Extracting Human Levels of Trust in Human–Swarm Interaction Using EEG Signals

Abstract

Trust is an essential building block of human civilization. However, when it relates to artificial systems, it has been a barrier to intelligent technology adoption in general. This article addresses the gap in determining levels of trust in scenarios that include humans interacting with a swarm of robots. Electroencephalography (EEG) recordings of the human observers of the different swarms allow for extracting specific EEG features related to different trust levels. Feature selection and machine learning methods comprise a classification system that would allow recognition of different levels of human trust in those human–swarm interaction scenarios. The results of this study suggest that EEG correlates of swarm trust exist and are distinguishable in machine learning feature classification with very high accuracy. Moreover, comparing common EEG features across all human subjects used in this study allows for the generalization of the classification method, providing solid evidence of specific areas and features of the human brain where activations are related to levels of human–swarm trust. This work has direct implications for effective human–machine teaming with applications to many fields, such as exploration, search and rescue operations, surveillance, environmental monitoring, and defense. In these applications, quantifying levels of human trust in the deployed swarm is of utmost importance because it can lead to swarm controllers that adapt their output based on the human's perceived trust level.