The invention relates to an automatic driving prediction-planning integration method based on a traffic heterogeneous graph, and belongs to the technical field of automatic driving automobiles. The method comprises the following steps: S1, modeling intelligent agent dynamic features and interaction features between traffic participants, and designing lane map node feature representation based on a graph convolutional network; s2, an encoding-decoding architecture is adopted, interaction features between lane nodes and agents are captured through a graph attention mechanism, and after feature fusion is carried out, a multi-agent trajectory prediction model based on a traffic heterogeneous graph is constructed; and S3, on the basis of future position information of surrounding vehicles output by the trajectory prediction model, designing a target function and various constraints to carry out self-vehicle action optimization solution. Compared with a traditional planning method, the method is more excellent in prediction performance, safety and driving efficiency.
本发明涉及一种基于交通异构图的自动驾驶预测‑规划集成方法,属于自动驾驶汽车技术领域。该方法包括:S1:建模智能体动态特征以及交通参与者之间的交互特征,并设计基于图卷积网络的车道图节点特征表示;S2:采用编码‑解码架构,通过图注意力机制捕捉车道节点与智能体之间的交互特征,进行特征融合后构建基于交通异构图的多智能体轨迹预测模型;S3:基于轨迹预测模型输出的周围车辆未来位置信息,设计目标函数及多种约束来进行自车动作最优化求解。与传统规划方法相比,本发明预测性能、安全性以及行驶效率更加优异。
Automatic driving prediction-planning integration method based on traffic heterogeneous graph
一种基于交通异构图的自动驾驶预测-规划集成方法
2025-05-06
Patent
Electronic Resource
Chinese
Heterogeneous graph collaborative learning traffic flow prediction method
European Patent Office | 2025
|Automatic driving forklift traffic planning method based on storage space coordinates
European Patent Office | 2023
|End-to-end automatic driving behavior planning method based on graph attention
European Patent Office | 2024
|