On-Orbit Operations Simulator for Workload Measurement during Telerobotic Training

Training for telerobotic systems often makes heavy use of simulated platforms, which ensure safe operation during the learning process. Outer space is one domain in which such a simulated training platform would be useful, as On-Orbit Operations (O3) can be costly, inefficient, or even dangerous if not performed properly. In this paper, we present a new telerobotic training simulator for the Canadarm2 on the International Space Station (ISS), and record physiological data from subjects as they perform a task from the simulator under conditions which increased workload (e.g. latency and time pressure). As most current workload measures are subjective and non-continuous, we analyse how objective measures from the simulator and physiological data can provide a more reliable and continuous measure. ANOVA of task data revealed which simulator-based performance measures could predict the presence of latency and time pressure. Furthermore, EEG classification using a Riemannian classifier and Leave-One-Subject-Out cross-validation showed promising classification performance. EEG results also reveal that Independent Component Analysis (ICA) preprocessing and centrally located channels are more discriminative for 5-class discrimination, whereas information derived from the EEG parietal channels was more accurate in two-class classification of latency and time pressure paradigms.