The invention provides a surrounding vehicle trajectory prediction method and system based on MATT-GNN, and the method comprises the steps: firstly constructing a multi-attention spectrum space-time diagram neural network, inputting the vehicle information, collected in real time, of a surrounding traffic scene into the trained multi-attention spectrum space-time diagram neural network, and outputting the future trajectory of a predicted vehicle; the multi-attention spectrum space-time diagram neural network comprises an encoder, a GRU layer, an MT-step layer and a decoder, the MT-step layer is composed of n MT-step module groups, and the MT-step modules enable space-time features among surrounding vehicles to be fully extracted; the method can accurately predict the tracks of surrounding vehicles in a complex traffic scene.
本发明提供了一种基于MATT‑GNN的周边车辆轨迹预测方法及系统,该预测方法首先构建多注意力谱时空图神经网络,然后将实时采集的周围交通场景车辆信息输入训练后的多注意力谱时空图神经网络,输出被预测车辆的未来轨迹;所述多注意力谱时空图神经网络包括编码器、GRU层、MT‑stem层和解码器,MT‑stem层由n个MT‑stem模块组,MT‑stem模块使得周边车辆间的时空特征得到充分提取;本发明能精准预测复杂交通场景下对周边车辆轨迹。
MATT-GNN-based surrounding vehicle trajectory prediction method and system
基于MATT-GNN的周边车辆轨迹预测方法及系统
2022-06-24
Patent
Elektronische Ressource
Chinesisch
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES |
Parametric trajectory prediction of surrounding vehicles
IEEE | 2017
|Europäisches Patentamt | 2020
|Europäisches Patentamt | 2024
|TRAJECTORY PREDICTION OF SURROUNDING VEHICLES USING PREDEFINED ROUTES
Europäisches Patentamt | 2021
|