Extending a blackboard architecture for approximate processing

Abstract

Approximate processing is an approach to real-time AI problem-solving systems in domains where there are a range of acceptable answers in terms of certainty, accuracy, and completeness. Such a system needs to evaluate the current situation, make time predictions about the likelihood of achieving current objectives, monitor the processing and pursuit of those objectives, and if necessary, choose new objectives and associated processing strategies that are achievable in the available time. In this approach, the system is performingsatisficing problem-solving, in that it is attempting to generate the best possible solutions within available time and computational resource constraints.

Previously published work (Lesser, Pavlin and Durfee 1988) has dealt with this approach to real-time; however, an important aspect was not fully developed: the problem solver must be very flexible in its ability to represent and efficiently implement a variety of processing strategies. Extensions to the blackboard model of problem solving that facilitate approximate processing are demonstrated for the task of knowledge-based signal interpretation. This is accomplished by extending the blackboard model of problem solving to include data, knowledge, and control approximations. With minimal overhead, the problem solver dynamically responds to the current situation by altering its operators and state space abstraction to produce a range of acceptable answers. Initial experiments with this approach show promising results in both providing a range of processing algorithms and in controlling this dynamic system with low overhead.