Blackboard Architecture

AI and DAI based planning techniques, suitable for automated manufacturing systems are surveyed and compared. The relation of learning to planning is described and it is explained how learning may be used to improve planning. Several examples are presented. A complete reference list is provided.

With increased number of new services and users being added to the communication network, management of such networks becomes crucial to provide assured quality of service. Finding skilled managers is often a problem. To alleviate this problem and also to provide assistance to the available network managers, network management has to be automated. Many attempts have been made in this direction and it is a promising area of interest to researchers in both academia and industry. In this paper, a review of the management complexities in present day networks and artificial intelligence approaches to network management are presented. Published by Elsevier Science B.V.

Design-to-time is an approach to problem solving in resource-constrained domains where: multiple solution methods are available for tasks, those solution methods make trade-offs in solution quality versus time, and satisficing solutions are acceptable. Design-to-time involves designing a solution to a problem that uses all available resources to maximize the solution quality within the available time. This paper defines the design-to-time approach in detail, contrasting it to the anytime algorithm approach, and presents a heuristic algorithm fdr design-to-time real-time scheduling.

Human cognition is unique in the way in which it relies on combinatorial (or compositional) structures. Language provides ample evidence for the existence of combinatorial structures, but they can also be found in visual cognition. To understand the neural basis of human cognition, it is therefore essential to understand how combinatorial structures can be instantiated in neural terms. In his recent book on the foundations of language, Jackendoff described four fundamental problems for a neural instantiation of combinatorial structures: the massiveness of the binding problem, the problem of 2, the problem of variables, and the transformation of combinatorial structures from working memory to long-term memory. This paper aims to show that these problems can be solved by means of neural "blackboard" architectures. For this purpose, a neural blackboard architecture for sentence structure is presented. In this architecture, neural structures that encode for words are temporarily bound in a manner that preserves the structure of the sentence. It is shown that the architecture solves the four problems presented by Jackendoff. The ability of the architecture to instantiate sentence structures is illustrated with examples of sentence complexity observed in human language performance. Similarities exist between the architecture for sentence structure and blackboard architectures for combinatorial structures in visual cognition, derived from the structure of the visual cortex. These architectures are briefly discussed, together with an example of a combinatorial structure in which the blackboard architectures for language and vision are combined. In this way, the architecture for language is grounded in perception. Perspectives and potential developments of the architectures are discussed.

PROTEAN is an evolving knowledge-based system that is intended to identify the three-dimensional conformations of proteins in solution. Using a variety of empirically derived constraints, PROTEAN must identify legal positions for each of a protein's constituent structures (e.g., atoms, amino acids, helices) in threedimensional space. In fact, because protein-structure analysis is an underconstrained problem, PROTEAN must identify the entire family of conformations allowed by available constraints. In this paper, we discuss PROTEAN's approach to the protein-structure analysis problem and its current implementation within the BBl blackboard architecture.

Hospital laboratories perform examination tests upon patients, in order to assist medical diagnosis or therapy progress. Planning and scheduling patient requests for examination tests is a complicated problem because it concerns both minimization of patient stay in hospital and maximization of laboratory resources utilization. In the present paper, we propose an integrated patient-wise planning and scheduling system which supports the dynamic and continual nature of the problem. The proposed combination of multiagent and blackboard architecture allows the dynamic creation of agents that share a set of knowledge sources and a knowledge base to service patient test requests. #

The set of partially interdependent lexical and syntactic decisions that have to be made in the process of natural language generation are best seen as a complex planning and search problem. This paper discusses the phenomena involved in natural language generation planning and argues that a blackboard-type architecture with agenda-style control is more appropriate for this task than a sequential control architecture with backtracking. The blackboard architecture we describe is implemented in the language generator DIOGENES.

A methodology for recognizing ZIP codes (US postal codes) in handwritten addresses is presented that uses many diverse pattern recognition and image processing algorithms. Given a high-resolution image of a handwritten address block, the solution invokes routines capable of hypothesizing the location of the ZIP code, segmenting and recognizing ZIP code digits, locating and recognizing city and state names, and looking up the results in a dictionary. The control structure is not strictly sequential, but rather in the form of a blackboard architecture that opportunistically invokes routines as needed. An implementation of the methodology is described as well as results with a database of grey-level images of handwritten addresses (taken from live mail in a US Postal Service mail processing facility). Future extensions of the approach are discussed

AEROBA#11> Are there any budget constraints in the problem (Yes No)? USER-RESPONSW> Yes AEROBA#12> Please enter data for Demand-Location-Name D1 AEROBA#13> Please enter data for Demand-Location-Name 0 2 AEROBA#14> Are there any constraints on the quantities being purchased (Integer Capacitated Neither)? USER-RESPONSE#12> Integer AEROBA#15> Please enter the data for the Supply-Location-Name AEROBA#16> State your alternate objective (Profit-Max Time-Min Neither) USER-RESPONSE#14> Neither AEROBA#17> Based on your response, AEROBA assumes a Cost-Min objective AEROBA#18> Please enter total budget data for Supply-Locations AEROBA#19> Please enter the relationship between the total cost and the budget for the Supply locations (LE GE EQ) AEROBA#20> Please enter the data for the shipping cost (S 1 01) AEROBA#21> Please enter the data for the shipping cost (Sl 0 2) AEROBA#22> Please enter the data for the shipping cost (S2 D1) AEROBA#23> Please enter the data for the shipping cost (S2 0 2) AEROBA#24> Please enter the stock data for Supply-Location (Sl) USER-RESPONSE#8> 01 0 2 USER-RESPONSE#lO> 70 USER-RESPONSE#11> 40 USER-RESPONSE#13> S1 5 2 USER-RESPONSE#15> 15 000 USER-RESPONSE#16> LE USER-RESPONSE#17> 20 USER-RESPONSE#18> 25 USER-RESPONSE#19> 50 USER-RESPONSE#20> 55 USER-RESPONSE#21> 50 AEROBA#25> Please enter the stock data for Supply-Location (S 2) AEROBA#26> Please enter the purchasing cost at Supply-Location USER-RESPONSE#22> 20 (SI) (52) USER-RESPONSE#23> 400 AEROBA#27> Please enter the purchasing cost at Supply-Location USER-RESPONSE#24> 350 AEROBA#28> Done. . .

A knowledge-based shell for circuit simulation has been developed as one part of a design environment for analog circuits. This shell offers circuit-specific simulation support exploiting expert knowledge for dealing with problems like test function generation and simulation clustering. Furthermore it provides worst-case analysis capabilities as well as automatic documentation facilities like data sheet generation and a design database. The prototype implementation, SILAS, has been realized as an expert system with blackboard architecture. Knowledge and knowledge execution are strictly separated to allow an easy extension of the incorporated knowledge bases. SILAS is organized as a simulation assistant, which means the user may specify a specific task by a workplan while the task organization and control is taken over by the system. Application areas are all domains which require automated circuit characterization such as synthesis or cell library maintenance.

When optimizing designs for practical electromagnetic problems, the number of design constraints and variables is increased drastically. The construction and step-by-step creation of an electrical system, in practice, is a trial and error process. The design may lead to a sub-optimal solution since the success of a design depends on the experience of the designer. Optimization requires that all design goals, of a device, be connected into a single objective function with all independent variables and constraints. In practice, effective preprocessing and post processing of data are necessary in addition to high performance computing capabilities. To achieve this process, we propose the creation of a generalized optimization environment or a virtual designer.

This paper presents MESSIE, a multi-specialist architecture for scene interpretation in a robotic application. MESSIE is a centralized hierarchical blackboard architecture. The generic model of objects and the explicit description of sensors and materials allow the use of an application independent interpretation strategy. Two remote sensing applications on 2D scene interpretation and a third one, presented in this paper, on 3D scene interpretation allow the validation of the proposed architecture as well as the main features of MESSIE. After a brief overview of the state of art in 3D object modeling and scene interpretation, we discuss the scene interpretation problem from the knowledge representation view point. Then the architecture of MESSIE, the object modeling and the processing strategies (object detection and scene interpretation) are described. Further an application of 3D indoor scene interpretation in mobile robot context is given. We also present an interpretation running example using constrained low-level feature extraction mechanism to improve the image segmentation results.

Attempts to apply conventional rule-based expert systems to legal problem-solving raise seemingly insurmountable obstacles. The authors analyse the key challenges of developing a legal expert system by reference to a case study of issues arising in their prototype system, the JAES project. This paper explores the advantages of exploiting three alternative approaches- namely: case-based reasoning, blackboard architecture, and service-oriented architecture for the next generation of legal expert systems. The authors advocate the use of hybrid architecture to address the complexity and dynamic nature of the legal domain. The paper evaluates the extent to which these enhancements can meet the special complexities of the legal domain.

We describe a biologically inspired memory in a multi-agent based robotic architecture. In this approach, memory and pattern recognition are intertwined to form a cognitive memory that is used for recognition of objects in a robotics environment.

In a competitive environment, selecting and effectively using reliable information technologies, accurate methodologies and the right information systems, led to a search for an audit process. The information system audit process is therefore viewed as a detailed field program of many steps related to two basic decisions:

This article presents an architecture of a model-based and knowledge-based system for real-time supervisory control of chemical process systems. This architecture incorporates the following key features: (1) a temporal reasoning strategy based on time-stamped data arriving from the process; (2) the use of an online process model to assist in the decision-making process; (3) a blackboard system for the communication between various knowledge sources; (4) a meta-level decision maker to coordinate the action of these knowledge sources in an orderly and priority-driven fashion, and (5) the concept of continued operational plan refinement to meet the overall goals of the process operation in the presence of continuously changing external environmental stimuli. The proposed architecture has been implemented using an object-oriented programming environment offered through extensions to the C language. Some results on application to the control of an autoclave curing process are given in this paper. The main contribution of this paper is a layout of the system architecture and a demonstration of the advantages resulting from the integration of traditional knowledge-based control implemented using expert operators with model-based control that utilize a simulation model of the process.

The paper introduces a taxonomy of the possible coordination models for mobile agent applications and evaluates their impact in the design of a widely distributed application in the area of information retrieval. The analysis outlines the advantages of uncoupled coordination models and points out the need for coordination models based on reactive blackboards.

In this paper we address the problem of how new categories and new interpretations can be created in legal reasoning. We present some examples of such creativity, and then an- alyze them t-o identify the mechanisms that must be mod- eled for incorporating creativity. We point out that many of these mechanisms can be implemented by using components of already existing sysrems. Based on this analysis, we out- line our approach, which uses a blackboard style architecture to generate creative arguments. Top-down processes are activated by ponions of rules or ratio decidendi of precedents. Bottom-up processes are activated by the facts of the cur- rent case and precedents. The retrieval of precedents is also modeled as a blackboard process, so that which precedents are examined is determined dynamically depending on the contents of the blackboard. We compare our approach with existing research and then briefly mention future research problems.

"It is desirable to incorporate heuristic and empirical knowledge including hydrological and bio-geochemical considerations into the selection process of a potential landfill site. In this article, a prototype expert system for the selection of a landfill site, with hybrid knowledge representation approach under object-oriented design environment in a blackboard architecture, is described. It incorporates an artificial neural network for training of partial hazardous scores and a fuzzy rule base for the representation of heuristic knowledge. The evaluation is based on the hazardous waste site ranking system recommended by the US Environmental Protection Agency, adapted to Hong Kong conditions by incorporating the stipulation of some local regulations. It is shown to be a useful aid in assisting novice engineers in the selection process of a potential landfill site during preliminary investigation.

Keywords: artificial neural network; blackboard architecture; expert system; fuzzy inference; hazardous waste; sanitary landfill; site selection"

Abstmct--A subclass of knowledge intensive problems is identified wherein the problems are transient in nature but still benefit from the application of expertise. The authors denote these problems as Episodic Classification Problems and detail the evolution of a blackboard-based approach, first as an architecture and then as a prototype application, used to solve this class of problems. They note that, while some system changes are required to accommodate the nature of the application being addressed, similarities over these problems lend themselves to a generalized solution.

In the automotive industry, the knowledge, information, and tools required for design, analysis, manufacturing, and testing of company products are distributed throughout the organization. This fragmentation of expertise and information creates impediments to cost-e ective design engineering. This article describes: 1) an approach to building integrated engineering environments based on blackboard technology as the integrating infrastructure; and 2) the RRM Engineering Environment, developed at Ford Research Laboratory. The RRM Engineering Environment is a large-scale prototype application comprising thirteen agents, some of which are legacy application programs, written in various languages, and distributed over heterogeneous machines and platforms. Use of integrated environments, such as the RRM environment, is expected to result in increased productivity, fewer delays and errors, and better communication among interacting participants in the design-to-manufacture process.

The Maneuver Decision Aid (MDA) is a knowledge-based planner currently being developed at the US Naval Undersea Warfare Center. the goal of MDA is to generate an optimal next-maneuver recommendation, to support the submarine commander's decision making process which includes absorbing an extensive amount of complex information in the short time interval between maneuvers. The model for the maneuver generation process decomposes into three main parts: situation assessment, goal formulation, and constraint satisfaction. It is essential for an automated reasoning system in this domain to consider all factors and concerns in a given situation to put forth its best recommendation. A key aspect of this model is that all identified situation goals and constraints are represented and combined according to their varying degrees of importance. The authors describe how constraint ratings are evaluated and combined within an object-oriented blackboard framework. The focus is on how rated-constraints are formed, represented, and combined to provide optimal solutions

Automated video surveillance networks are a class of sensor networks with the potential to enhance the protection of facilities such as airports and power stations from a wide range of threats. However, current systems are limited to networks of tens of cameras, not the thousands required to protect major facilities. Realising thousand camera automated surveillance networks demands middleware and architectural support; replacing the ad hoc approaches used in current systems with robust and scalable methods.

This paper presents a knowledge-based approach for dynamic rescheduling. Scheduling is a complex activity often influenced by diverse and conflicting constraints. The problem is complicated further by dynamic environments, where rescheduling in response to changes is critical. In this paper a generalized architecture for dynamic rescheduling is presented. The architecture combines a blackboard-based opportunistic scheduling system that is integrated with reason maintenance capabilities. The blackboard component focuses on the process of constructing a schedule that is deemed to be primarily opportunistic in nature. The reason maintenance capabilities of the system focus on rescheduling, keeping track of justifications for assignments, and ensuring that the current schedule is always valid, that is, flee of inconsistencies.

Change in requirements has been recognized lately as an event that is expected to occur in the life of a software system, contrary to the popular belief in the past that changes in requirements are an exception. Software engineering community has been addressing this new paradigin hy proposing various solutions for adapting the software to such changes. The term "adaptation" in software engineering is usually 111terpreted differently than in control. Tn this paper we present an attempt to incorporate the notions of adaptive and restructural)lc control, as i t is understood in control, into thc realm of software engineering. We assumed that the software system (the plant) changes in an unpredictahle fashion, i.e., i t s model may changt in the futurc. I n t tlie software designer IS not ahlc to anticipate what kind of change slmiild be &t hat snrh softmaze fails to achieve its goal, i.e.. rerognize objects/targets when unexpected changes in the inputs occur.

"Owing to the high degree of vulnerability of liquid retaining structures to corrosion problems, there are stringent requirements in its design against cracking. In this paper, a prototype knowledge-based system is developed and implemented for the design of liquid retaining structures based on the blackboard architecture. A commercially available expert system shell VISUAL RULE STUDIO working as an ActiveX Designer under the VISUAL BASIC programming environment is employed. Hybrid knowledge representation approach with production rules and procedural methods under object-oriented programming are used to represent the engineering heuristics and design knowledge of this domain. It is demonstrated that the blackboard architecture is capable of integrating different knowledge together in an effective manner. The system is tailored to give advice to users regarding preliminary design, loading specification and optimized configuration selection of this type of structure. An example of application is given to illustrate the capabilities of the prototype system in transferring knowledge on liquid retaining structure to novice engineers.

Keywords: expert-system; flow; management, liquid retaining structure, design, blackboard architecture"

A major drawback of 3-D medical image registration techniques is the performance bottleneck associated with re-sampling and similarity computation. Such bottlenecks limit registration applications in clinical situations where fast execution times are required and become particularly apparent in the case of registering 3-D data sets. In this paper a novel framework for high performance intensity-based volume registration is presented. Geometric alignment of both reference and sensed volume sets is achieved through a combination of scaling, translation, and rotation. Crucially, resampling and similarity computation is performed intelligently by a set of knowledge sources. The knowledge sources work in parallel and communicate with each other by means of a distributed blackboard architecture. Partitioning of the blackboard is used to balance communication and processing workloads. Large-scale registrations with substantial speedups, when compared with a conventional implementation, hav...

Vehicle intelligent control is a robotics real time application where elaborated reasoning process and reactive process work together and have to cooperate or more to be interdependent. Multi-agent systems are well suited to such complex systems specication, because of their software engineering, their reasoning capabilities (from a cognitive point of view) or their performances (from a reactive point of view). This paper proposes a model of agent integrating both reactive and deliberative capabilities adapted to real time context. The paper introduces and discusses the use of a parallel blackboard architecture to support the agent model in order to meet real time constraints. An illustration of the functioning of the agent architecture is given through a roadway tra c scenario emphasizing the main aspects of real time distributed decision making.

This paper delineates the development of a prototype hybrid knowledge-based system for the optimum design of liquid retaining structures, OPTLIQ, by coupling the blackboard architecture, an expert system shell VISUAL RULE STUDIO and genetic algorithm (GA). Through custom-built interactive graphical user interfaces under a user-friendly environment, the user is directed throughout the design process, which includes preliminary design, load specification, model generation, finite element analysis, code compliance checking and member sizing optimization. For structural optimization, GA is applied to the minimum cost design of structural systems with discrete reinforced concrete sections. The design of a typical example of the liquid retaining structure is illustrated. The results demonstrate extraordinarily converging speed as near-optimal solutions are acquired after merely exploration of a small portion of the search space. This system can act as a consultant to assist novice designers in the design of liquid retaining structures.

We present a model of visual working memory in ventral prefrontal cortex. Activation in ventral PFC consists of reverberating activity. Representations in ventral PFC are conjunctions of location and (partial) identity representations. With many objects, representations in ventral PFC interfere, which results in loss of information. Therefore, the number of objects in working memory is limited. However, because ventral PFC is connected to the 'identity' levels in the visual cortex, the number of features for each object is unlimited. The 'blackboard' architecture of ventral PFC results in a uniÿcation (binding) of the feature representations of the objects maintained in memory.

The objective of this research is to provide appropriate cross-layer architecture for wireless cognitive networks for efficient resource allocation and improved quality of service. We proposed the blackboard model, which is known for coordinating multiple agents (cognitive nodes) in a real-time manner, receiving the current state of information from these nodes, providing conclusions basing on information received from these nodes, updating these nodes with current conclusions, and suggesting needed actions for these nodes. Each cognitive node is assumed as an agent to the blackboard. The parameter values abstracted from these cognitive nodes to blackboard are structured messages that are optimized with respective to an objective function. This paper introduces the crosslayer design of a cognitive network, the role of the blackboard architecture, and possible applications.

This paper proposes IIP (intelligent Internet protocol) which effectively addresses the issues involved in wireless communication at network layer such as support for mobility, frequent loss of connection clue to fading, hand-offs and security. We have chosen to use intelligent agent technology for our architecture of IIP because it provides desirable properties such as speed-up and efficiency, robustness and reliability,

T h e nzaiiirhzzotron technaque has proelided ayrzcziltural sczeatists t h e opportuiiaty of obserziiiig 7 h i : osphere activztaes wztkout destroying loot structures Nonetheless, t h e laborzous analysts of the data still prohabats zts wade applacataoiis Advanced i m a g e t i ndersiaiidaiig techiizques are needed t o derive saiisfciclory descraptions of p l a n t root iieiiuorks a n a n e f i c r e n t orrd robust way. This paper presents a plnni roof image analysis s y s t e m deszgned as a blackboard nichileciure wath a hierarchy of data abstractions Iniporiunt propertzes of plant roots are used throughout t h e processiiig a n d niultzple sources of tn forinaiaon are combiaerl t o resolve uii cert aaiit zes an zmog e an i erp ret aiz oii Ez perzinental results from s o m e stages of t h e rea~arcli arc given whach support t h e overall processing s c h e m e

We present a system for the reconstruction of houses from aerial images. Most of the methods proposed sofar use rather specific models. These models do not hold when dealing with european-style houses. Our system works with rules instead of models merely based on shape. This enables us to include additional domain specific knowledge, allowing a larger variability of the objects. However, this also necessitates a more complex structure of the knowledge base and a more sophisticated reasoning control. We explain the practical application of such a system for the reconstruction of a house from an aerial image. 1

This paper presents ongoing research into using Artificial Intelligence (AI) techniques to intelligently control finite element thermal analyses. These techniques are used to implement component level decomposition of the physical domain, and to integrate domain information into the analysis process to increase computational efficiency. We have implemented these techniques into a new proof-of-concept finite element program which employs a blackboard architecture to integrate the various numerical and symbolic knowledge sources. The blackboard architecture also supports the storage (and retrieval) of data in an object-oriented form. A test problem involving transient thermal analysis of an integrated circuit package is presented. Use of the proposed method showed a significant decrease in the number of floating point operations required compared to conventional solution technologies. The penalty associated with this saving was approximately a 4% difference in the calculated temperature in the critical region of interest.