Spencer K. Lynn1, Susan S. Latiff1, William Norsworthy1, Jr., Mark Turner2, Peter Weyhrauch1
Interservice/Industry Training, Simulation, and Education Conference (I/ITSEC), Orlando, Florida (4 December 2024)
How do we create artificially intelligent agents capable of meaningful and trusted teaming with humans for training and operations? “Common ground” refers to congruent knowledge, beliefs, and assumptions among a team about their objectives, context, and capabilities. It has been a guiding principle in cognitive systems engineering for human-AI interaction, where research has focused on improving communication between human and machines. Coordination (e.g., directability) and transparency (e.g., observability and predictability) are important for establishing, maintaining, and repairing both human-AI and human-human common ground. Nonetheless, human-AI common ground remains relatively impoverished, and AI remains a tool rather than a teammate Communication between humans and machines plays a crucial role in establishing the machine’s state. Conversely, when machines communicate with humans, it provides transparency by revealing the machine’s state to the human. Among humans, common ground occurs at the level of concept structure; however, human concepts are not merely variables to be parameterized, but are constructed during discourse. For example, an instructor uses communication to activate and shape concepts (through dialog) in the student’s mind, contextualizing and refining concepts until shared perceptions are categorized (understood) in a common way. To increase autonomy and human-AI teaming, the challenge is to provide the AI with human-like conceptual structure. An architecture to enable human-AI common ground must provide the AI with representational capacity and algorithms that mimic features of human conceptual structure and flexibility. Here, we identify critical features of human conceptual structure, including Conceptual Blending, Situated Categorization, and Concept Degeneracy. We evaluate challenges of implementing these features in AI and we outline technical approaches for hybrid symbolic/subsymbolic AI to meet those challenges. As contemporary human-factors approaches to human-AI common ground continue to mature, common ground issues will move from interface transparency to concept congruency
1 Charles River Analytics
2 Case Western Reserve University
For More Information
To learn more or request a copy of a paper (if available), contact Spencer Lynn.
(Please include your name, address, organization, and the paper reference. Requests without this information will not be honored.)
