SIFT has pioneered a human-automation integration architecture, called Playbook™, based on a shared model of the tasks in the domain. This shared task model provides a means of human-automation communication about plans, goals, methods and resource usage—a process akin to referencing plays in a sports team's playbook. The Playbook enables human operators to interact with subordinate systems with the same flexibility as with well-trained human subordinates, thus allowing for adaptive automation. We describe this approach and its application in an ongoing project called Playbook-enhanced Variable Autonomy Control System™ (P-VACS).
A central source of cultural differences, with powerful impacts on perception and behavior, is communication of "politeness" and its role power and familiarity relationships, urgency, indebtedness, etc. We are operationalizing and making computational a culturally abstract and universal theory of human politeness which combines culture-specific aspects of social context (power and familiarity relationships, imposition, character), to produce expectations about politeness behaviors (also culturally defined). Such a model will enable better training materials, simulations, and even better decision aids. By using observations of politeness behaviors (or their lack), the same model can infer those attributes. We describe our algorithm and results from two validation experiments. We have used this model to guide simulated game agents in interpreting and generating politeness behaviors and have demonstrated promise for reducing software development costs and/or increasing an agent's behavior repertoire through the creation of modular, crosscultural etiquette libraries.
Knowledge Acquisition (KA) is important throughout systems development for gathering expert domain knowledge that is incorporated into the requirements and design of a system. There are problems ensuring that accurate and useful knowledge is captured initially, refined as needed, and transferred to later development efforts in a usable format. We present a method, called tagging, for addressing these problems without undue burden on the KA practitioners, along with initial studies to examine the feasibility of real-time tagging and to inform the design of a tool called TAGGER. TAGGER operates by permitting KA discussions to be "tagged" as they happen with concepts and groupings relevant to software development.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.