Efficient Quadcopter Flight Control Using Hybrid SSVEP + P300 Visual Brain Computer Interface

ABSTRACT

The objective of this study was to assess the feasibility of hybrid SSVEP + P300 visual BCI systems for quad-copter flight control in physical world. Existing BCI-based quad-copter flight control has limitations of slow navigation, lower system accuracy, rigorous user training requirement and lesser number of independent control commands. So, there is need of hybrid BCI design that combines evoked SSVEP and P300 potentials to control flight direction of quad-copter movement. GUI design is developed such that user can effectively control quad-copter flight by gazing at visual stimuli buttons that produce SSVEP & P300 potentials simultaneously in human cortex. We compare the performance metrics of the proposed flight control systems with other existing BCI-based flight control as conventional SSVEP BCI and P300 BCI and commercially available keyboard flight control systems. Results proved that the proposed system outperforms the existing BCI-based flight control systems but has slightly lower performance efficiency than the commercial keyboard flight control systems. Further, the proposed quad-copter flight control system proved its suitability for patients with severe motor disabilities.

Disclosure of potential conflict of interest

None of the authors has any conflict of interest.

Ethical approval

All procedures performed in this study involving human participants were in accordance with the ethical standards of the Nagpur university research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. Research Recognition Committee (RRC) of Nagpur University approves this research work with approval number “RTMNU/RRC/Engg./2729”.

Informed consent

As per Good Clinical Practices (GCP) certification suggestions, a written consent (informed consent) was taken from all participants.

Additional information

Notes on contributors

Deepak Kapgate

Deepak Kapgate completed his PhD in Computer Science and Engineering. His area of interest include Machine Learning, Optimization and Brain-Compter Interface.