A High-DOF BCI Control Strategy Mapping Discrete Commands to Continuous Motion for a Drone

Because of the non-stationary nature of electroen- cephalogram (EEG) signals, traditional non-invasive brain- computer interfaces (BCIs) usually only produce discrete commands, limiting their ability to control external devices continuously. This study proposes a novel BCI control strategy mapping multiple discrete commands to continuous motion, enabling real-time manipulation of a drone in four degrees of freedom (DOF). Our strategy used the fast steady state visual evoked potential (SSVEP) encoding and decoding method to convert user intentions into the drone’s flight status in near real-time. Simultaneously, the drone’s live video was embedded into the SSVEP stimuli, providing users with a first-person perspective control experience. In drone control experiments, participants successfully maneuvered the drone through complex path-following tasks in simulated and physical scenarios. The Received 27 October 2024; revised 24 April 2025; accepted 20 July 2025. Date of publication 29 July 2025; date of current version 28 August 2025. This article was recommended for publication by Associate Editor H. Lu and Editor P. Rocco upon evaluation of the reviewers’ comments. This work was supported in part by the Science and Technology Innovation (STI) 2030- Major Projects under Grant 2022ZD0210200; in part by the National Natural Science Foundation of China under Grant 62122059, Grant 81925020, Grant 82472101, and Grant 62206198; and in part by the Introduce Innovative Teams of 2021 “New High School 20 Items” Project under Grant 2021GXRC071. (Corresponding authors: Yongzhi Huang; Minpeng Xu.) This work involved human subjects or animals in its research. Approval of all ethical and experimental procedures and protocols was granted by the Research Ethics Committee of Tianjin University under Application No. TJUE-2022-192. Jie Mei and Ang Li are with the Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China, also with the Department of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin 300072, China, and also with the State Key Laboratory of Advanced Medical Materials and Devices, Tianjin 300072, China. Weize Chen is with the Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China, and also with the State Key Laboratory of Advanced Medical Materials and Devices, Tianjin 300072, China. Yongzhi Huang, Xiaolin Xiao, Kun Wang, Minpeng Xu, and Dong Ming are with the Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China, also with the Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration, Tianjin 300392, China, and also with Tianjin Key Laboratory of Brain Science and Neu- roengineering, Tianjin 300072, China (e-mail: yongzhi huang@tju.edu.cn; xmp52637@tju.edu.cn). Weibo Yi is with Beijing Institute of Mechanical Equipment, Beijing 100143, China. Tzyy-Ping Jung is with the Swartz Center for Computational Neuroscience, University of California at San Diego, La Jolla, CA 92093 USA, and also with the Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China. Data is available on-line at https://sites.google.com/view/bci-drone-control Digital Object Identifier 10.1109/TASE.2025.3593497 mean flight trajectory bias ratio was measured as 0.81, with a mean flight smoothness of -3.31 (measured by spectral arc length) and mean Fitts’s throughput of 9.18 bits/min. Notably, the brain-to-hand ratio (BHR) for all metrics approached 1, indi- cating that our non-invasive control system achieved comparable performance to manual control systems. These results suggest the effectiveness of our proposed BCI control strategy that maps discrete commands to continuous motion and extends the capabilities of non-invasive BCIs in continuous control scenarios. This study significantly advances the applications of BCI and propels human-machine interaction towards a more direct realm. Note to Practitioners—This work is motivated by the real- time and continuous control challenges in using non-invasive brain-computer interfaces (BCIs). Non-invasive BCIs establish a direct communication pathway between the human brain and external devices. Due to their safety and convenience, they are considered a promising human-machine interaction method for future practical applications. However, a major bottleneck is that non-invasive BCIs that generate discrete commands are unable to meet the demands of continuous control for external devices. Additionally, the low accuracy and high latency in decoding commands from human intent further distance current brain- control systems from practical application. In this paper, we propose a BCI strategy that includes a continuous encoding and decoding method for EEG signals. This strategy reduces the latency of command output while maintaining both the size of the command set and decoding accuracy. Furthermore, it introduces a method to map the decoded commands to continuous movements of external devices, effectively bridging the existing gap. We conducted extensive simulations and real- world experiments, demonstrating that the proposed strategy allows users to achieve continuous, real-time, four-degree-of- freedom control of a quadcopter using a non-invasive BCI. The analysis of results shows that, in terms of control accuracy, continuity, and operational efficiency, brain control is comparable to manual control. In the future, we aim to enhance the external devices with artificial intelligence to enable collaborative control between humans and machines, thereby advancing the practical development of BCIs.