Research Interests
human-robot interaction, human-robot teaming, driver-vehicle interaction, autonomous vehicles, trust, situation awareness
Estimating and Calibrating Situation Awareness for Improving Human-Robot Teaming Performance
Funded by the Automotive Research Center (2022-2025)
The objective of this research project was to develop methods for estimating and calibrating situation awareness in human-robot teams to optimize their overall performance. A multi-phase solution was used. An experiment on how shared mental models and communication amount impact team situation awareness contributed with an expression of team situation awareness and demonstration of how shared mental models are critical for team situation awareness when communication is limited. Next, an experiment on communication sources clarified the crucial role of external communication in enhancing human situation awareness. Then, a situation awareness system that estimates human situation awareness in real-time and adapts robot behavior in response was developed and evaluated. Through experimentation, the situation awareness system was demonstrated to improve situation awareness and performance.
Journal and conference papers from these projects are currently under review.
Building Trust across Dynamic, Heterogeneous Teams
Funded by U.S. Army Research Laboratory Strengthening Teamwork for Robust Operations in Novel Groups (STRONG) (2021-2022)
The goal of this project was to allocate indivisible tasks to agents on a human-robot team in order to increase performance and achieve a common goal. A novel task allocation method based on trust in each teammate was proposed with the ability to learn unknown agent capabilities and allocate both familiar and new tasks. The task allocation method was demonstrated to outperform other methods.
This work is detailed in an article published in Scientific Reports.
Driver Takeover Study in Highly Automated Vehicles
Oakland University Honors College Thesis funded in part by the Office of the Provost & Vice President for Academic Affairs (2019-2020)
The purpose of this study was to understand how common non-driving related tasks impact a driver’s takeover performance. In highly automated vehicles, a driver is required to takeover control from the automated system and manually drive in the event of a situation that automation cannot handle. However, it is possible the driver became occupied with an alternate, non-driving related task and no longer has the proper situation awareness to safely takeover driving before automation is disengaged. To study the effects of non-driving related tasks on takeover performance, important non-driving related tasks were determined through a questionnaire and a realistic driving simulator was constructed.
This work is documented in an paper at the National Conference on Undergraduate Research. Additional details on the background literature, takeover study, and preliminary results are documented in my Honors College thesis.