With the rapid development of drone technology, its applications in areas such as aerial photography, logistics, and environmental monitoring are becoming increasingly widespread. However, the complexity of low altitude flight environments poses a serious challenge to the collision avoidance capabilities of drones. A study has proposed an autonomous control method based on fuzzy neural networks. This method combines the ability of fuzzy logic to handle uncertainty and fuzzy information, as well as the powerful learning and generalization capabilities of neural networks, aiming to achieve accurate prediction of drone flight status and intelligent generation of collision avoidance strategies. By constructing a fuzzy neural network model, taking the flight parameters, environmental information, and obstacle data of the drone as inputs, and training and optimizing the network, collision avoidance control instructions are output to achieve autonomous control of the drone. The experimental results show that the proposed fuzzy neural network autonomous control method exhibits good collision avoidance performance in low altitude flight scenarios. This method can effectively identify and avoid obstacles, ensuring the safe flight of the drone. At the same time, this method has high real-time performance and robustness, and can work stably in complex and changing environments. This study not only provides a new solution for the collision avoidance problem of unmanned aerial vehicles in low altitude flight scenarios, but also offers new ideas for the application of fuzzy neural networks in the field of autonomous control of unmanned aerial vehicles.
Li et al. (Wed,) studied this question.