AI-Based Workload Monitoring to Enhance Human-Machine Symbiotic Collaboration
Abstract
Command and Control (C2) of current autonomous or semi-autonomous systems such as swarms is still amajor challenge due to immense operator workload and difficulty in representing and communicatingmission goals, tasks, values and situation awareness across the human-machine boundary [1]. Providingadequate support to the human operator requires intelligent systems to acquire situation awareness notonly on the environment but also on the human operators cognitive state and resulting performance.Moreover, providing adaptive support to human operators will enhance trust between the humanmachineteam by making the agent more receptive to human needs [2].Current Naval intelligent systems are still unable to effectively perceive and understand the humanoperators moment-to-moment needs. This results in a lack of effective adaption in agents by failing toprovide dynamic and flexible support to human operators. Thus, there is a need to develop methods forphysiological and behavioral measurement of operators cognitive states that intelligent and autonomousagents can use to make allocation decisions in complex supervisory control mission scenarios (i.e., so thatan agents response can be truly adaptable). In addition, using operators cognitive states, adaptive controlsystems can be developed that reduce workload and promote teamwork between humans and machines.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 31, 2020
- Source ID
- N629092012063
Entities
People
- Caroline Vandevyver
Organizations
- Office of Naval Research
- Swiss Federal Institute of Technology in Lausanne
- United States Navy