基于Transformer模型的四旋翼无人机时空协同航迹预测方法设计

无人机在执行任务时面临的飞行环境复杂多变，为了减少事故的风险，并在飞行时对异常情况进行预测和响应，研究一种基于Transformer模型的四旋翼无人机时空协同航迹预测方法。采集四旋翼无人机原始航迹，实施异常点剔除和缺失点插值处理，以优化和清理原始航迹数据，便于后续的航迹预测。结合深度学习和表示学习方法完成数据降维，基于Transformer模型实现无人机时空协同航迹的精准预测。实验测试结果表明，设计方法的预测结果虽然相对于真实的坐标点稍有偏差，然而整体结果在可接受范围内，验证集所有数据的均方误差在数据条数为300时仅为0.32m，R方测试结果最接近1，具有良好的航迹预测能力。

Design of spatiotemporal collaborative trajectory prediction method for quadcopter unmanned aerial vehicles based on Transformer model

In order to reduce the risk of accidents and predict and respond to abnormal situations in the complex and ever-changing flight environment faced by unmanned aerial vehicles (UAVs) during mission execution, a spatiotemporal collaborative trajectory prediction method based on Transformer model for quadcopter UAVs is studied. Collect the original trajectory of a quadcopter drone, implement outlier removal and missing point interpolation processing to optimize and clean up the original trajectory data for subsequent trajectory prediction. By combining deep learning and representation learning methods, data dimensionality reduction is achieved, and precise prediction of unmanned aerial vehicle spatiotemporal cooperative trajectories is achieved based on the Transformer model. The experimental test results show that although the prediction results of the design method have a slight deviation from the actual coordinate points, the overall results are within an acceptable range. The mean square error of all data in the validation set is only 0.32m when the number of data is 300, and the R-square test result is closest to 1, indicating good trajectory prediction ability.