Learning User Preferences for Trajectories from Brain Signals

TL;DR

This paper introduces a method to decode user preferences for robot trajectories from brain signals, enabling robots to adapt to human preferences using EEG data during observation and feedback.

Contribution

It presents a novel approach to infer user preferences from EEG signals, allowing preference-based robot motion adaptation without explicit feedback.

Findings

EEG signals during observation encode preference information

Brain signals can reliably infer pairwise trajectory preferences

Performance comparable to explicit feedback in trajectory retrieval

Abstract

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 preference. Furthermore, we demonstrate that user feedback from brain signals can be used to reliably infer pairwise trajectory preferences as well as to retrieve the preferred observed trajectories of the user with a performance comparable to explicit behavioral feedback.