Mind Meets Robots: A Review of EEG-Based Brain-Robot Interaction Systems

TL;DR

An up-to-date review of 87 curated studies published between 2018 and 2023 is presented, identifying the research landscape of EEG-based BRI systems and proposing a BRI system model comprising three entities: Brain, Robot, and Interaction, depicting their internal relationships.

Abstract

Brain-robot interaction (BRI) empowers individuals to control (semi-)automated machines through their brain activity, either passively or actively. In the past decade, BRI systems have achieved remarkable success, predominantly harnessing electroencephalogram (EEG) signals as the central component. This paper offers an up-to-date and exhaustive examination of 87 curated studies published during the last five years (2018-2023), focusing on identifying the research landscape of EEG-based BRI systems. This review aims to consolidate and underscore methodologies, interaction modes, application contexts, system evaluation, existing challenges, and potential avenues for future investigations in this domain. Based on our analysis, we present a BRI system model with three entities: Brain, Robot, and Interaction, depicting the internal relationships of a BRI system. We especially investigate the essence and principles on interaction modes between human brains and robots, a domain that has not yet been identified anywhere. We then discuss these entities with different dimensions encompassed. Within this model, we scrutinize and classify current research, reveal insights, specify challenges, and provide recommendations for future research trajectories in this field. Meanwhile, we envision our findings offer a design space for future human-robot interaction (HRI) research, informing the creation of efficient BRI frameworks.

Figures (4)

• Figure 1: The common framework of a complete BRI system utilizing EEG.
• Figure 2: The research agenda of EEG-based BRI in the last few years: A: The number of publications (2013-2023) related to the search results of "EEG-based", "brain", "robot", and "interaction" in the four tested databases. An apparent growing trend is identified especially from 2018. B: The number of papers in our corpus for each year with publishers. For convenience, we listed three main publishers: IEEE, ACM, and Springer, while other publishers are noted as Others. C: The number of studies published for each year with countries.
• Figure 3: Flow chart of the corpus formulation process with the identification of databases and the initial search query (see Sections \ref{['search_stra']} and \ref{['search_term']}), and filtering, pre-selecting, and the manual screening (see Section \ref{['filter_screen']}), which resulted in 87 full papers.
• Figure 4: Overview of the BRI system model. The three entities: Brain, Interaction, and Robot, are distilled from our corpus. Human brains and robots are intercorrelated by the Interaction entity. Each entity is affiliated with several dimensions, while some of them are comprised of extra sub-dimensions.