A Real-Time Control Architecture for an Approximate Processing Blackboard System

Abstract

Approximate processing is an approach to real-time AI problem solving in domains in which compromise is possible between the resources required to generate a solution and the quality of that solution. It is a satisficing approach in which the goal is to produce acceptable solutions within the available time and computational resource constraints. Previous work has shown how to integrate approximate processing knowledge sources within the blackboard architecture. However, in order to solve real-time problems with hard deadlines using a blackboard system, we need to have: (1) a predictable blackboard execution loop, (2) a representation of the set of current and future tasks and their estimated durations, and (3) a model of how to modify those tasks when their deadlines are projected to be missed, and how the modifications will affect the task durations and results. This paper describes four components for achieving this goal in an approximate processing blackboard system. A parameterized low-level control loop allows predictable knowledge source execution, multiple execution channels allow dynamic control over the computation involved in each task, a meta-controller allows a representation of the set of current and future tasks and their estimated durations and results, and a real-time blackboard scheduler monitors and modifies tasks during execution so that deadlines are met. An example is given that illustrates how these components work together to construct a satisficing solution to a time-constrained problem in the Distributed Vehicle Monitoring Testbed (DVMT).

Situated Image Understanding in a Multiagent Framework

“…For example, state and metareasoning are used in an approximate processing blackboard system in Ref. 15. Here, different levels of control are used and metalevel mechanisms are exploited to manage scheduling of actions and their specialization.…”

“…In these situations, difficulties in the control of image understanding activities 15,19 ' 29 arise because it is not possible to foresee a sequence of operations allowing an acceptable classification of patterns in every possible image; a recognition sequence depends on the characteristics of the image at hand. ' In manual or interactive approaches to image understanding, at each step of the process the execution of an operation produces results that the human operator evaluates before choosing the next operations.…”

Toward a semi-automatic interpretation of scenes issued from multisensor satellite images

“…The hypothesis is the basic data unit of the blackboard and represents a partial solution. The agents are invoked by the control mechanism in response to a particular change on the blackboard which is the event [1].…”

“…Direct measurements are not sufficient to provide an understanding of the forces driving change. Linking spatial and temporal observations to empirical models provides a comprehensive approach to understanding land-cover change [1]. One promising class of models designed to simulate and interpret are multi-agent system based on blackboard architecture which used as a collection of intelligent agents gathered around a hierarchical blackboard, looking for information written on it, thinking about the current state of the solution, and writing their generated conclusions on it.…”

Incremental Coordination for Time-Bounded Agents

“…The PGPP is another approach that extends the contract-net to resource-bounded agents. The GPGP [6] integrated dynamic and real-time agents while PGPP integrates the progressive processing agents to deal with dynamic and time-constrained situations. PGP [7], TRACONET [24] and MARS [10] are introduced to coordinate agents but they do not take limited rationality of agents into consideration.…”