Blackboard-Based Framework for Mixed-Initiative, Crewed-Space-System Applications

An ideal way to organize large-scale, nearly autonomous, intelligent systems is by using a blackboard-based architecture in which computational knowledge modules interact with human operators when necessary. Blackboard architectures have demonstrated significant advantages in modularity, scalability, extensibility, distribution, heterogeneity of representations and problem-solving techniques, and dynamic control of problem-solving activities. We propose to make these advantages available to nearly autonomous manned-space-system applications by advancing the state of the art in integrating human operators into the problem-solving model of the blackboard paradigm. Specifically, we will focus on two key aspects of integrating computational knowledge with human operators.