Psychophysiological Monitoring of Crew State for Extravehicular Activity
A spacewalk, or extravehicular activity (EVA), is one of the most mission critical and physically and cognitively challenging tasks that crewmembers complete. With next-generation missions to the Moon and Mars, exploration EVA will challenge crewmembers in partial gravity environments with increased frequency, duration, and autonomy of operations. Given the distance from Earth, associated communication delays, and durations of exploration missions, there is a monumental shift in responsibility and authority taking place in spaceflight; moving from Earth-dependent to crew self-reliant. For the safety, efficacy, and efficiency of future surface EVAs, there is a need to better understand crew health and performance. With this knowledge, technology and operations can be designed to better support future crew autonomy.
The focus of this dissertation is to develop and evaluate a psychophysiological monitoring tool to classify cognitive workload during an operationally relevant EVA task. This was completed by compiling a sensor suite of commercial wearable devices to record physiological signals in two human research studies, one at Virginia Tech and one at NASA Johnson Space Center. The approach employs supervised machine learning to recognize patterns in psychophysiological features across different psychological states. This relies on the ability to simulate, or induce, cognitive workload in order to label data for training the model. A virtual reality (VR) Translation Task was developed to control and quantify cognitive demands during an immersive, ambulatory EVA scenario. Participants walked on a passive treadmill while wearing a VR headset to move along a virtual lunar surface. They walked with constraints on time and resources, while simultaneously identifying and recalling waypoints in the scene. Psychophysiological features were extracted and labeled according to the task demands, i.e. high or low cognitive workload, for the novel Translation Task, as well as for the benchmark Multi-Attribute Task Battery (MATB). Predictive models were created using the K Nearest Neighbor (KNN) algorithm.
The contributions of this dissertation span the simulation, characterization, and modeling of cognitive state. Ultimately, this work tests the limits of extending laboratory psychophysiological monitoring to more realistic environments using wearable devices, and of generalizing predictive models across participants, times, and tasks. This work paves the way for future field studies and real-time implementation to close the loop between human and automation.