Dynamic Cascade Spiking Neural Network Supervisory Controller for a Nonplanar Twelve-Rotor UAV DOI Creative Commons
Peng Cheng, Guanyu Qiao, Bing Ge

и другие.

Sensors, Год журнала: 2025, Номер 25(4), С. 1177 - 1177

Опубликована: Фев. 14, 2025

Unknown variables in the environment, such as wind disturbance during a flight, affect accurate trajectory of multi-rotor UAVs. This study focuses on intelligent supervisory neurocontrol tracking for nonplanar twelve-rotor UAV to address this issue. Firstly, is developed with structure, which makes up defects conventional multi-rotors weak yaw movement. A characteristic model devised so facilitate controller design without losing information. For purpose achieving and fast strong self-learning ability, an composite combining adaptive sliding-mode feedback control dynamic cascade spiking neural network (DCSNN) feedforward proposed. The novel structure constructed better adapt changing data unstable environments. weight learning algorithm work together ensure stability robustness. Finally, comparative numerical simulations prototype experiments verify superior performance, even outdoors disturbances.

Язык: Английский

Dynamic Cascade Spiking Neural Network Supervisory Controller for a Nonplanar Twelve-Rotor UAV DOI Creative Commons
Peng Cheng, Guanyu Qiao, Bing Ge

и другие.

Sensors, Год журнала: 2025, Номер 25(4), С. 1177 - 1177

Опубликована: Фев. 14, 2025

Unknown variables in the environment, such as wind disturbance during a flight, affect accurate trajectory of multi-rotor UAVs. This study focuses on intelligent supervisory neurocontrol tracking for nonplanar twelve-rotor UAV to address this issue. Firstly, is developed with structure, which makes up defects conventional multi-rotors weak yaw movement. A characteristic model devised so facilitate controller design without losing information. For purpose achieving and fast strong self-learning ability, an composite combining adaptive sliding-mode feedback control dynamic cascade spiking neural network (DCSNN) feedforward proposed. The novel structure constructed better adapt changing data unstable environments. weight learning algorithm work together ensure stability robustness. Finally, comparative numerical simulations prototype experiments verify superior performance, even outdoors disturbances.

Язык: Английский

Процитировано

1