Brain-Computer Interfaces in Navigation and Control of Quadcopters

This narrative review synthesizes recent advancements in brain-computer interface (BCI) technologies for the navigation and control of quadcopters. Focusing on developments over the past five years, the article explores multi-modal neural decoding approaches—such as motor imagery, steady-state visual evoked potentials (SSVEPs), and eye blinking—and their integration with sophisticated signal processing and machine learning algorithms to enhance command accuracy and reduce cognitive workload during drone operation. The review traces historical progress from early EEG-based speller systems to real-time aerial control, emphasizing the critical role of hybrid and adaptive models in improving system robustness and user experience. Key challenges persist, including asynchronous continuous control, environmental variability, mode-switching complexity, and long-term user adaptation, which currently limit widespread deployment. The discussion highlights practical applications in assistive technology, hazardous environment operation, defense, and education, while acknowledging ethical and safety concerns. The review concludes by identifying future directions such as scalable multi-drone control, deeper integration with autonomous flight systems, and the establishment of standardized protocols to accelerate clinical and operational translation. Overall, this work provides a comprehensive framework that encapsulates both the promise and the complexity of BCI-enabled quadcopter navigation, underlining its transformative potential across interdisciplinary domains.

کلیدواژه ها:

Brain-computer interfaces ، Electroencephalography (EEG) ، Multi-modal neural decoding ، Quadcopter navigation ، Signal processing algorithms ، User cognitive load