AUTHOR=Duan Xu , Xie Songyun , Xie Xinzhou , Meng Ya , Xu Zhao 

TITLE=Quadcopter Flight Control Using a Non-invasive Multi-Modal Brain Computer Interface

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 13 - 2019

YEAR=2019

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2019.00023

DOI=10.3389/fnbot.2019.00023

ISSN=1662-5218

ABSTRACT=Brain-Computer Interface (BCI) translate neuronal information into commands to control external software or hardware, which can improve the quality of life for both healthy and disabled individuals. Here, a multimodal BCI which combined motor imagery (MI) and steady-state visual evoked potential (SSVEP) was proposed to achieve stable control of a quadcopter in three-dimensional physical space. The complete information common spatial pattern (CI-CSP) method was used to extract two MI features to control the quadcopter flying left-forward and right-forward, and canonical correlation analysis (CCA) was employed to perform the SSVEP feature classification for rise and fall. Eye blinking was designed to switch these two modes while hovering. The real-time feedback was provided to the subject by a global camera. Two flight tasks were conducted in physical space in order to certify the reliability of the BCI system. Subject was asked to control the quadcopter flying forward along the zig-zag pattern to pass through a gate in relatively simple task. For more complex task, the quadcopter was controlled to pass through two gates successively according to an S-shaped route. The performance of the BCI system is quantified using suitable metrics and the subject is able to acquire 90% of accuracy for the relatively complicated flight task. It is demonstrated that multi-modal BCI has the ability to increase both the degree-of-freedom and accuracy, and improve the performance of BCI system in the real-world.