A blackboard approach to modeling expertise in corporate settlement decisions*

Abstract: The SKADE system models expertise in corporate settlement decisions using the blackboard approach. The full model has four knowledge sources: General Counsel, Attorney, Manager and Insurance Adjuster. The combined expertise from each of these is required to make the settlement decision. A control component in the model coordinates the activities of the various knowledge sources. Based on the latest data entries on the blackboard, the control selects and executes the next knowledge source. The blackboard model reproduces the experts' opportunistic reasoning processes by the interaction between the various knowledge sources. The results of analyses of a hypothetical case through a series of experiments with the SKADE system indicate that the blackboard is an appropriate model for development of multiple cooperative expert systems in the settlement decision domain. Compared to straight rule-based models, this blackboard provides more efficient problem solving. The initial success with the blackboard model suggests that further work needs to be done to see whether more complex models can be built to incorporate a broader range of determinants of settlement decisions.     

Using grate to build cooperating agents for industrial control

Communities of cooperating problem solvers have recently begun to emerge as a paradigm for overcoming the complexity of building large software systems in the area of process control. Each agent is capable of solving some problems by itself, but its power can be extended by sharing information and tasks with others. Also, more importantly, the community as a whole exhibits some desirable problem solving characteristics (eg graceful degradation of performance, robustness, etc.) as well as offering the opportunity of connecting and integrating existing problem solvers. GRATE is a general purpose cooperation environment which enables groups of interacting problem solvers to be built for the domain of industrial control. It has been applied to two real-world problems in this area: electricity transport management and diagnosis in a particle accelerator beam controller. We reflect upon GRATE's functional architecture, its underlying principles and the insights gained during this process.     

Bipartite tracking of homogeneous and heterogeneous linear multi-agent systems

In this paper, we consider bipartite tracking of linear multi-agent systems with a leader. Both homogeneous and heterogeneous systems are investigated. The communication between agents is modelled by a directed signed graph, where the negative (positive) edges represent the antagonistic (cooperative) interactions among agents. Linear Quadratic Regulator (LQR)-based approach is used to derive the distributed protocol for the follower agent to achieve bipartite tracking of the leader. It is shown that solving the bipartite tracking problem over the structurally balanced signed graph is equivalent to solving the cooperative tracking problem over a corresponding graph with nonnegative edge weights. This bridges the gap between the newly raised bipartite tracking problem and the well-studied cooperative tracking problem. Three novel control protocols are proposed for both cooperative and bipartite output tracking of heterogeneous linear multi-agent systems. Numerical examples are given to show the effectiveness of our control protocols.     

Trends in cooperative distributed problem solving

The authors present an overview of cooperative distributed problem solving (CDPS), an emerging research area that combines aspects of AI (artificial intelligence) and distributed processing. CDPS can be used to study how a loosely coupled network of sophisticated problem-solving nodes can solve a complex problem which consists of a set of interdependent subproblems. Subproblems arise because of spatial, temporal, and functional distribution of data, knowledge, and processing capabilities. Application areas include distributed interpretation, distributed planning and control, cooperating expert systems, and computer-supported human cooperation. The authors survey the important approaches and empirical investigations that have been developed. The approaches covered include negotiation, functionally accurate cooperation, organizational structuring, multiagent planning, sophisticated local control, and theoretical frameworks     

Voice Loops as Coordination Aids in Space Shuttle Mission Control

Voice loops, an auditory groupware technology, are essential coordination support tools for experienced practitioners in domains such as air traffic management, aircraft carrier operations and space shuttle mission control. They support synchronous communication on multiple channels among groups of people who are spatially distributed. In this paper, we suggest reasons for why the voice loop system is a successful medium for supporting coordination in space shuttle mission control based on over 130 hours of direct observation. Voice loops allow practitioners to listen in on relevant communications without disrupting their own activities or the activities of others. In addition, the voice loop system is structured around the mission control organization, and therefore directly supports the demands of the domain. By understanding how voice loops meet the particular demands of the mission control environment, insight can be gained for the design of groupware tools to support cooperative activity in other event-driven domains.     

When client/server isn't enough: coordinating multiple distributedtasks

Computing in a distributed environment for multitasked cooperative work is a promising area that presents many coordination issues. Our prototype system implements a three-layer architecture to provide greater control and flexibility in the distributed multitasking environment. The architecture includes a groupware server, application servers, and clients. The architecture can be further refined to provide more flexible control of activities. More applications, such as group calendaring and participative design can also be studied to find their idiosyncratic coordination needs and to elaborate the division of labor among different servers and clients     

语义Web中开放知识服务体系的研究

WWW是信息时代的重要标志。基于WWW的信息管理系统不仅要能运行在不同的平台上、分布的信息网络中,而且还能提供通用的平台与大量的、独立的、多类型的数据源和应用程序进行交互。开放知识服务体系OKSA就是为实现这一目标而提出的,在开放的Web资源环境中,建立动态的、跨平台的虚拟知识环境,使得人们能够获取、发布、共享和管理各种Web资源,并向用户提供按需的知识服务以支持协同工作、问题求解和决策支持等。     

Integrating multiple paradigms within the blackboard framework

The complexity and diversity of real world applications have forced researchers in the AI field to focus more on the integration of diverse knowledge representation and reasoning techniques for solving challenging, real world problems. Our development environment, BEST (Blackboard based Expert Systems Toolkit), is aimed to provide the ability to produce large scale, evolvable, heterogeneous intelligent systems. BEST incorporates the best of multiple programming paradigms in order to avoid restricting users to a single way of expressing either knowledge or data. It combines rule based programming, object oriented programming, logic programming, procedural programming and blackboard modelling in a single architecture for knowledge engineering, so that the user can tailor a style of programming to his application, using any or arbitrary combinations of methods to provide a complete solution. The deep integration of all these techniques yields a toolkit more effective even for a specific single application than any technique in isolation or collections of multiple techniques less fully integrated. Within the basic, knowledge based programming paradigm, BEST offers a multiparadigm language for representing complex knowledge, including incomplete and uncertain knowledge. Its problem solving facilities include truth maintenance, inheritance over arbitrary relations, temporal and hypothetical reasoning, opportunistic control, automatic partitioning and scheduling and both blackboard and distributed problem solving paradigms     

搅拌设备化工预设计专家系统的黑板系统结构

传统的手工设计混合设备的方法十分耗时且容易出错,因此实现设计的自动化和智能化是非常用意义的开发了搅拌设备化工预设计专家系统系统。详细介绍了专家系统的结构,系统采用两层黑板结构模型和多种知识源相结合的策略,来处理解决复杂的协同问题。知识源包括设计规则库、设计公式库和机械设备标准库,内部黑板主要是为规则库的推理机存储信息服务,而全局黑板系统则是整个系统的数据共享和信息交换中心,并采用层次框架结构进行表达,将人工智能技术与普通设计程序相结合,可以在设计过程为用户提供系统的帮助和指导,来实现搅拌设备设计的自动化和智能化。     

基于协作的协同设计过程控制对象知识建模技术

在分析协同设计领域问题的协作求解模式基础上，分析了协同设计领域问题求解的过程控制对象，提出了协同设计领域问题求解过程控制对象的多层次协作求解机制。并以领域问题协作求解、业务处理的过程控制以及领域控制知识的处理过程为核心，构建基干协作的协同设计过程控制对象的知识处理模型。最后以活动框架的业务处理过程控制为背景，讨论了协同设计领域问题求解过程控制对象的知识处理算法及其程序实现过程。     

渗碳专家系统中的多专家求解问题的研究

本文研究了在渗碳专家系统中的问题求解策略，为了避免系统求解的主观性和片面性，提出了多黑板系统，例如问题黑板，辩论择优黑板，领域黑板和结论黑板作为问题的求解策略。使其非公认的渗碳领域问题通过专家进行辩论择优选出最佳解，为此提出建立基于多元组命题性知识的辩论理论框架，并体现不同策略的辩论算法，对此进行了计算机仿真，结果证明此方法是有效的。     

有限时间内的动车组群分布式协同巡航多智能体控制

本文研究了动车组群系统的移动闭塞协同巡航控制问题,通过设计有限时间分布式协同控制算法实现了多车高速协同巡航.算法取消了动车组中心控制单元,将单列动车组的每个动力单元视为一个智能体,不同动车组之间的智能体形成多智能体群系统.设计了动车组智能体有限时间分布式协同控制算法,该算法首先实现了单列动车组各个动力单元快速追踪到期望的速度,且保证车钩位移在安全范围内,其次该算法还能实现动车组群高速巡航等间距运行,提高了线路利用率的同时避免了碰撞.最后进行了理论分析,证明了算法的稳定性和有限时间收敛性,并提供了仿真结果验证了该算法的有效性.     

数控自动编程专家系统

本文简要地介绍了数控自动编程专家系统.其中包括:专家系统知识表示的形式;分层次的黑板结构;前向推理求解策略和相应的解释功能;系统针对不同类型的曲线组合,采用不同的独立的知识源(KS)进行处理.由于在知识的处理上采用编码技术,在前向推理求解策略中使用启发信息和“剪技”技术,提高了系统的时空效率.系统中的规划程序能自动规划切削路径.输出供数控车床使用的 NC 代码,并可在显示屏上进行图形显示和切削仿真.目前原型系统已经在 IBM-PC 和 Sun3/60计算机上利用FORTRAN 语言实现.     

面向协同设计系统的分布式群决策支持技术研究

在探讨业务处理中间件的分布计算模式、多主体控制以及分布式问题处理多库管理技术基础上,该文重点分析群体决策支持的协问设计系统分布计算环境;提出并实现了领域问题求解策略、应用模块的模型化管理方法以及分布式问题求解及其过程监控.同时深入研究协同设计系统业务处理中间件的信息资源共享和分布式问题求解的多维信息交互过程,实现了协同设计系统开放式群体决策集成开发平台.最后以预研项目为研究背景,实现了设备设计的产品集成化开发设计,取得了明显的实际应用效果.     

一种图象理解的专家系统工具语言

为了在实时图象处理系统中,实现并行环境下基于黑板模型的多知识源协同求解,从知识表示、推理方式、控制机制等方面介绍了智能所自行研制的一种图象理解专家系统工具语言--V语言（V.3版本）。该语言具有多种知识表示,采用数据驱动与模型驱动相结合的推理方式,由黑板对推理进行控制,知识库由多个知识源（分别存在有关模型的静态知识和各种图象处理算法）组成等特点。最后给出了针对水上桥梁一类的图象进行理解的具体实例。     

Using knowledge generated in heuristic search for nonchronological backtracking

Problem solvers that use heuristics to guide choices often run into untenable situations that can be characterized as overconstrained. When this happens, the problem must be able to identify the right culprit from among its heuristic choices in order to avoid a potentially explosive search. In this paper, we present a solution to this for a certain class of problems where the justifications associated with choice points involve an explicit assessment of the pros and cons of choosing each alternative relative to its competitors. We have designed a problem solver that accumulates such knowledge about the pros and cons of alternative selections at choice points during heuristic search, which it updates in light of an evolving problem situation. Whenever untenable situations arise, this preserved knowledge is used to determine the most appropriate backtracking point. By endowing the backtracker with access to this domain-specific knowledge, a highly contextual approach to reasoning in backtracking situations can be achieved.     

A temporal blackboard for a multi-agent environment

The multi-agent system paradigm emerges as an interesting approach in the Knowledge Based System (KBS) field, when distributed problem-solving techniques are required for solving problems that can be represented as a collection of groups of cooperating intelligent individuals. A key concept in the multi-agent systems is the interaction between agents. On the other hand time plays a crucial role in a wide range of KBS applications. Temporal reasoning and representations consists of formalizing the notion of time and providing means to represent and reason about the temporal aspects of knowledge. This paper presents a framework for agent communication based on the blackboard paradigm which is able to manage temporal information, and it provides its multiple access and coherence management protocols.     

Cooperative output regulation of multi-agent systems with switched leader dynamics

In this paper, the cooperative output regulation problem for heterogeneous multi-agent systems is addressed by considering a switched leader dynamics. The switched leader dynamics consists of multiple linear models and a switching rule governing the switches among them. A switched leader is capable of generating various sophisticated reference signals for more complicated multi-agent coordination tasks. A novel distributed hybrid impulsive switching control scheme is proposed to achieve cooperative output regulation. Distributed switching stability is established using the average dwell-time technique with multiple Lyapunov functions. Moreover, the associated distributed control synthesis conditions are formulated in terms of linear matrix inequalities plus linear matrix equations. As a result, both switching rules for the leader and distributed switching protocols for the followers can be jointly synthesised via efficient semi-definite programming. An example has been used to demonstrate the effectiveness of the proposed approach.     

COMBINING MULTI‐AGENT PARADIGM AND MEMETIC COMPUTING FOR PERSONALIZED AND ADAPTIVE LEARNING EXPERIENCES

Learning is a critical support mechanism for industrial and academic organizations to enhance the skills of employees and students and, consequently, the overall competitiveness in the new economy. The remarkable velocity and volatility of modern knowledge require novel learning methods offering additional features as efficiency, task relevance and personalization. Computational Intelligence methodologies can support e‐Learning system designers in two different aspects: (1) they represent the most suitable solution able to support learning content and activities, personalized to specific needs and influenced by specific preferences of the learner and (2) they assist designers with computationally efficient methods to develop “in time” e‐Learning environments. This article attempts to achieve both results by exploiting an ontological representations of learning environment and memetic approach of optimization, integrated into a cooperative distributed problem solving framework. This synergy enables multi‐island memetic approach managing a collection of models and processes for adapting an e‐Learning system to the learner expectations and to formulate objectives in an effective and dynamic intelligent way. More precisely, our proposal exploits ontological representations of learning environment and a memetic distributed problem‐solving approach to generate the best learning presentation and, at the same time, minimize the computational efforts necessary to compute optimal learning experiences.     

Cooperative Constrained Control of Distributed Agents With Nonlinear Dynamics and Delayed Information Exchange: A Stabilizing Receding-Horizon Approach

This paper addresses the problem of cooperative control of a team of distributed agents with decoupled nonlinear discrete-time dynamics, which operate in a common environment and exchange-delayed information between them. Each agent is assumed to evolve in discrete-time, based on locally computed control laws, which are computed by exchanging delayed state information with a subset of neighboring agents. The cooperative control problem is formulated in a receding-horizon framework, where the control laws depend on the local state variables (feedback action) and on delayed information gathered from cooperating neighboring agents (feedforward action). A rigorous stability analysis exploiting the input-to-state stability properties of the receding-horizon local control laws is carried out. The stability of the team of agents is then proved by utilizing small-gain theorem results.