Human Agent Teaming: Cognitive Shadowing

Project
Human-AI Collaboration for Adaptive Command and Control

Summary
Autonomous systems face a major socio-technical integration challenge when they must collaborate with human operators, and that challenge is hindering their effectiveness and use. Specifically, human-AI agent teamwork comes with cognitive costs and new skill requirements for shared understanding and mutual adaptation. We propose to help overcome these shortcomings through human-AI co-learning of teamwork and taskwork. An adaptive command and control (C2) process with adjustable human-autonomy collaboration is therefore proposed herein. This framework will be developed and tested in simulated maritime operations scenarios where a human supervisory controller manages several unmanned vehicles to perform tasks in challenging environments requiring agility. Experiments using a simulated environment will measure the impacts of augmenting the human-autonomy system with the envisioned co-learning, shared understanding, and adaptive C2 capabilities. The main benefits of this partnership for the industry are to: 1) contribute to the acquisition of knowledge for the design of efficient human-agent systems; 2) to offer new perspectives in applied cognitive science on the collaboration between human and artificial intelligence; and 3) iteratively test successive versions of a proof of concept. These advances will allow the industrialization of solutions that will help improve public safety and transportation and, more generally, Quebec's competitiveness in terms of advanced digital technologies.