The invention relates to a lane changing intention prediction method, a model training method, a vehicle and a storage medium, and relates to the technical field of automatic driving. The method comprises the following steps: acquiring motion feature information of a target vehicle and vehicles in a plurality of areas around the target vehicle at N moments; and predicting the lane changing intention of the target vehicle based on the motion feature information at the N moments and the trained lane changing intention prediction model. Therefore, the accuracy of the model prediction result can be improved, and the technical problem that the LSTM unit cannot accurately obtain the interaction information between the traffic flows at different moments due to the fact that the physical significance of the information output by the CNN unit is indefinite is avoided.
本申请涉及一种变道意图预测方法、模型训练方法、车辆及存储介质,涉及自动驾驶技术领域。该方法包括:获取目标车辆和目标车辆周围的多个区域的车辆在N个时刻的运动特征信息;基于N个时刻的运动特征信息和训练好的变道意图预测模型,预测目标车辆的变道意图。由此,可以提高模型预测结果的准确性,避免由于CNN单元输出的信息物理意义不明确,导致LSTM单元无法准确获得不同时刻车流之间交互信息的技术问题。
Lane changing intention prediction method, model training method, vehicle and storage medium
变道意图预测方法、模型训练方法、车辆及存储介质
2024-10-01
Patent
Electronic Resource
Chinese
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 |
Vehicle lane changing intention prediction method and related equipment
European Patent Office | 2024
|Vehicle lane changing intention prediction method considering vehicle complex interaction
European Patent Office | 2024
|European Patent Office | 2025
|European Patent Office | 2024
|Vehicle lane changing decision model training method and vehicle lane changing decision method
European Patent Office | 2024
|