This is a HYRBID event with a VIRTUAL SPEAKER. The GRASP on Robotics Seminar will be streamed for in-person attendees in Wu and Chen and virtual attendees may join the talk via Zoom.

ABSTRACT

Every team has top performers — people who excel at working in a team to find the right solutions in complex, difficult situations. These top performers include nurses who run hospital floors, emergency response teams, air traffic controllers, and factory line supervisors. While they may outperform the most sophisticated optimization and scheduling algorithms, they cannot often tell us how they do it. Similarly, even when a machine can do the job better than most of us, it can’t explain how. The result is often an either/or choice between human and machine. In this talk I share the Situational Awareness Framework for Explainable AI (SAFE-AI), and discuss the ways in which traditional XAI methods can promote or undermine human situation awareness. I also share our lab’s latest research in employing the framework to effectively blend the unique decision-making strengths of humans and LLM- and RL-enabled machines.