Mica Endsley

SA Technologies, U.S.A.

Lecture. Supporting Human-AI Teams: Transparency, Explainability, and Situation Awareness

Abstract.

   System autonomy and AI are being developed for a wide variety of applications where it will need to be able to work closely with people, forming human-AI teams (HAT). As AI capabilities grow, even more effective teaming behaviors will be expected of AI systems to support flexible implementations and mutual support.

   Situation awareness (SA) of autonomous systems and AI is critical for effective interaction with AI and for oversight of these systems. To build AI that works effectively as a part of a human-AI team there will also be an increased need for shared SA between the human and AI teammates.  Methods for supporting team SA within HAT will be discussed and a framework for understanding the types of information that needs to be shared within HATs, including a focus on taskwork SA, agent SA, and teamwork SA.  

   AI based on learning systems also creates new challenges for the development of good SA and mental models. AI transparency and explainability are discussed in terms of their separate roles for supporting SA, trust, and mental models in HAT. A systematic methodology for developing transparent AI displays for HAT will be presented.

Bio. Dr. Endsley is president of SA Technologies and a former Chief Scientist of the U.S. Air Force.  She has also held the positions of Visiting Associate Professor at MIT in the Department of Aeronautics and Astronautics and Associate Professor of Industrial Engineering at Texas Tech University. Dr. Endsley is a recognized world leader in the design, development and evaluation of systems to support human situation awareness (SA) and decision-making, as well as methods for improving SA through training of individuals and teams. She has published over 200 articles on situation awareness and the effects of AI and automation on human performance. Dr. Endsley has a PhD in Industrial & Systems Engineering from the University of Southern California and is a fellow and former President of the Human Factors and Ergonomics Society.

Reading. https://www.sciencedirect.com/science/article/abs/pii/S0747563222003946