A vehicle and related systems and methods are provided for classifying detected objects in a location-dependent manner using a local model in a federated learning environment. A method involves: obtaining sensor data of a detected object external to a vehicle from a sensor of the vehicle; obtaining position data associated with the detected object; obtaining a local classification model associated with the object type; using a local classification model, and based on the local classification model, according to the output of the sensor data and the position data, distributing an object type to the detected object; in response to assigning an object type to the detected object, an action is initiated at the vehicle.
提供了用于在联邦学习环境中使用局部模型以位置相关的方式对检测到的对象进行分类的车辆和相关系统及方法。一种方法涉及:从车辆的传感器获得车辆外部的被检测对象的传感器数据;获得与被检测对象相关联的位置数据;获得与对象类型相关联的局部分类模型;使用局部分类模型,基于局部分类模型根据传感器数据和位置数据的输出,将对象类型分配给被检测对象;响应于将对象类型分配给检测到的对象,在车辆处启动动作。
Federated learning for connected camera applications in vehicles
用于车辆中的连接的摄像机应用的联邦学习
2023-07-11
Patent
Elektronische Ressource
Chinesisch
Federated learning on the road autonomous controller design for connected and autonomous vehicles
BASE | 2022
|