Presentation
I Am Too Tired for This! Designing Human-AI Teaming Studies to Examine and Mitigate the Effects of Cognitive Fatigue
SessionPoster Session 1
DescriptionHuman-AI teaming integrates the complementary capabilities of human adaptability and intuition with artificial intelligence (AI) speed and power to enhance performance in complex work environments. As AI systems are increasingly deployed as collaborative teammates, it is essential to understand factors that may degrade human performance, such as cognitive fatigue (CF). CF refers to a mental state arising from sustained cognitive effort, and can impair monitoring, decision-making, and overall team effectiveness. This paper presents a structured framework for designing future studies to induce and measure CF in the context of human-AI teams. It reviews established induction tasks, including the Stroop and TloadDback paradigms, and differentiates between active and passive fatigue states. Experimental design considerations are discussed, emphasizing the alignment of task characteristics with the type of fatigue being elicited. To support manipulation checks and outcome assessment, we recommend the integration of subjective self-reports and objective physiological measures. Finally, we argue that AI systems should be designed as true teammates—supporting shared mental models and mutual adaptation—to mitigate fatigue-related risks. By advancing methods to study CF in human-AI teaming, this work contributes to the development of resilient, high-performing sociotechnical systems.
Event Type
Poster
TimeTuesday, October 14th5:30pm - 6:30pm CDT
LocationRiverside East