北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (5): 121-128.

• 研究报告 • 上一篇    

基于LSTM-KF的无人机航迹跟踪算法

刘金铭,张玉艳,张碧玲   

  1. 北京邮电大学 网络教育学院
  • 收稿日期:2021-10-28 修回日期:2022-03-31 出版日期:2022-10-28 发布日期:2022-11-01
  • 通讯作者: 张碧玲 E-mail:bilingzhang@ bupt. edu. cn

Trajectory Estimation Algorithm for Unmanned Aerial Vehicle Based on LSTM-KF

LIU Jinming, ZHANG Yuyan, ZHANG Biling #br#   

  1. School of Network Education, Beijing University of Posts and Telecommunications
  • Received:2021-10-28 Revised:2022-03-31 Online:2022-10-28 Published:2022-11-01
  • Contact: ZHANG Biling E-mail:bilingzhang@ bupt. edu. cn

摘要: 在量测信息有限的情况下,针对使用单一运动模型的卡尔曼滤波(KF)算法难以应对无人机航道跟踪的问题,提出了一种新颖的将长短期记忆网络(LSTM)KF 算法结合的 LSTM-KF 算法首先,使用 LSTM 预测目标平均速度和瞬时速度的方法解决了非参数模型在位置预测任务中泛化能力差的问题其次,分析了 KF 算法使用运动模型的预测局限性,提出利用 LSTM 的预测结果修正运动模型的预测结果的方法,来降低预测误差修正后的预测结果与量测数据结合,实现对目标的状态估计最后,将所提 LSTM-KF 算法在生成的轨迹上进行了验证,仿真结果证明,LSTM-KF 算法比已有模型具有更高的跟踪精度和更强的鲁棒性

关键词: 无人机, 长短期记忆网络, 卡尔曼滤波, 航迹跟踪

Abstract:

In the case of limited measurement information, Kalman filter (KF) is difficult to deal with unmanned aerial vehicle tracking by using a single motion model. To solve this problem, a novel long short-term memory(LSTM)-KF algorithm combining LSTM and KF algorithm is proposed. First, LSTM is used to predict the average and instantaneous velocity of the target so that the problem of poor generalization ability of nonparametric model can be solved in position prediction task. Then, the prediction limitation of KF algorithm using motion model is analyzed, and the method of using LSTM prediction results to modify the prediction results of motion model is proposed to reduce the prediction error. The revised prediction results are combined with the measurement data to realize the state estimation of the target. Finally, the proposed algorithm is verified on the generated trajectory. The simulation results show that LSTM-KF algorithm has higher tracking accuracy and stronger robustness than the existing models.

Key words: unmanned aerial vehicle,  long short-term memory, Kalman filter, trajectory tracking

中图分类号: