The invention discloses an interactive vehicle multi-modal trajectory prediction method based on GRU-GCN, and the method comprises the following steps: obtaining a data set, and carrying out the data preprocessing; a GRU-based encoder is used for encoding historical track information of a target vehicle and surrounding vehicles, and vehicle dynamics encoding features corresponding to all the vehicles are output; extracting space-time interaction characteristics between the vehicles by using an interaction module; the behavior recognition module recognizes the behavior of the target vehicle; and based on the behavior recognition result m, utilizing GRU decoding to generate a future multi-modal prediction trajectory. According to the invention, the problem that the prediction precision of the existing prediction method on the multi-modal trajectory of the vehicle is low is solved.
本发明公开了一种基于GRU‑GCN的交互式车辆多模态轨迹预测方法,包括以下步骤:获得数据集,进行数据预处理;利用基于GRU的编码器对目标车辆及周围车辆的历史轨迹信息进行编码,输出各车辆对应的车辆动力学编码特征;利用交互模块提取车辆间的时空交互特征;行为识别模块识别目标车辆的行为;基于行为识别结果m利用GRU解码生成未来多模态预测轨迹。本发明解决了现有预测方法对车辆多模态轨迹的预测精度较低的问题。
Interactive vehicle multi-modal trajectory prediction method based on GRU-GCN
基于GRU-GCN的交互式车辆多模态轨迹预测方法
2023-08-15
Patent
Electronic Resource
Chinese
IPC: | G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Multi-modal vehicle trajectory prediction method based on graph interaction mechanism
European Patent Office | 2024
|Multi-modal vehicle trajectory prediction method based on hierarchical order network
European Patent Office | 2023
|Vehicle multi-modal trajectory prediction method based on semi-supervised model
European Patent Office | 2023
|