A Blackboard-style decision-making system for multi-tier craft control and its evaluation

• Published in: Journal of experimental & theoretical artificial intelligence Vol. 27; no. 6; pp. 763 - 777
• Main Authors: Straub, Jeremy, Reza, Hassan
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 02.11.2015; Taylor & Francis Ltd
• Subjects: Artificial intelligence; Autonomous; autonomous control; blackboard architecture; Computer architecture; Control systems; Crafts; Decision making; Decision making models; Expert systems; Extrapolation; multi-tier control; robotic control; Robots
• ISSN: 0952-813X; 1362-3079
• DOI: 10.1080/0952813X.2015.1020569

This article presents an approach for decision-making in support of the control of an autonomous system of multiple tiers of robots (e.g., satellite, aerial and ground) based on the Blackboard architectural style. Under the proposed approach, the system evaluates prospective approaches for goal satisfaction (identified by user selected final rules), identifies the lowest-cost solution and determines the best path to achieving the goal, via the analysis of the Blackboard rule and action set. Two different approaches to this rule and action path generation are discussed. This article presents the proposed Blackboard-style architecture for autonomous multi-tier control and describes its implementation. The benefits and drawbacks of the Blackboard-style approach are analysed, its extrapolation to the control of multiple heterogeneous craft is presented and the tradeoffs between the two approaches to rule-path generation are assessed.