Unmanned Aircraft Trajectory Prediction Based on Isolated Forest and LSTM Algorithm
Yizhi Wang, Hanbao Wu, Hao Liu, Shanqiang Zhang · 2021 IEEE International Conference on Unmanned Systems (ICUS) · 2021
Nowadays, the technology of unmanned aircraft trajectory prediction has been more mature. But one of the reasons that affect the accuracy of the prediction curve is the inevitable systematic error of the radar itself. In addition, outliers and random oscillations generated in the process of data acquisition and transmission will also interfere with the prediction results. In order to solve this problem, we use Isolated Forest algorithm for data cleaning, and design a parallel LSTM system to deal with the inherent system error of radar. Experiments show that the performance of this method is improved compared with the mainstream methods.