Precise trajectory planning is crucial in terms of enabling unmanned aerial vehicles (UAVs) to execute interference avoidance and target capture actions in unknown environments and when facing intermittent target loss. To address the trajectory planning problem of UAVs in such conditions, this paper proposes a UAV trajectory planning system that includes a predictor and a planner. Specifically, the system employs a bidirectional Temporal Convolutional Network (TCN) and Gated Recurrent Unit (GRU) network algorithm with an adaptive attention mechanism (BITCN-BIGRU-AAM) to train a model that incorporates the historical motion trajectory features of the target and motion intention the inferred by a Dynamic Bayesian Network (DBN). The resulting predictions of the maneuvering target are used as terminal inputs for the planner. An improved Radial Basis Function (RBF) network is utilized in combination with an offline–online trajectory planning method for real-time obstacle avoidance trajectory planning. Additionally, considering future practical applications, the predictor and planner adopt a parallel optimization and correction algorithm structure to ensure planning accuracy and computational efficiency. Simulation results indicate that the proposed method can accurately avoid dynamic interference and precisely capture the target during tasks involving dynamic interference in unknown environments and when facing intermittent target loss, while also meeting system computational capacity requirements.

Optimization based on conventional neural networks can only guarantee calculation speed. However, the accuracy of network prediction is also a key index in online trajectory optimization. This paper proposes a novel online trajectory optimization approach based on an Improved Radial Basis Function Neural Network (IRBFNN). First, multiple optimal trajectories for different variations of Air-Breathing Supersonic Vehicles (ASVs) are generated, considering attitude, and collected as the dataset. Then, an IRBFNN is trained to predict trajectories online with the above dataset, in which an enhanced loss function is introduced to improve prediction accuracy. Finally, numerical simulations are presented to demonstrate the feasibility and superiority of the proposed online trajectory optimization method. The open-source code of the proposed method is shared in the form of a link to showcase its implementation.