Efficient map matching method for autonomous driving and apparatus thereof
AssigneeThordrive Co., Ltd
InventorGyumin Oh
Life of this patent
Estimating the term…
Abstract
A map matching method for autonomous driving includes extracting a first statistical map from 3D points contained in 3D map data; extracting a second statistical map from 3D points of surroundings which are obtained by a detection sensor simultaneously or after the previous extracting of the statistical map; dividing the second statistical map into a vertical-object part and a horizontal-object part; and performing map matching using the horizontal-object part and/or the vertical-object part and the first statistical map.
Claims22
A map matching method for autonomous driving that is performed by one or more processors for an autonomous driving apparatus, the map matching method comprising:
- extracting, by the one or more processors, a first statistical map from 3D points of 3D map data;
- extracting, by the one or more processors, a second statistical map from 3D points obtained by a detection sensor of the autonomous driving apparatus simultaneously or after the previous extraction of the first statistical map;
- dividing, by the one or more processors, the second statistical map into a vertical-object part and a horizontal-object part depending on statistical values of respective divided regions of the second statistical map;
- and
- estimating, by the one or more processors, a pose of the autonomous driving apparatus by comparing the horizontal-object part or the vertical-object part with the first statistical map,
- wherein regions of the statistical maps that have statistical values larger than a predetermined value are extracted as the vertical-object part, and regions of the statistical maps that have statistical values smaller than the predetermined value are extracted as the horizontal-object part.
Dependencies are inferred from the claim text.