Automating maintenance for a one-way transmitting blackboard system used for autonomous multi-tier control

The blackboard architecture has particular utility in applications where conclusions must be drawn in the absence of human involvement. Through properly crafted rules, this approach can determine what a collection of data may mean. This can be utilized by other onboard software to limit transmission to only relevant data or conclusions. Some applications, such as robotic exploration, may preclude or severely limit the availability of controller‐to‐craft‐agent communications. In this case, the maintenance of the system must be performed autonomously.This paper discusses common maintenance tasks that may be relevant to a long‐running blackboard‐based system (e.g. clearing extraneous data from the blackboard regularly to improve performance, archiving relevant but infrequently used data for performance enhancement). A system for automating these tasks is presented that is suitable for most blackboard‐style systems. Its particular utility to those that cannot be easily accessed is discussed. Quantitative analysis of the value of removing rules from the system is performed and presented, and these results are extrapolated to several prospective blackboard maintenance approaches.