文章主要分为两个部分：多Agent分类学，以及多Agent的架构   2005 4 20

1、             为什么要使用Multi Agent Teamwork？

I、               如果不同的组织或者人，他们有着不同甚至是矛盾的目标而且带有不同属性的信息，那么用多Agent系统来处理它们的交互。（if there are different people or organizations with different (possibly conflicting) goals and proprietary information, then a multi agent system is needed to handle their interactions.）

II、            健壮性（robustness）是多Agent系统的另外一个优点，由于它有很多Agent的冗余。

III、          容错性好。If control and responsibilities are sufficiently shared among different agents, the system can tolerate failures by one or more of the agents.

IV、          可扩展性好。Another benefit of multi agent systems is their scalability. Since they are inherently modular, it should be easier to add new agents to a multi agent system than it is to add new capabilities to a monolithic system.

V、      可以将任务分成多个子任务分别交给Agents运行，可以用于并行计算。

2、              分类学：（Taxonomy）

猜想：黑盒子可以被看作是Agent？

在此模型中：

An agent can be perceives as being an autonomous entity able to rationally balance pro-active (i.e. goal-driven) and reactive behavior.

Agents are situated in an environment. The concepts of action and percept are significant since they form the interface between the agent and its environment. Agents are pro-active, thus the concept of goals is crucial. Agents are reactive. In order to be reactive an     agent must recognize significant things when they happen in order to respond to them. These "significant occurrences" are termed events. Agents are typically situated in rapidly changing environments where the agents have a limited view of the environment. Thus the concepts of plans (as a library of partial recipes for achieving particular goals, or reacting to particular events) and of beliefs are useful. （有一点点疑问：percept是如何与外界环境进行交互的呢？是Agent搜集证据的功能吗？如此一来，Percepts影响它们的观点，而Action是Agent影响Environment的唯一手段。我们的系统能做到这样智能吗？或者，我们怎样才能做到这样智能呢？）

3、             BDI: (Belief, Desire, Intention)]模型

（有关BDI的信息更多在Anan S Rao , Michael P Georgeff  , “BDI  Agent : From Theory to Practice”, Proceedings of First International Conference of Multi Agent Systems (ICMAS-95), San Francisco , USA June 95）

The BDI [1] model is one of the most popular agent architectures.

• Beliefs: Information about the environment; (Agent对环境的看法，在推理机中应该是事实的集合。对环境中的物质的确认或者否认。)
• Desires: Objectives to be accomplished, possibly with each objective's associated priority/payoff; （和目标有什么区别？？在推理机中，应该是推理目标。）
• Intentions: The currently chosen course of action; （在推理机中似乎是推理机的选择规则的原则。）
• Plans: Means of achieving certain future world states. Intuitively, plans are an abstract specification of both the means for achieving certain desires and the options available to the agent. Each plan has (i) a body describing the primitive actions or sub-goals that have to be achieved for plan execution to be successful; (ii) an invocation condition which specifies the triggering event (Some events are considered as goal-events.), and (iii) a context condition which specifies the situation in which the plan is applicable. （在推理机中应该是推理的规则集合，虽然其本身非常非常地简陋，呵呵）（主要的三个方面分别是指：描述了一个结果目标，或者是一组过程。触发过程，用于事件触发，对于推理机而言，就是前件为真的时候，……这个前件就应当算是触发的事件。上下文，这个我觉得推理机没有这么细粒度的东东，似乎后两个合在一起，算是前件的作用吧！）

4、BDI: (Belief, Desire, Intention)]模型实现：

Beliefs are treated as a relational database (i.e. a collection of predicates) or an arbitrary data structure（推理机中就是事实库）； goals/desires are treated as an event type（反向推理机？由推理目标开始搜索）; and intentions are realized simply as an executing plan.（规则库） A plan typically has an invocation condition, context condition, fail/success actions, plan body, and maintenance condition. （总体来说，也许将推理机与Agent相比不是很适当。Agent应该比推理机有更多的智能。推理机也不像Agent有那么多的自治性）

5、  ALLIANCE Architecture（下面开始讲述的似乎是Robot作为Agent的多Agent架构，与项目关系不大，所以我也不打算再看了，- - ）