Online Trajectory Optimization of an ASV Based on an Improved RBFNN

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.