公开(公告)号：US20180224857A1

公开(公告)日：2018-08-09

申请号：US15800431

申请日：2017-11-01

Applicant: Hyundai Motor Company ,  Kia Motors Corporation

Inventor： Seok Youl Yang ,  Tae Seok Lee ,  Seong Su Im

IPC: G05D1/02

CPC classification number: G05D1/0212 ,  G05D1/0246 ,  G05D1/0257 ,  G05D2201/0213

Abstract: A method of determining a driving lane of an autonomous vehicle is provided. The method includes classifying, by an autonomous driving logic of an electronic control unit (ECU), at least one object sensed in front of the autonomous vehicle as a stationary object or a moving object. A clustering group is generated by clustering the stationary object and a boundary of an entire driving road is determined based on a position of a moving object approaching the subject vehicle among the moving objects and the clustering group. Additionally, the method includes comparing positions of a plurality of lanes based on lane widths of the lanes for travel of the subject vehicle with the boundary of the entire driving road and determining a driving lane of the subject vehicle.

公开(公告)号：US20140035777A1

公开(公告)日：2014-02-06

申请号：US13713820

申请日：2012-12-13

Applicant: HYUNDAI MOTOR COMPANY

Inventor： Jin Hak Kim ,  Kyung Ho Yoo ,  Yoon Ho Jang ,  Seong Su Im ,  Hui Sung Lee ,  Kyoung Moo Min ,  Eun Jin Choi

IPC: G01S13/93

CPC classification number: G01S13/93 ,  G01S7/292 ,  G01S7/41 ,  G01S13/86 ,  G01S13/91 ,  G01S13/931 ,  G08G1/16

Abstract: The present invention provides a method and a system for producing a classifier for recognizing an obstacle, including a processor configured to: display surface data of a plurality of obstacles measured by a distance measurement sensor in a two-dimensional (2D) coordinate system; group and classify the surface data displayed in the 2D coordinate system for each obstacle; setting a plurality of feature references to analyze region based features displayed for each obstacle in the 2D coordinate system and calculate the respective feature references for each obstacle grouping; and producing the classifier by applying a weight to each of the feature references.

Abstract translation: 本发明提供一种用于产生用于识别障碍物的分类器的方法和系统，包括处理器，其被配置为：在二维（2D）坐标系中显示由距离测量传感器测量的多个障碍物的表面数据; 对每个障碍物在2D坐标系中显示的表面数据进行分组; 设置多个特征参考以分析在2D坐标系中为每个障碍物显示的基于区域的特征，并且计算每个障碍物分组的各个特征参考; 以及通过对每个特征参考应用权重来产生分类器。