Encoder-Decoder Multi-Step Trajectory Prediction Technology Based on LSTM

• Published in: Hangkong Bingqi Vol. 28; no. 2; pp. 49 - 54
• Main Author: Li Qingyong, He Bing, Zhang Xianyang, Zhu Xiaoyu, Liu Gang
• Format: Journal Article
• Language: Chinese
• Published: Editorial Office of Aero Weaponry 01.04.2021
• Subjects: trajectory prediction|lstm|encoder-decoder|supervised learning|multi-step prediction
• ISSN: 1673-5048
• DOI: 10.12132/ISSN.1673-5048.2020.0175

Aiming at the trajectory and motion characteristics of weakly constrained non-cooperative targets, a LSTM-based encoder-decoder multi-step trajectory prediction technology (EDMTP) is proposed. The introduction of first-order difference processing reduces the time dependence of the trajectory data, and obtains a trendless trajectory. Constructing an input and output trajectory data pair, transforming the prediction problem into a supervised learning problem, the change of model performance in the multi-step prediction process is studied to realize end-to-end trajectory prediction. Simulation results show that this method can extract more trajectory features from historical trajectory data, and has obvious advantages in multi-step trajectory prediction. Compared with the trajectory prediction algorithms of KFTP and HMMTP, the error growth rate of EDMTP decrease by 2.18% and 3.52% year-on-year, respectively, and achieves better trajectory prediction results.