Gm Global Technolgoy Operations, Inc.

Gui Chen

Bo Yu

Joon Hwang

Fan Bai

Carl P Darukhanavala

Shuqing Zeng

Vivek Vijaya Kumar

Shu Chen

Donald K Grimm

Michael A Losh

Brent Navin Roger Bacchus

Carolyn Heather MacLeod

A method for crowd-sourcing lane line map data for a vehicle includes receiving a plurality of observations. The method also includes classifying the plurality of observations into a plurality of observation categories. Each of the plurality of observation categories includes at least one of the plurality of observations. The method also includes determining a plurality of aligned point clouds based at least in part on the plurality of observations. One of the plurality of aligned point clouds corresponds to each of the plurality of observation categories. The method also includes determining a plurality of lane line maps based at least in part on the plurality of aligned point clouds. One of the plurality of lane line maps corresponds to each of the plurality of aligned point clouds. The method also includes updating a map database based at least in part on the plurality of lane line maps.

Crowd-sourcing lane line maps for a vehicle

A system for fusing two or more versions of map data together includes one or more central computers that receive road network data representing a road network for a predefined geofenced area. The central computers compute a plurality of points that are each positioned at a predetermined distance from one another. The central computers create a plurality of bounding boxes for the road network based on the plurality of points and 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. The central computers 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.

System for fusing two or more versions of map data

A method for crowd-sourcing lane line map data for a vehicle may include receiving a plurality of observations. The plurality of observations includes at least a first observation and a second observation. The method further may include generating a point cloud alignment vector based at least in part on the plurality of observations. The method further may include generating an optimized aligned point cloud based at least in part on the point cloud alignment vector. The method further may include determining a lane line map based at least in part on the optimized aligned point cloud. The method further may include updating a map database based at least in part on the lane line map.

A method for merging lane line maps includes determining a road topology of a road segment. The method also includes identifying a plurality of fused points based at least in part on the road topology and based at least in part on a first lane line map of the road segment and a second lane line map of the road segment. The method also includes forming a fused lane line map based at least in part on the plurality of fused points. The method also includes performing a first action based at least in part on the fused lane line map.

Merging lane line maps for a vehicle

A method for quantifying map errors includes receiving first map data and second map data. The method includes receiving a road topographic map. The method further includes dividing the road into road segments. The method further includes creating a plurality of bounding boxes for each of the plurality of road segments. The method includes creating a first map tile and a second map tile by filtering out the bounding boxes. The method includes executing point cloud registration to align the plurality of first data points in the first map tile with the plurality of second data points in the second map tile to determine a plurality of absolute offsets between the plurality of first data points and the plurality of second data points. The method includes determining a relative map error between the first map and the second map based on the absolute offsets.

Method and system for quantifying map errors

A global positioning system (GPS)-bias detection and reduction system including a GPS-bias model having GPS statistical data creating a database representing data collected from a vehicle group having thousands or multiple thousands of vehicles saved in a database. At least one newly collected vehicle GPS data point is compared to the GPS statistical data to reduce negative effects of GPS-bias and to update the vehicle GPS-bias correction based on a previous GPS-bias model. A selected road node and a segment of a roadway have a map matching performed using a nearest service from a collection location of the GPS statistical data. A GPS-bias is calculated using a look-up of the database. An estimated horizontal position error (EHPE) defining a quality indicator is applied to distinguish a good quality GPS statistical data from a poor quality GPS statistical data.

Global positioning system bias detection and reduction

A method of creating a high-definition (HD) map of a roadway includes receiving a multi-layer probability density bitmap. The multi-layer probability density bitmap represents a plurality of lane lines of the roadway sensed by a plurality of sensors of a plurality of vehicles. The multi-layer probability density bitmap includes a plurality of points. The method further includes recursively conducting a hill climbing search using the multi-layer probability density bitmap to create a plurality of lines. In addition, the method includes creating the HD map of the roadway using the plurality of lines determined by the hill climbing search.

Hill climbing algorithm for constructing a lane line map

A method includes receiving sensor data from a plurality of sensors of a plurality of vehicles. The sensor data includes vehicle GPS data and sensed lane line data of the roadway. The method further includes creating a plurality of multi-layer bitmaps for each of the plurality of vehicles using the sensor data, fusing the plurality of the multi-layer bitmaps of each of the plurality of vehicles to create a fused multi-layer bitmap, creating a plurality of multi-layer probability density bitmaps using the fused multi-layer bitmap, extracting lane line data from the plurality of multi-layer probability density bitmaps, and creating the high-definition (HD) map of the roadway using the multi-layer probability density bitmaps and the lane line data extracted from the plurality of multi-layer probability density bitmaps.

Growing community of inventors

Sterling Heights, MI, United States of America

Gui Chen