首页> 外国专利> DRIVING PATTERN MANAGEMENT SERVER FOR AUTONOMOUS VEHICLES AND DRIVING PATTERN CLASSIFYING METHOD THEREOF

DRIVING PATTERN MANAGEMENT SERVER FOR AUTONOMOUS VEHICLES AND DRIVING PATTERN CLASSIFYING METHOD THEREOF

机译:用于自动车辆的驱动模式管理服务器及其驱动模式分类方法

摘要

A driving pattern management server for receiving driving data provided from an autonomous driving vehicle running on a road according to an embodiment of the present invention includes a communication unit receiving the driving data transmitted from the autonomous driving vehicle, the received driving data, and the A storage unit for storing infrastructure information of a road, and a control unit for deriving the accumulated driving data as a driving pattern for each road section through machine learning, and analyzing the driving pattern in connection with the infrastructure information of the road, wherein the control unit Is, controlling the communication unit and the storage unit to accumulate the driving data in the storage unit for a specific period, classifying the accumulated driving data by section of the road, and converting the classified driving data into data in a form suitable for machine learning. It consists of three, and is clustered using a self-organizing map (SOM) algorithm and K-means++ algorithm for the data set to derive a driving pattern, and the driving pattern and the road infrastructure information are linked to the autonomous vehicle. Analyze the driving characteristics of each section of the road.
机译:用于接收由根据本发明的实施例的在道路上运行的自主行驶车辆提供的驱动数据的驾驶模式管理服务器包括接收从自动驾驶车辆发送的驱动数据,接收的驾驶数据和A的通信单元存储单元用于存储道路的基础设施信息,以及用于通过机器学习将累积的驱动数据导出作为每个道路截面的驱动模式的控制单元,并通过机器学习分析与道路的基础设施信息相关的驱动模式,其中控制单位是控制通信单元和存储单元,以累积存储单元中的驱动数据,以便特定时段,分类累积的驱动数据通过部分部分,并将分类的驱动数据转换为适合于机器的表单中的数据中的数据学习。它由三个组成,并且使用自组织地图(SOM)算法和用于数据集的K-Means ++算法来集群,以导出驱动模式,并且驱动模式和道路基础设施信息与自主车辆连接。分析道路各部分的驱动特性。

著录项

  • 公开/公告号KR102233723B1

    专利类型

  • 公开/公告日2021-03-30

    原文格式PDF

  • 申请/专利权人

    申请/专利号KR1020200122496

  • 发明设计人 김형주;서영훈;임동현;

    申请日2020-09-22

  • 分类号G05D1/02;B60W40/09;B60W40/10;B60W50;B60W60;G05D1;G06N20;H04W4/40;

  • 国家 KR

  • 入库时间 2024-06-14 21:23:46

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号