US 12,467,765 B2
System for fusing two or more versions of map data
Gui Chen, Sterling Heights, MI (US); Bo Yu, Troy, MI (US); Shuqing Zeng, Sterling Heights, MI (US); Fan Bai, Ann Arbor, MI (US); Joon Hwang, Pflugerville, TX (US); Vivek Vijaya Kumar, Shelby Township, MI (US); Mason David Gemar, Cedar Park, TX (US); and Carl P. Darukhanavala, Royal Oak, MI (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on May 16, 2023, as Appl. No. 18/318,247.
Prior Publication US 2024/0385010 A1, Nov. 21, 2024
Int. Cl. G01C 21/00 (2006.01)
CPC G01C 21/3811 (2020.08) 11 Claims
OG exemplary drawing
 
1. A system for fusing two or more versions of map data together, the system comprising:
one or more central computers in wireless communication with one or more communication networks for receiving the two or more versions of map data and ground truth map data, wherein each version of the map data represents a singular predefined geofenced area, the one or more central computers executing instructions to:
receive road network data representing a road network for the predefined geofenced area, wherein the road network is a graph that models roadways based on a plurality of road segments;
compute a plurality of points that are each positioned at a predetermined distance from one another, wherein the plurality of points divides an individual road segment of the plurality of road segments by the predetermined distance;
create a plurality of bounding boxes for the road network based on the plurality of points, wherein the predetermined distance between two of the plurality of points represents a width of one of the plurality of bounding boxes;
create a set of closest matched map data points for each bounding box that is part of the road network by executing a map-matching registration algorithm to align the two or more versions of map data with one another;
execute a maximum likelihood estimation algorithm to determine probability distribution parameters of the set of closest matched map data points compared to the ground truth map data, wherein the probability distribution parameters include a mean value of a first offset between a first set of map data points and the ground truth map data, a mean value of a second offset between a second set of map data points and the ground truth map data, a variance of the first offset, and a variance of the second offset;
fuse the set of closest matched map data points together to create fused map data based on the probability distribution parameters;
calculate a map fusion offset between individual fused map data points of the fused map data and corresponding map data points of the ground truth map data, wherein the map fusion offset represents an absolute map error;
evaluate map fusion performance by comparing a mean value and a standard deviation of the map fusion offset with the mean value and a standard deviation of the first offset, and by comparing the mean value and the standard deviation of the map fusion offset with the mean value and a standard deviation of the second offset;
transmit, over a wireless connection, the fused map data to an autonomous vehicle; and
control, by an autonomous driving system of the autonomous vehicle, motion of the autonomous vehicle based on the fused map.