Learning User Preferences for Trajectories from Brain Signals

Robot motions in the presence of humans should not only be feasible and safe, but also conform to human preferences. This, however, requires user feedback on the robot's behavior. In this work, we propose a novel approach to leverage the user's brain signals as a feedback modality in order to decode the judgment of robot trajectories and rank them according to the user's preferences. We show that brain signals measured using electroencephalography during observation of a robotic arm's trajectory as well as in response to preference statements are informative regarding the user's target trajectory. Furthermore, we demonstrate that user feedback from brain signals can be used to reliably infer pairwise trajectory preferences as well as to retrieve the target trajectories of the user with a performance comparable to explicit behavioral feedback.

Automated summary

This paper proposes a novel method to utilize user's brain signals as feedback to decode and rank robot trajectories based on user preferences. The research shows that brain signals measured during observation of a robot's trajectory can effectively reflect the user's target trajectory. Furthermore, user feedback from brain signals can be used to infer trajectory preferences and retrieve target trajectories with comparable performance to explicit behavioral feedback.