The invention belongs to the technical field of automatic auxiliary driving, and particularly relates to a self-adaptive virtual lane line drawing method in a lane line-free road environment. According to the method, the spatial undirected graph is constructed by taking the obtained target information and the target as nodes, the time sequence information is converted into a graph matrix form, and the time sequence of the graph matrix form is stored. And processing the graph matrix data by using the reconstructed LSTM model, and processing the time sequence of the data by using the cyclicity of the LSTM. Effective features are extracted from space graph matrix data by using a Transform space attention mechanism, and a model is trained; and the high-frequency information and the low-frequency information are continuously processed by using an inceptionmixer module, and effective features in the information are extracted again, so that the accuracy and the high efficiency of the method are ensured. The method can efficiently predict the track of the surrounding vehicle for a long time, effectively guarantees the driving safety and road safety, can be applied to an intelligent traffic system, improves the traffic safety and efficiency, and assists in route optimization, intersection prediction and other operations.
本发明属于自动辅助驾驶技术领域,具体涉及一种无车道线道路环境下的自适应虚拟车道线绘制方法。本发明通过得到的目标信息和目标本身作为节点构建出空间无向图,将时序性信息转化成图矩阵形式,并保存其时序性。使用重构后的LSTM模型处理图矩阵数据,并利用LSTM的循环性处理数据的时序性。使用Transformer的空间注意力机制从空间图矩阵数据中提取有效特征并训练模型。用inception_mixer模块继续处理高频信息和低频信息,将信息中的有效特征再次提取,保证了本方法的准确性和高效性。该方法可以高效地长时预测周围车辆的轨迹,有效地保障了行车安全和道路安全,可以应用于智能交通系统,提高交通安全性和效率,协助路线优化和路口预测等操作。
Transform and LSTM-based vehicle trajectory prediction method
一种基于Transformer和LSTM的车辆轨迹预测方法
04.07.2023
Patent
Elektronische Ressource
Chinesisch
IPC: | G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / 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 |
Vehicle trajectory prediction based on LSTM network
IEEE | 2022
|LSTM-Based Vehicle Trajectory Prediction Using UAV Aerial Data
Springer Verlag | 2023
|Research on Vehicle Trajectory Prediction Based on Improved LSTM Model
Springer Verlag | 2024
|Transform-based networked autonomous vehicle trajectory prediction method
Europäisches Patentamt | 2025
|