Inferring individual evaluation criteria for reaching trajectories with obstacle avoidance from EEG signals

When we avoid obstacles while reaching out for an object, we make sure that our arm passes the obstacle with sufficient margin. This comfort margin varies across users and is displayed as challenging environmental constraints. When passing a fragile object, risk adverse individuals may adopt a larger margin than risk-prone people. The deviation from the traditional quasi straight line is less efficient, as it leads to a longer path to the target. This study investigates whether such individual preference results from differentiated weighting given to energy minimization versus comfort, and monitors brain error-related potentials (ErrP) evoked when subjects observe a robot moving dangerously close to a fragile object. Seventeen healthy participants monitored a robot performing safe, daring and unsafe trajectories around a wine glass. Each participant displayed distinct evaluation criteria. ErrPs were consistent with such individual specific evaluation. A subject specific linear classifier trained to predict subject’s individual response encapsulated with high predictability individual specific weighting across energy efficiency and comfort. This study suggests that ErrPs could be used in conjunction with an optimal control approach to identify cost used by one individual’s central nervous system. It further opens new avenues for the use of brain-evoked potential to train assistive robotic devices through the use of neuroprosthetic interfaces.