Intersection node-assisted high-definition mapping

Patent metadata

Field	Value
Publication number	US-11914378-B2
Application number	US-202117323842-A
Country	US
Kind code	B2
Filing date	May 18, 2021
Priority date	May 18, 2021
Publication date	Feb 27, 2024
Grant date	Feb 27, 2024

Abstract

A computer-implemented method for controlling a vehicle includes receiving, via a processor, from two or more IX control devices disposed at a two or more stationary positions having known latitudes longitudes and orientations, first sensory data identifying the position and dimensions of a feature in a mapped region. The processor generates a plurality of IX nodes based on the first sensory data received from the IX control devices, and receives LiDAR point cloud that includes LiDAR and other vehicle sensory device data such as Inertial Measurement Unit (IMU) data received from a Vehicle (AV) driving in the mapped region. The LiDAR point cloud includes a simultaneous localization and mapping (SLAM) map having second dimension information and second position information associated with the feature in the mapped region. The processor generates, without GPS and/or real-time kinematics information, an optimized High-Definition (HD) map having Absolute accuracy using batch optimization and map smoothing.

First claim

That which is claimed is:

1. A method for controlling an Autonomous Vehicle (AV), comprising:
generating, by a first intersection (IX) control device comprising a first Light Detection and Ranging (LiDAR) system and a second IX control device comprising a second LiDAR system, first sensory data comprising first dimensional information and first position information of a stationary environmental feature in a mapped region;
receiving, via a processor, from the first IX control device and the second IX control device, the first sensory data;
collecting, by one or more sensors disposed in the AV, a LiDAR point cloud and Simultaneous Localization and Mapping (SLAM) data associated with the stationary environmental feature in the mapped region while the AV is driving along one or more roadways in the mapped region;
receiving, via the processor, from the AV, the LiDAR point cloud and the SLAM data;
generating, via the processor, based on a combination of the LiDAR point cloud and the SLAM data, second sensory data comprising second dimensional information and second position information of the stationary environmental feature in the mapped region;
generating, via the processor, a plurality of IX node data points based on a combination of the first sensory data and the second sensory data, wherein the plurality of IX node data points comprises a first IX node data point associated with the first IX control device and a second IX node data point associated with the second IX control device;
generating an optimized High-Definition (HD) map comprising the stationary environmental feature in the mapped region by smoothing the plurality of IX node data points using a batch optimization algorithm, wherein the batch optimization algorithm uses the first IX node data point as a first static IX control point and the second IX node data point as a second static IX control point; and
navigating the AV along the one or more roadways in the mapped region using the optimized HD map.

2. The method according to claim 1 , wherein the batch optimization algorithm reduces linearization error of the plurality of IX node data points to be less than a threshold for linearization error by smoothing the plurality of IX node data points without moving the first IX node data point or the second IX node data point relative to a remainder of the plurality of IX node data points.

3. The method according to claim 1 , wherein the first IX control device is disposed in the mapped region at a first stationary position having a first known latitude and a first known longitude and the second IX control device is disposed at a second stationary position having a second known latitude and a second known longitude, and wherein a precision with which the stationary environmental feature is aligned on the optimized HD map is based on the first stationary position and the second stationary position in the mapped region.

4. The method according to claim 1 , wherein the first sensory data is generated based on LiDAR sensory data collected by the first LiDAR system of the first IX control device and the second LiDAR system of the second IX control device.

5. The method according to claim 1 , wherein the LiDAR point cloud comprises LiDAR sensory data and Inertial Measurement Unit (IMU) data.

6. The method according to claim 1 , wherein the first sensory data and the LiDAR point cloud do not include Global Positioning System (GPS) data.

7. The method according to claim 1 , wherein the first sensory data and the LiDAR point cloud do not include Real-Time-Kinematics (RTK) information.

8. A system, comprising:
a processor; and
a memory for storing executable instructions, the processor programmed to execute the instructions to:
generate, by a first intersection (IX) control device comprising a first Light Detection and Ranging (LiDAR) system and a second IX control device comprising a second LiDAR system, first sensory data comprising first dimensional information and first position information of a stationary environmental feature in a mapped region;
receive, from the first IX control device and the second IX control device, the first sensory data;
collect, by one or more sensors disposed in an Autonomous Vehicle (AV), a LiDAR point cloud and Simultaneous Localization and Mapping (SLAM) data associated with the stationary environmental feature in the mapped region while the AV is driving along one or more roadways in the mapped region;
receive, from the AV, the LiDAR point cloud and the SLAM data;
generate, based on a combination of the LiDAR point cloud and the SLAM data, second sensory data comprising second dimensional information and second position information of the stationary environmental feature in the mapped region;
generate a plurality of IX node data points based on a combination of the first sensory data and the second sensory data, wherein the plurality of IX node data points comprises a first IX node data point associated with the first IX control device and a second IX node data point associated with the second IX control device;
generate an optimized High-Definition (HD) map comprising the stationary environmental feature in the mapped region by smoothing the plurality of IX node data points using a batch optimization algorithm, wherein the batch optimization algorithm uses the first IX node data point as a first static IX control point and the second IX node data point as a second static IX control point; and
navigate the AV along the one or more roadways in the mapped region using the optimized HD map.

9. The system according to claim 8 , wherein the batch optimization algorithm reduces linearization error of the plurality of IX node data points to be less than a threshold for linearization error by smoothing the plurality of IX node data points without moving the first IX node data point or the second IX node data point relative to a remainder of the plurality of IX node data points.

10. The system according to claim 8 , wherein the first IX control device is disposed in the mapped region at a first stationary position having a first known latitude and a first known longitude and the second IX control device is disposed at a second stationary position having a second known latitude and a second known longitude, and wherein a precision with which the stationary environmental feature is aligned on the optimized HD map is based on the first stationary position and the second stationary position in the mapped region.

11. The system according to claim 8 , wherein the first sensory data is generated based on LiDAR sensory data collected by the first LiDAR system of the first IX control device and the second LiDAR system of the second IX control device.

12. The system according to claim 8 , wherein the LiDAR point cloud comprises LiDAR sensory data and Inertial Measurement Unit (IMU) data.

13. The system according to claim 8 , wherein the first sensory data and the LiDAR point cloud do not include Global Positioning System (GPS) data.

14. The system according to claim 8 , wherein the first sensory data and the LiDAR point cloud do not include Real-Time-Kinematics (RTK) information.

15. A non-transitory computer-readable storage medium in a High-Definition (HD) mapping system, the computer-readable storage medium having instructions stored thereupon which, when executed by a processor, cause the processor to:
generate, by a first intersection (IX) control device comprising a first Light Detection and Ranging (LiDAR) system and a second IX control device comprising a second LiDAR system, first sensory data comprising first dimensional information and fi

Assignees

• Ford Global Tech Llc

Inventors

• Vora Ankit
• Agarwal Siddharth
• Krishnan Krishanth

Classifications

• G05D1/0212 Primary

  with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287) · CPC title

• G01C21/3815

  Road data · CPC title

• G01C21/3841 Primary

  Data obtained from two or more sources, e.g. probe vehicles · CPC title

• G05D1/027

  comprising intertial navigation means, e.g. azimuth detector (inertial navigation G01C21/16; inertial navigation combined with non-inertial navigation instruments G01C21/165) · CPC title

• G05D1/0231

  using optical position detecting means (position-fixing by using electromagnetic waves other than radio waves, e.g. optical position detecting means G01S5/16) · CPC title