The invention provides a traffic participant trajectory prediction method and system based on multiple interaction behaviors, and the method comprises the steps: obtaining high-precision map data and node features of traffic participants, and carrying out the construction of a static interaction layer and a dynamic interaction layer; performing dynamic interaction on the static interaction layer and the dynamic interaction layer based on a preset traffic light information gating neural network to construct an interaction network; and performing supervised learning training on the interactive network through a preset target loss function, outputting a trajectory prediction network model, and performing trajectory prediction through the trajectory prediction network model. According to the method, the problem of inaccurate traffic participant trajectory prediction in the prior art is solved, mutual fusion of multiple traffic interaction behaviors is realized, and accurate trajectory prediction is completed.
本发明提供一种基于多重交互行为的交通参与者轨迹预测方法及系统,包括:获取高精地图数据和交通参与者的节点特征,进行静态交互层和动态交互层的构建;基于预设的交通灯信息门控神经网络将所述静态交互层和动态交互层进行动态交互,构建交互网络;对所述交互网络通过预设的目标损失函数进行监督学习训练,输出轨迹预测网络模型,通过所述轨迹预测网络模型进行轨迹预测。本发明解决了现有技术中对交通参与者轨迹预测不准确的问题,实现将多重交通交互行为进行相互融合,完成轨迹的准确预测。
Traffic participant trajectory prediction method and system based on multiple interaction behaviors
基于多重交互行为的交通参与者轨迹预测方法及系统
2023-02-28
Patent
Elektronische Ressource
Chinesisch
LSTM model-based vulnerable traffic participant trajectory prediction method
Europäisches Patentamt | 2022
|Traffic participant trajectory prediction method in complex heterogeneous environment
Europäisches Patentamt | 2023
|Europäisches Patentamt | 2023
|VEHICLE TRAJECTORY PREDICTION USING ROAD TOPOLOGY AND TRAFFIC PARTICIPANT OBJECT STATES
Europäisches Patentamt | 2021
|