Abstract: The Blackboard Instructional Planner is a blackboard-based dynamic planner for intelligent tutoring systems. It generates a sequence of lesson plans customized to a student's background, and adaptively replans to handle student requests and unexpected changes to the student model or time remaining. The planner is designed to be generic to tutors that teach troubleshooting for complex physical devices. It controls the Lower Hoist Tutor, a prototype tutor for the Mark-45 naval gun mount. This tutor teaches troubleshooting of the lower hoist, a complex hydraulic-electronic-mechanical assembly of the Mark-45. The tutor implementation demonstrates the planner's operation and means of integration. This research contributes to an understanding of dynamic instructional planners, planner-controlled tutors, and ITS control architectures. The planner implementation shows precisely how a blackboard architecture can be used to realize a dynamic instructional planner. Although experimental, the tutor implementation demonstrates how such a planner can be embedded in an intelligent tutoring system and what the respective roles of the different components of a planner-controlled tutor are. Finally, the analysis of the planner's use of the blackboard architecture clarifies requirements for control architectures in intelligent tutoring systems and trade-offs made in choosing alternatives.

Abstract: This volume presents concise and comprehensive coverage of the principles and concepts that are fundamental to the design of expert systems software and hardware and the development of knowledge-based systems. The volume includes an overview of the symbolic and object-oriented programming languages used to create knowledge representation languages structures, a description of declarative and procedural knowledge representation schemes, a discussion of search algorithms and various numerical and non-numericla techniques for dealing with uncertainty, and an introduction to reasoning with one or more inference engines. The book also provides an overview of the architecrure and functions of blackboard systems, a review of the state of the art in explanation, and a discussion of user interface requirements and integrated systems.

Abstract: The recent publication of two books on blackboard architectures, Blackboard Architectures and Applications (eds. V. Jagannathan, R. Dodhiawala, and L.S. Baum, Academic Press, Inc., 1989) and Blackboard Systems (eds. R. Engelmore and T. Morgan, Addison Wesley, 1988) is an indication of the maturity and current popularity of this particular area of AI research. Blackboard Architectures and Applications, the book under review here, is the most current of these two works.

Abstract: These original contributions provide a unique opportunity for researchers and computing professionals, engineers, and managers to explore both the principles underlying basic AI research and their application in practice.The first part of the book describes work in five areas of AI research that is currently at the stage where it can be implemented in practical programs. These areas include blackboard architectures and systems, learning algorithms and strategies, neural networks, adaptive learning using pattern recognition, and signal processing.The second part describes six systems, designed for a wide variety of applications, that are now either in operation or at an advanced stage of development; intelligent techniques for spectral estimation, expert systems applied to antenatal assessment of fetal well-being, AI in the processing of underwater acoustic data, automatic speech recognition using neural networks, fault diagnosis of microwave digital radio, and waveguide filter alignment using adaptive learning techniques.A. R. Mirzai is a Research Fellow in the Department of Electrical Engineering at the University of Edinburgh. "Artificial Intelligence: Concepts and Applications" is included in the Artificial Intelligence series, edited by Michael Brady, Daniel Bobrow, and Randall Davis.

Abstract: An expert system includes a blackboard, a plurality of knowledge sources, a control knowledge source and a control module. The blackboard stores data used during an execution cycle. Each knowledge source includes rules for performing selected operations in connection with the data in the blackboard. The control knowledge source includes selection rules for selecting among the knowledge sources. The control module performing an execution cycle including an eligibility determination phase to identify one or more of the knowledge sources, a knowledge source selection phase using the selection rules in said control knowledge source to select one of the identified knowledge sources, and an action phase to process a rule of the selected knowledge source.

Abstract: A set of tools have been developed which support multisensor fusion for autonomous robots. These tools include a consistent data representation, a control approach, an interface mechanism, system configuration, debugging and performance monitoring. The data representation is structured as a class tree and uses a blackboard paradigm for subsystem interaction. The properties of the objects in this class tree are represented by a value, a measure of the value’s accuracy, a confidence in that accuracy, a timestamp and a set of active functions. Control is distributed to the computational subsystems in the form of elementary control statements (ECSs). These extended forms of production rules control subsystem function as well as the distribution of data to the system components. The interface mechanism supports both shared memory and message passing communications facilities. The development support tools all take advantage of the power of the representation and control components to ease the configuration, implementation and debugging of the system software components.

Abstract: A description is given of Pilot's Associate (PA), a control-advisory system expected to fly in late-1990s tactical fighter aircraft. PA will improve pilot effectiveness by improving pilot awareness of not only external situations but also the internal status of aircraft systems and options for accommodating faulty equipment. A blackboard architecture was used in developing the internal-awareness function, called system status. To get a clearer view of system status functionality, several examples are given to show how it aids pilots and supports other PA functions. System status architecture is described. Performance testing and evaluation results for PA are presented. Positive characteristics and drawbacks of the current architecture are summarized. >

Abstract: The integration of computer-based design and manufacturing systems has a number of advantages. Currently integration is often effected by a one-way link between a computer aided design system and the appropriate machine tool. When the tool is an automatic inspection system, there is however, a need for feedback. An approach to providing an intelligent two-way link between design and manufacturing is discussed based upon the artificial intelligence concept of a “blackboard”. An application of this technique is described in the form of an initial demonstrator linking a computer aided design system to a coordinate measuring machine.

Abstract: In this paper we present a general natural language processing system called CARAMEL (in French: Comprehension Automatique de Recits, Apprentissage et Modelisation des Echanges Langagiers). Over the last few years our group has developed many programs to deal with different aspects of natural language processing. This paper describes a general architecture that integrates them in a flexible way, and provides a control strategy capable of adapting itself to the requirements of a particular task. The model is composed of three fundamental elements:- a structured memory containing permanent knowledge and working structures of the system- a set of processes, dedicated to the execution of the various cognitive tasks- a supervisor, whose function is to trigger, to run coherently and to synchronize the processes.The system contains a kind of blackboard, which is enhanced with a control mechanism driven by meta-rules. This architecture is fully implemented. We are currently developing the meta-rules necessary to use the model for various tasks.

Abstract: Cell control forms one level of a hierarchical approach to the control of automated manufacturing systems. This paper describes the application of the artificial intelligence techniques of blackboard and actor-based systems for intelligent cell control in a framework termed Production Logistics and Timings Organizer (PLATO-Z). The blackboards required are described and the implementation is overviewed.

Abstract: A novel approach to the design automation of analog circuits is presented. The prototype implementation -OASE- has been realized as a set of cooperating expert systems with blackboard architectures. The circuit specific knowledge bases use hybrid representation schemes and are strictly separated from the execution engine. This alleviates the knowledge acquisition process as well as the extension and maintenance of existing knowledge. OASE has been developed as a design assistant, providing a hierarchical design style and fully embedded standard algorithmic tools.

Abstract: The interaction of multiple cooperating knowledge sources (MCKS) on a blackboard system is used to create an expert system shell specifically designed to address the task of designing thermal energy systems for buildings. Two themes are explored in this second generation prototype system. The first is the use of an object-oriented blackboard data representation for design artifacts with tightly coupled links to drawings, data bases, and bid specification. The second is an efficient and flexible control architecture, which organizes knowledge sources for particular tasks and enforces consistency and completeness during the execution of a design project. Design of a solar domestic hot water system is presented as an example application. The experiences of working design engineers in developing modular HVAC design knowledge sources are also discussed.

Abstract: The Cooperative Architecture of Independent Blackboards (CAIBL) package is an evolving product of an independent research and development program in distributed problem solving at Planning Research Corporation (PRC). It was originally adapted from Stanford's BB1, a general-purpose shell for the development of blackboard-based expert systems. CAIBL provides support for communicating, cooperating expert systems that are distributed across heterogeneous platforms. Its primary focus is to serve as a flexible framework for distributed expert systems working concurrently upon multiple problems that require dynamic control of communication decisions. This paper identifies the prior research upon which CAIBL is based and describes key components of CAIBL's architecture.

Abstract: Several plan recognition systems for intelligent tutoring systems are reviewed. A blackboard model for plan recognition systems in intelligent tutoring systems is developed, where the model consists of the following knowledge sources: A Plan Recognizer, a Planner and a Goal Recognizer. A set of six dimensions for plan recognition systems in intelligent tutoring systems is presented and is used for characterization and examination of some existing plan recognition systems.

Abstract: This paper describes the design and implementation of a prototype working model of an intelligent computer-aided design system (ICADS). It is the objective of the ICADS project to demonstrate the feasibility of a computer-aided design partnership in which the user orchestrates the evolution of a design solution with the intelligent assistance of the computer. The vehicle for this demonstration is a prototype CAD system shell serving as an intelligent interface between the building designer and a variable assortment of project-related data bases and knowledge bases. Specifically, ICADS Working Model Version 1 is composed of an existing, commercially available computer-aided drawing system; a geometry interpreter capable of extracting architecturally meaningful geometric objects (e.g., spaces, walls, windows) from point/line data schemes; a relational data base incorporating prototypical building type information, site/neighborhood descriptions, and sundry reference data; and an Expert Design Advisor consisting of four intelligent design tools, or domain experts, which automatically monitor the evolving design solution, and a blackboard control system responsible for coordinating the activities of the domain experts, resolving conflicts, and controlling the overall operation of the system. The Expert Design Advisor has been implemented in a production rule environment utilizing a frame-based representation structure. Its advising capabilities aremore » currently restricted to the domains of structural support, thermal environment, daylighting, and acoustics.« less

Abstract: PURPOSE: To freely edit data displayed in common on this side by mounting a connection means connecting a common display device to a ready terminal and providing a means editing the data indicated from the ready terminal according to the editing method indicated from the ready terminal to the common display apparatus. CONSTITUTION: A ready blackboard system is constituted of a common display panel 401 capable of being looked in common by all of the attendants of a meeting, the main processor 402 controlling the display panel, a ready blackboard 413 to which an attendant can input his opinion or idea, the auxiliary processor 408 controlling the blackboard, the transmission line 407 connecting the main processor 402 to the auxiliary processor 408 to transmit data and the input pen 416 for inputting handwriting data from the ready blackboard 413. By this constitution, data displayed in common can be freely edited by indicating said data on this side and further indicating the editing method thereof. COPYRIGHT: (C)1992,JPO&Japio

Abstract: This paper describes a framework for running cooperating agents in a distributed environment to support the Intelligent Computer Aided Design System (ICADS), a project in progress at the CAD Research Unit of the Design Institute at the California Polytechnic State University. Currently, the systems aids an architectural designer in creating a floor plan that satisfies some general architectural constraints and project specific requirements. At the core of ICADS is the Blackboard Control System. Connected to the blackboard are any number of domain experts called Intelligent Design Tools (IDT). The Blackboard Control System monitors the evolving design as it is being drawn and helps resolve conflicts from the domain experts. The user serves as a partner in this system by manipulating the floor plan in the CAD system and validating recommendations made by the domain experts. The primary components of the Blackboard Control System are two expert systems executed by a modified CLIPS shell. The first is the Message Handler. The second is the Conflict Resolver. The Conflict Resolver synthesizes the suggestions made by the domain experts, which can be either CLIPS expert systems, or compiled C programs. In DEMO1, the current ICADS prototype, the CLIPS domain expert systems are Acoustics, Lighting, Structural, and Thermal; the compiled C domain experts are the CAD system and the User Interface.

Abstract: The application of blackboard architectures to control problems, along with associated issues is discussed. Issues of time scales, real-time responsiveness, and hierarchical control are considered, along with, two control paradigms that are being used in conjunction with blackboard systems: the cognitive-servo approach and the hierarchical-controller approach. >

Abstract: The object-oriented programming rationale for discrete event simulation is discussed An object oriented framework for developing VIS (visual interactive simulation) system is then described The implementation of VIS concepts is illustrated with the SIMFLEX, an experimental object-oriented VIS system for simulation of flexible manufacturing systems The blackboard problem solving model is used to support the decision making process It allows for the existence of a set of knowledge sources for solving problems which require expert knowledge VIS has been found to be a natural domain for application of the paradigm and graphical capabilities provided in Smalltalk-80 >

Abstract: A knowledge-based graphic description tool (KGDT) that is used to recognize and understand engineering drawings is described. This tool basically consists of a concept description network, a graphic description language, a physical description framework, a set of image processing modules, a matcher, a rule-based inference engine, an interpreter, and a blackboard control architecture. The matcher recognizes all graphic symbols and characters in the engineering drawing based on the various properties of the different graphic symbols and characters that are extracted by the low-level image processing routines. The rule-based inference engine is built to infer possible relations among graphic symbols and generate a relational graph. The interpreter is used to generate an acceptable explanation in terms of traversal of the relational graph. The interactions among the interpreter, the matcher, the inference engine, and the image processing routines are controlled by the blackboard control architecture. >

Abstract: Fundamental to the operation of most currently envisioned Intelligent Vehicle-Roadway System (IVRS) projects are advanced systems for surveillance, control and management of integrated freeway and arterial networks. A major concern in the development of such Smart Roads, and the focus of this paper, is the provision of decision support for traffic management center personnel, particularly for addressing nonrecurring congestion in large or complex networks. Decision support for control room staff is necessary to effectively detect, verify and develop response strategies for traffic incidents. The purpose of this paper is to suggest a novel artificial intelligence-based solution approach to the problem of providing operator decision support in integrated freeway and arterial traffic management systems, as part of a more general IVRS. A conceptual design is presented that is based on multiple real-time knowledge-based expert systems (KBES) integrated by a distributed blackboard problem-solving architecture. The paper expands on the notions of artificial intelligence and Smart Roads, and in particular the role, characteristics and requirements of KBES for real-time decision support. The overall concept of a decision support architecture is discussed and the blackboard approach is defined. A conceptual design for the proposed distributed blackboard architecture is presented, and discussed in terms of the component KBES functions at an areawide level, as well as at the subnetwork or individual traffic control center level.

Abstract: The paper proposes a model of program designer behavior, based on the blackboard architecture, that has the capability of describing multi-directional decision-making by means of hierarchical (i.e., ‘top-down’ and ‘bottom-up’), heterarchical, sequential and incremental planning strategies for the design process. It is expressed in terms of cognitive processes that operate on, and communicate via, information posted on a specific blackboard structure. These processes, or specialists, are an extension of the set proposed by Hayes-Roth and Hayes-Roth (1979) for opportunistic planning. Additional specialists in our characterization are divided into those that correspond to general problem-solving methods and those relating specifically to the program design task. These include specialists that note features of the problem, those that analogize and make assessments about sub-problems and those that modify policies. Details of an experimental study involving the collection of verbal and video protocols are also reported. The proposed model is used as an explanatory framework for the results obtained. These are also discussed in relation to other cognitive models of the program design process.

Abstract: PURPOSE:To eliminate a code between a marker and another circuit by providing a switch, for which a tuning circuit is constituted when a pen body is abutted to the writing surface, etc., of a blackboard main body. CONSTITUTION:When the marker is operated on the writing surface of the blackboard main body, a switch 151 is operated and the tuning circuit, which is composed of a coil 152 and capacitors 153 and 154, is constituted. However, in such a case, an electric wave to have a prescribed frequency is received from an antenna coil in the blackboard main body side and the induced voltage of a prescribed frequency is generated in the tuning circuit. A current flows into the tuning circuit by this induced voltage and the electric wave of the almost same frequency as the prescribed frequency is transmitted from a coil 152. However, since the current is continued to flow without being rapidly attenuated even when the electric wave from the antenna coil is stopped, the induced voltage of the almost same frequency as the prescribed frequency is generated in the antenna coil. Accordingly, the usage of the marker can be discriminated in the blackboard main body side.