Dynamic Cascade Spiking Neural Network Supervisory Controller for a Nonplanar Twelve-Rotor UAV

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