自动化学报2026，Vol.52Issue(2)：296-308,13.DOI:10.16383/j.aas.c250429
知识−数据−模型驱动的低空动目标轨迹融合预测方法
Knowledge-data-model-driven Trajectory Fusion Prediction Method for Low-altitude Moving Target
摘要
Abstract
Aiming at the moving target trajectory prediction problem in low-altitude environments,a knowledge-data-model-driven trajectory fusion prediction framework for moving target is proposed.A flight knowledge mixture-of-experts model is constructed based on the kinematic characteristics of low-altitude aerial vehicles.Multi-source sensor data are fed into various flight knowledge expert modules to achieve precise identification of target man-euver modes,while spatiotemporal correlation features are extracted by using the Mamba model.A weight adapt-ive adjustment mechanism is designed to dynamically fuse multi-source perception data by using an attention mech-anism,thereby addressing the spatiotemporal asynchrony issue of sensors.Long-term temporal dependencies are modeled by using gated recurrent unit to produce preliminary trajectory predictions based on historical flight data of target.A physics-informed neural network is constructed based on the kinematic equations of low-altitude tar-gets.By dynamically balancing data-driven loss and physical constraint loss,the network corrects data-driven bi-ases,ensures predicted trajectories satisfy kinematic constraints,and effectively suppresses error accumulation in multi-step prediction.Numerical simulations and experimental validation results demonstrate that the proposed knowledge-data-model-driven trajectory fusion prediction method can effectively forecast low-altitude moving tar-get flight trajectories.关键词
低空环境/知识−数据−模型驱动/动目标/数据融合/轨迹预测Key words
low-altitude environment/knowledge-data-model-driven/moving target/data fusion/trajectory predic-tion引用本文复制引用
周同乐,刘子仪,陈谋..知识−数据−模型驱动的低空动目标轨迹融合预测方法[J].自动化学报,2026,52(2):296-308,13.基金项目
国家自然科学基金(62203217,U23B2036),江苏省基础研究计划自然科学基金(BK20220885)资助Supported by National Natural Science Foundation of China(62203217,U23B2036)and Jiangsu Province Basic Research Pro-gram Natural Science Foundation(BK20220885) （62203217,U23B2036）
