Real-time Dynamic Trajectory Prediction Algorithm Based on Reservoir Computing
YANG Zhiliang
MAO Yuru
YAO Jinjie
AN Jianping
Abstract：Real-time prediction of the trajectories of moving targets using neural network models has extremely high applica-tion value.Taking the dynamic trajectory prediction of drone as a case study,this paper studies the trajectory prediction of moving targets based on the reservoir computing algorithm.The reservoir network is trained with the acquired historical of drone,and the network model generated by the training is used to predict the future movement trajectory of drone.Based on the network model trained with 5 000 frames of historical movement trajectories of drones,real-time prediction of the next moment trajectory is achieved.According to the evaluation criteria for trajectory prediction,the experimental results show that when predicting the trajec-tories for the next 10 frames,the prediction errors of 80％of the prediction points can be controlled within 0.8％.
Keywords：reservoir computingdynamic trajectory predictiondrone
Publication Date：2025-12-20
Online Publishing Date：2026-03-23(First online date of this platform, not the publication date of the document)
Pages：6( 46-50,89 )