The invention relates to an automatic driving decision-making dangerous scene generation method, system and device, and a medium. The method comprises the following steps: extracting static element information and dynamic element information of a scene when a driver takes over an automatic driving vehicle in a real vehicle road test; establishing a dynamic element behavior model according to the extracted static element information and dynamic element information; setting a parameter space of the dynamic element behavior model, determining a parameter combination of the dynamic element behavior model in each analog simulation test, and constructing a dangerous scene; clustering and fitting are conducted on the constructed parameter combination of the dangerous scene, a dangerous scene area under the parameter combination is generated, efficient generation of the dangerous scene can be achieved, and the method can be widely applied to the field of intelligent vehicles.
本发明涉及一种自动驾驶决策危险场景生成方法、系统、设备及介质,包括:提取实车道路测试中自动驾驶车辆发生司机接管情况时的场景的静态要素信息和动态要素信息;根据提取的静态要素信息和动态要素信息,建立动态要素行为模型;设定动态要素行为模型的参数空间,确定每次模拟仿真测试中动态要素行为模型的参数组合,并构建危险场景;对构建出危险场景的参数组合进行聚类和拟合,生成该参数组合下的危险场景区域,本发明能够实现危险场景的高效生成,可以广泛应用于智能车辆领域中。
Automatic driving decision-making dangerous scene generation method, system, equipment and medium
一种自动驾驶决策危险场景生成方法、系统、设备及介质
2023-03-14
Patent
Elektronische Ressource
Chinesisch
Automatic driving decision-making scene recognition method and device, equipment and storage medium
Europäisches Patentamt | 2022
|Dangerous lane changing scene generalization generation method and system for automatic driving test
Europäisches Patentamt | 2023
|Decision-making method for automatic driving mode in emergency scene
Europäisches Patentamt | 2021
|Dangerous scene generation method, device and equipment and readable storage medium
Europäisches Patentamt | 2022
|Automatic driving decision-making method and system, medium, automatic driving system and vehicle
Europäisches Patentamt | 2024
|