计算机工程与应用2026，Vol.62Issue(11)：338-351,14.DOI:10.3778/j.issn.1002-8331.2503-0068
频域-时空协同框架下的车辆轨迹预测及意图识别模型
Vehicle Trajectory Prediction and Intention Recognition Model Under Frequency-Spatiotemporal Collaborative Framework
摘要
Abstract
To mitigate error accumulation from high-frequency noise and low computational efficiency in complex spatial interaction modeling for trajectory prediction,this paper proposes a frequency-spatiotemporal cooperative prediction framework.The method first applies multivariate variational mode decomposition(MVMD)to historical trajectories,sup-pressing noise and extracting frequency-domain features by constraining anomalous perturbations.Then,convolutional neural networks(CNNs)with feature scaling enhance vehicle-environment interaction perception.Finally,it adaptively fuses multi-frequency trajectory components and spatial interaction features.Combined with LSTM networks and a driving intention probability vector,a mixture density network(MDN)outputs the predicted trajectory's probability density distri-bution.Experiments on the NGSIM dataset show the proposed method outperforms baseline models,effectively co-optimizing frequency-domain analysis,temporal modeling,and interaction perception.The maximum root mean squared error(RMSE)over the 1～5 s prediction horizon is only 1.43 m,meeting complex traffic scenario requirements.关键词
轨迹预测/频域-时空协同/多元变分模态分解(MVMD)/卷积神经网络/混合密度网络(MDN)Key words
trajectory prediction/frequency-spatiotemporal cooperative/multivariate variational mode decomposition(MVMD)/convolutional neural network/mixture density network(MDN)分类
信息技术与安全科学引用本文复制引用
王庆荣,韩芳文,朱昌锋,金小龙..频域-时空协同框架下的车辆轨迹预测及意图识别模型[J].计算机工程与应用,2026,62(11):338-351,14.基金项目
国家自然科学基金(72161024) （72161024）
甘肃省教育厅"双一流"重大研究项目(GSSYLXM-04). （GSSYLXM-04）
