Abstract

Blackboard systems are not new technology. The first blackboard system, the Hearsay-II speech understanding system [1], was developed nearly twenty years ago. While the basic features of Hearsay-II remain in today’s blackboard systems, numerous advances and enhancements have been made as a result of experience gained in using blackboard systems in widely varying application areas. Unlike most AI problem-solving techniques that implement formal models, the blackboard approach was designed as a means for dealing with ill-defined, complex applications. Unconstrained by formal requirements, researchers and developers have had considerable flexibility in inventing and applying advanced techniques to blackboard architectures. However, the lack of formal specifications has also contributed to confusion about blackboard systems and their proper place in the AI problem-solving toolkit. This article describes the characteristics and potential of blackboard systems. I’ll discuss what a blackboard system is (and is not) and why the use of blackboard-based problem solving is only now emerging from the academic and research laboratory. Finally, I’ll discuss whether you should consider using the blackboard approach for your applications and how to get started

Citations

278	The Hearsay-II Speech-Understanding System: IntegraKnowledge to Resolve Uncertainty - Hayes-Roth, Lesser, et al. - 1980
27	GBB: A generic blackboard development system - Corkill, Gallagher, et al. - 1986
1	Nii and Nelleke Aiello. AGE (Attempt to GEneralize): A knowledge-based program for building knowledge-based programs - Penny - 1979
1	BB1 User Manual. Knowledge Systems - Garvey, Hewett, et al. - 1986