究应用

多智能体协同技术是人工智能领域的一个重要分支。机器人足球比赛为多智能体协同技术的研究提供了一个测试平台,仿真机器人足球比赛球员Agent具有号码属性与角色属性。文中以仿真机器人足球比赛中的球员Agent为研究对象,利用在线教练机制对球员Agent进行建模,提出了对手角色识别策略以及基于多智能体协同的球员Agent动态角色互换策略。在Agent2D底层中编程实现,与某球队进行测试,胜率大大增加,结果表明了该算法的有效性,该算法可提高球队的进攻能力。     

智能体视觉策略在RoboCup中的设计

智能体对环境的认识是其进行决策的重要依据。在机器人足球仿真比赛(RoboCup)中,视觉感知是智能体获得信息、构建世界模型的主要途径。针对仿真比赛中球员智能体进行决策时信息不准确的问题,结合优先级和可信值对智能体的视觉策略进行了设计。根据对观察目标需求的紧迫程度动态地指定观察目标的优先级,然后结合世界模型维护的观察目标的可信值生成各个视觉角度的评价值,通过搜索评价值最大的视觉角度获得优化的视觉信息。实验结果表明这种视觉策略使球员动作的执行更加可靠,增强了球队的整体性能。     

多智能体强化学习及其在足球机器人角色分配中的应用

足球机器人系统是一个典型的多智能体系统, 每个机器人球员选择动作不仅与自身的状态有关, 还要受到其他球员的影响, 因此通过强化学习来实现足球机器人决策策略需要采用组合状态和组合动作. 本文研究了基于智能体动作预测的多智能体强化学习算法, 使用朴素贝叶斯分类器来预测其他智能体的动作. 并引入策略共享机制来交换多智能体所学习的策略, 以提高多智能体强化学习的速度. 最后, 研究了所提出的方法在足球机器人动态角色分配中的应用, 实现了多机器人的分工和协作.     

基于换位思考模型的多智能体协作研究及在RoboCup中的应用

机器人世界杯(RoboCup)是一个典型的多智能体系统.为了提高多智能体协作的效率,提出一种新的基于换位思考模型的多智能体协作研究方法.首先,教练智能体获取仿真比赛环境中球员智能体的无噪音信息,对所有队友智能体建模;然后,应用高斯分布计算队友智能体的当前行为模式,并把当前模式反馈给仿真环境;最后,球员智能体根据换位思考模型计算得到的模式做出相应决策.该模型已经应用于HfutEngine2D仿真球队中,在RoboCup仿真比赛中获得2007年中国公开赛亚军,2008年机器人世界杯第7的好成绩.     

在机器人足球中利用遗传算法进行多智能体学习

本文通过对仿真机器人足球的研究的介绍，阐述了利用遗传算法对多智能体机器学习的研究。每个球员作为一个智能体，通过进化训练，不断地学习，使之能够作出当前状态下最优的动作。文中将以FIRA仿真机器人足球赛为例，论述战术动作的在线学习。     

自适应遗传算法和RBF网络在传球中的应用

机器人足球仿真比赛系统是研究人工智能的优秀平台,借助平台,将智能算法应用到仿真球队的相关策略设计中,通过球队之间的比赛以验证算法的可行性.传球是球员的基本动作之一,设计的好与否直接影响着球队的整体实力.由于仿真比赛环境是一个实时、动态、有干扰的环境,难以对传球动作建立精确的物理模型.为提高球队近似物理模型的传球成功率,提出了一种新的传球方法,即基于自适应遗传算法的RBF神经网络传球方法.用自适应遗传算法优化RBF神经网络的结构参数,通过优化,提高了网络的学习能力和全局搜索效率.仿真结果表明,经过自适应遗传算法优化的RBF神经网络的传球成功率得到了很大提高.     

RoboCup中传球策略的研究与实现

该文针对RoboCup仿真2D球队设计中的11个智能体相互间的合作和协调问题,结合整体的规划决策与每个智能体的动作模块的关系,根据BP神经网络的传球速度,提出了基于角色、基于区域及其基于概率判断的传球策略,并指出了三者之间的协调性,用于建立场上关键信息元素和决策之间有效的关系。     

Plan coordination by revision in collective agent based systems

In order to model plan coordination behavior of agents we develop a simple framework for representing plans, resources and goals of agents. Plans are represented as directed acyclic graphs of skills and resources that, given adequate initial resources, can realize special resources, called goals. Given the storage costs of resources, application costs of skills, and values of goals, it is possible to reason about the profits of a plan for an agent. We then model two forms of plan coordination behavior between two agents, viz. fusion, aiming at the maximization of the total yield of the agents involved, and collaboration, which aims at the maximization of the individual yield of each agent. We argue how both forms of cooperation can be seen as iterative plan revision processes. We also present efficient polynomial algorithms for agent plan fusion and collaboration that are based on this idea of iterative plan revision. Both the framework and the fusion algorithm will be illustrated by an example from the field of transportation, where agents are transportation companies.     

A multi-agent architecture for control of AGV systems

Agent is an autonomous, computational entity that can be viewed as perceiving its environment and acting upon it. Agents are event-driven objects that can be integrated in automated manufacturing environments to control certain tasks. In this paper a set of agents (a multi-agent system) is introduced to control an automated manufacturing environment. The architecture includes functions at the manufacturing cell level, materials handling and transport level, and factory scheduling level. Communication between these agents is accomplished by using a relational database (blackboard system). The relational database also integrates the requirements of a manufacturing execution system within the multi-agent task structure, which is unique to this architecture. Manufacturing cell and scheduling agents have been previously described in the literature. Here we focus our attention on the functions of the agents of the transport system, which is composed of a set of AGVs.     

Incident Command Skills in the Management of an Oil Industry Drilling Incident: a Case Study

The successful management of a complex, hazardous event in many domains demands a high level of incident command skills. In the oil and gas exploration and production industry, these skills were required by members of an Incident Management Team (IMT) established to respond the failure of a drilling riser in the Gulf of Mexico. When an incident occurs, members of an industrial IMT form an interdisciplinary, interdependent, but ad‐hoc team. As actual experience of dealing with major incidents of this nature is relatively rare, IMT members have to rely on emergency exercises in training, along with existing domain‐specific knowledge. Following a serious incident on an offshore drilling rig, semi‐structured interviews with the on‐shore strategic and tactical level IMT members (n=7) were conducted. These interviews have resulted in the identification and definition of incident command skills for members of an industrial IMT, namely decision making, situation awareness, communication, leadership, and teamwork, all of which can be affected by stress, as well as organisational factors that influenced the outcome of the incident. Limitations in current incident management training were identified, namely the need for specific incident command skills training. A framework is suggested around which specific incident command skills training can be structured. Key learnings from this case study are also presented which can provide guidance for the training and preparation of industrial incident management teams.     

Unplanned effects of intelligent agents on Internet use: a social informatics approach

This paper instigates a discourse on the unplanned effects of intelligent agents in the context of their use on the Internet. By utilizing a social informatics framework as a lens of analysis, the study identifies several unanticipated consequences of using intelligent agents for information- and commerce-based tasks on the Internet. The effects include those that transpire over time at the organizational level, such as e-commerce transformation, operational encumbrance and security overload, as well as those that emerge on a cultural level, such as trust affliction, skills erosion, privacy attrition and social detachment. Furthermore, three types of impacts are identified: economic, policy, and social. The discussion contends that economic impacts occur on the organizational level, social effects transpire on a cultural level, and policy impacts take place on both levels. These effects of the use of intelligent agents have seldom been predicted and discussed by visionaries, researchers, and practitioners in the field. The knowledge of these unplanned outcomes can improve our understanding of the overall impacts that innovative agent technologies may potentially have on organizations and individuals. Subsequently, this may help us develop better agent applications, facilitate the formulation of appropriate contingencies, and provide impetus for future research.     

Survey on Computer Vision for UAVs: Current Developments and Trends

During last decade the scientific research on Unmanned Aerial Vehicless (UAVs) increased spectacularly and led to the design of multiple types of aerial platforms. The major challenge today is the development of autonomously operating aerial agents capable of completing missions independently of human interaction. To this extent, visual sensing techniques have been integrated in the control pipeline of the UAVs in order to enhance their navigation and guidance skills. The aim of this article is to present a comprehensive literature review on vision based applications for UAVs focusing mainly on current developments and trends. These applications are sorted in different categories according to the research topics among various research groups. More specifically vision based position-attitude control, pose estimation and mapping, obstacle detection as well as target tracking are the identified components towards autonomous agents. Aerial platforms could reach greater level of autonomy by integrating all these technologies onboard. Additionally, throughout this article the concept of fusion multiple sensors is highlighted, while an overview on the challenges addressed and future trends in autonomous agent development will be also provided.     

Microconsistency in Simple Empirical Agent-Based Financial Models

Models with small numbers of agents have recently been simplified for direct empirical estimation. Parameters are estimated at the macro level to get a best fit to the data. However, little analysis is done at the micro level to examine the choices made by agents for forecasting rules. This paper explores one of these recent models from the standpoint of micro agent behavior. It is shown that at the fitted forecasting rules, agents would prefer deviating to other nearby rules. The simple two type model is then compared with several multi-type models allowing for agents to use a broader set of rules. This can impact the dynamics of the generated time series, but it also may not if one takes the parameter estimates of the original model as an exogenous restriction on a reasonable support for the forecasting rules. This result emphasizes that these models may be imposing some hidden micro assumptions about agent behavior.

     

Assessment with computer agents that engage in conversational dialogues and trialogues with learners

This article describes conversation-based assessments with computer agents that interact with humans through chat, talking heads, or embodied animated avatars. Some of these agents perform actions, interact with multimedia, hold conversations with humans in natural language, and adaptively respond to a person’s actions, verbal contributions, and emotions. Data are logged throughout the interactions in order to assess the individual’s mastery of subject matters, skills, and proficiencies on both cognitive and noncognitive characteristics. There are different agent-based designs that focus on learning and assessment. Dialogues occur between one agent and one human, as in the case of intelligent tutoring systems. Three-party conversations, called trialogues, involve two agents interacting with a human. The two agents can take on different roles (such as tutors and peers), model actions and social interactions, stage arguments, solicit help from the human, and collaboratively solve problems. Examples of assessment with these agent-based environments are presented in the context of intelligent tutoring, educational games, and interventions to help struggling adult readers. Most of these involve assessment at varying grain sizes to guide the intelligent interaction, but conversation-based assessment with agents is also currently being used in high stakes assessments.     

A Resource Logic for Multi-Agent Plan Merging

In a multi-agent system, agents are carrying out certain tasks by executing plans. Consequently, the problem of finding a plan, given a certain goal, has been given a lot of attention in the literature. Instead of concentrating on this problem, the focus of this paper is on cooperation between agents which already have constructed plans for their goals. By cooperating, agents might reduce the number of actions they have to perform in order to fulfill their goals. The key idea is that in carrying out a plan an agent possibly produces side products that can be used as resources by other agents. As a result, an other agent can discard some of its planned actions. This process of exchanging products, called plan merging, results in distributed plans in which agents become dependent on each other, but are able to attain their goals more efficiently. In order to model this kind of cooperation, a new formalism is developed in which side products are modeled explicitly. The formalism is a resource logic based on the notions of resource, skill, goal, and service. Starting with some resources, an agent can perform a number of skills in order to produce other resources which suffice to achieve some given goals. Here, a skill is an elementary production process taking as inputs resources satisfying certain constraints. A service is a serial or parallel composition of skills acting as a program. An operational semantics is developed for these services as programs. Using this formalism, an algorithm for plan merging is developed, which is anytime and runs in polynomial time. Furthermore, a variant of this algorithm is proposed that handles the exchange of resources in a more flexible way. The ideas in the paper will be illustrated by an example from public transportation.     

A measure of cross-training benefit versus job skill specialization

Given ever-higher labor costs, organizations should periodically assess the match of personnel skills and quantities with required duties. Consolidating similar functional specialties can improve efficiency by increasing staffing for high-demand jobs, or by identifying areas where staff may be reduced. However, such consolidation activities are often done anecdotally, and can potentially overlook successful skill pairings. We propose a model that enables an objective, repeatable skills consolidation assessment process. Our model—a cost/benefit ratio—identifies skill pairings which are likely to merge successfully, by comparing the costs of training to the benefits of increased staffing level efficiencies for these jobs.     

Integrating skills into multi-agent systems

Currently, an important topic of robotic research is the design and development of multi-agent robot systems (MASs). In these a number of autonomous robots cooperate and coordinate themselves in order to pursue given goals. The agents of an MAS not only have to work autonomously or in cooperation with other agents, but in dynamic, relatively unstructured environments. Therefore, the agents require agent-specific but flexible skills to cope with their tasks and the environment's variability. On the other hand, the actions to be performed by agents in an MAS have to meet certain requirements imposed by the MAS's structure. The representation of actions has to support planning, inter-agent communication, task negotiation etc. In this paper, we describe a method of combining the agent-specific nature of skills with the requirements for a general action knowledge representation inherent to MASs, by presenting elementary operations (EOs) that provide an appropriate interface.