US 11,668,831 B2
High-precision mapping method and device
Wendong Ding, Beijing (CN); Fan Yi, Beijing (CN); Li Yu, Beijing (CN); Pengfei Yuan, Beijing (CN); and Shiyu Song, Sunnyvale, CA (US)
Assigned to Beijing Baidu Netcom Science Technology Co., Ltd., Beijing (CN)
Filed by Beijing Baidu Netcom Science Technology Co., Ltd., Beijing (CN)
Filed on Dec. 30, 2020, as Appl. No. 17/137,470.
Claims priority of application No. 202010598678.X (CN), filed on Jun. 28, 2020.
Prior Publication US 2021/0405200 A1, Dec. 30, 2021
Int. Cl. G06K 9/00 (2022.01); G01S 17/894 (2020.01); G06T 7/521 (2017.01); G06T 7/70 (2017.01); G06V 40/20 (2022.01); G06V 20/64 (2022.01); G06V 20/56 (2022.01); G01S 17/06 (2006.01)
CPC G01S 17/894 (2020.01) [G01S 17/06 (2013.01); G06T 7/521 (2017.01); G06T 7/70 (2017.01); G06V 20/56 (2022.01); G06V 20/647 (2022.01); G06V 40/23 (2022.01); G06T 2207/10028 (2013.01); G06T 2207/30252 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A high-precision mapping method, comprising:
acquiring global initial poses of multiple point clouds, wherein the point clouds are point clouds of a location for which a map is to be built and are collected by a lidar using a multi-circle collection mode;
dividing the multiple point clouds into multiple spatial submap graphs according to a spatial distribution relationship of the multiple point clouds;
optimizing, for each spatial submap graph, global initial poses of point clouds belonging to the spatial submap graph to acquire global poses of the point clouds in each spatial submap graph; and
stitching the multiple spatial submap graphs together according to global poses of the point clouds in each spatial submap graph to acquire a base graph of the map to be built;
wherein before the optimizing, for each spatial submap graph, global initial poses of point clouds belonging to the spatial submap graph to acquire global poses of the point clouds in each spatial submap graph, the method further comprises:
forming, according to a point cloud distance limit, two point clouds in the spatial submap graph which have a common observation point and for which an absolute value of a difference between global initial poses is less than the distance limit into a point cloud pair, wherein a weight of the point cloud pair is negatively related to temporal distance between the point clouds contained in the point cloud pair.