2025 Speaker Series
May 28, 2025
Estimating Human Cognitive States when Teaming with Autonomous Systems in Space
1:00-2:00 PM MST
Allison Hayman
Associate Professor, Smead Aerospace Engineering Sciences, University of Colorado at Boulder
Abstract: Autonomous systems are increasingly integrated into society. Their use in operational environments, such as space, combat areas, or warehouses, have the potential to improve mission effectiveness, enable new ways of performing work, and reduce risks to human safety. Operating in space is a particularly challenging domain for human-autonomy teaming. Future human long duration exploration missions will need to be increasingly autonomous as crews travel farther from Earth. Deep space habitats will face uncrewed periods and remote operation under increased latency and limited bandwidth. Space-based satellites and operations are also being imbued with autonomy. Satellite operators are separated spatially and temporally from the systems with which they are working, reducing their ability to have context of the satellite’s state. Future autonomous systems will need to serve as better teammates to operators on Earth by leveraging real-time estimates of human cognitive states to intelligently adjust their behavior. This talk will discuss our research to address these challenges. To provide an autonomous system estimates of operator cognitive states, we aim to model an operator’s trust, workload, and situation awareness (TWSA) using data recorded from psychophysiological sensors. This work develops models of TWSA from electrocardiogram, respiration rate, electrodermal activity, and gaze data recorded as human operators perform a simulated habitat maintenance supervisory task. I also discuss our work to investigate trust dynamics and how trust develops over time as someone continues to interact with autonomous systems. Here, we focus on remote satellite operators who are working in a supervisory manner, but rely on the autonomous satellite system to perform their jobs. In sum, this work addresses human cognitive state estimation in human autonomy teaming by focusing on understanding the person in the spaceflight environment.
Bio: Allison Hayman is an Associate Professor in the Smead Aerospace Engineering Sciences Department at the University of Colorado Boulder. She graduated in 2007 with a B.S. in Astronautics Engineering from the University of Southern California with a minor in Astronomy. She received an M.S. in Aerospace Engineering and an M.S. in Technology Policy in 2011 from the Massachusetts Institute of Technology (MIT), and a Ph.D. in Aerospace Biomedical Engineering in 2014 from MIT. She received a postdoctoral fellowship from the National Space Biomedical Research Institute to study human space physiology at the Dartmouth-Hitchcock Medical Center. At the University of Colorado – Boulder she is also affiliated with Integrative Physiology Department, Biomedical Engineering program, and the Robotics program. Her work focuses on human-autonomy teaming, aerospace biomedical engineering, spacesuit design, wearable sensors, spacecraft habitat design, alternative reality technologies, and human physiology in extreme environments. Specifically, her work is directed toward understanding human performance in operational environments.

March 21, 2025
On the Structure and Consequences of Humans Interacting with Autonomous Agents
9:00-10:00 AM MST
Katie Driggs-Campbell, Electrical and Computer Eng., University of Illinois
Abstract: Autonomous systems are becoming prevalent in our everyday lives and are changing the foundations of our way of life. However, the desirable impacts of autonomy are only achievable if the underlying algorithms can handle the unique challenges humans present. In this talk, we will first discuss how inferring hidden states (e.g., driver traits, pedestrian intent) coupled with robust prediction methods can be used to improve human-robot interaction. We’ll demonstrate how we can combine insights through graphical representations to produce safe, interactive policies for social navigation. Then, we will discuss the consequences of repeated interactions over time and how these agents may influence one another. We experimentally demonstrate that generating influential robot behaviors becomes less effective over repeated interactions. We then provide solutions to maintain influence for effective interaction that is both safe, interactive, and efficient.
Bios: Katie Driggs-Campbell is currently an assistant professor at the University of Illinois at Urbana-Champaign in the Department of Electrical and Computer Engineering, with an affiliate appointment in the Department of Computer Science. Prior to joining Illinois, she received a B.S.E. with honors from Arizona State University in 2012 and an M.S. from UC Berkeley in 2015. She earned her PhD in 2017 in Electrical Engineering and Computer Sciences from the University of California, Berkeley. After that, she was a Postdoctoral Research Scholar at the Stanford Intelligent Systems Laboratory in the Aeronautics and Astronautics Department. Katie now runs the Human- Centered Autonomy Lab, which aims to design safe autonomous systems and robots that can safely interact with people out in the real-world. Katie is a recipient of the NSF CAREER award, the IEEE Robotics and Automation Society’s Early Academic Career Award, and multiple best paper awards (or runner ups) for her contributions to autonomous systems, robot learning, and human-centered AI.
