智能系统学报2025，Vol.20Issue(6)：1355-1365,11.DOI:10.11992/tis.202501020
分析力学和图神经网络的轨迹预测方法
Trajectory prediction methods based on analytical mechanics and graph neural networks
摘要
Abstract
Trajectory prediction seeks to forecast the future motion of intelligent agents by analyzing their past trajector-ies.While deep learning methods have been demonstrated to capture complex features,they frequently neglect physical constraints,thereby constraining interpretability.To address this,a trajectory prediction model is proposed that integ-rates analytical mechanics with graph neural networks(GNNs).The model combines GNNs,convolutional neural net-works,and graph attention to extract spatiotemporal dynamics,infers interaction forces from Euclidean distance and rel-ative motion,and incorporates Lagrange mechanics to enforce physical laws.Experiments on the Spring-balls dataset demonstrate the superior performance of the proposed model in comparison to traditional models,exhibiting a 14.29%accuracy gain in 10-frame short-term prediction for the 5-ball case and improvements of 6.25%and 4.81%in 50-frame long-term scenarios.In the domain of human motion prediction,our model demonstrates a reduction in mean position error(MPJPE)when compared to prevailing approaches for a wide range of actions.This finding signifies enhanced long-term accuracy and validates the efficacy of the model.关键词
轨迹预测/图神经网络/拉格朗日力学/交互作用力/深度学习/多层感知机/运动学模型/分析力学Key words
trajectory prediction/graph neural networks/Lagrangian mechanics/interaction force/deep learning/multi-layer perceptron/kinematic model/analytical mechanics分类
信息技术与安全科学引用本文复制引用
LI Minghan,XIAO Yang,XING Xianglei..分析力学和图神经网络的轨迹预测方法[J].智能系统学报,2025,20(6):1355-1365,11.基金项目
国家自然科学基金项目(62076078,61703119). （62076078,61703119）
