Use of relative atlas in autonomous vehicle

• US 10,474,699 B2
• Filed: 02/08/2019
• Issued: 11/12/2019
• Est. Priority Date: 03/29/2018
• Status: Active Grant

• Current Assignee: Aurora Operations Incorporated
• Original Assignee: Aurora Innovation, Inc.
• Inventors: Eade, Ethan, Bode, Michael, Bagnell, James Andrew
• Primary Examiner(s): Patel, Shardul D
• Application Number:
  US16/271,612
• Publication Number:
  US 20190303392A1
• Time in Patent Office: 277 Days
• Field of Search: 701 23, 701414
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01C 21/3848 Data obtained from both position sensors and additional sensors
• CPC Class Codes: G01C 21/3881 Tile-based structures
• CPC Class Codes: G05D 1/021 specially adapted to land vehicles
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G05D 1/0278 using satellite positioning signals, e.g. GPS
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/168 involving transform domain methods
• CPC Class Codes: G06V 10/426 Graphical representations
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G08G 1/00 Traffic control systems for road vehicles arrangement of road signs or traffic signals E01F9/00 ; automatic vehicle control B62D

Abstract

A relative atlas may be used to lay out elements in a digital map used in the control of an autonomous vehicle. A vehicle pose for the autonomous vehicle within a geographical area may be determined, and the relative atlas may be accessed to identify elements in the geographical area and to determine relative poses between those elements. The elements may then be laid out within the digital map using the determined relative poses, e.g., for use in planning vehicle trajectories, for estimating the states of traffic controls, or for tracking and/or identifying dynamic objects, among other purposes.

Claims

1. A method comprising:

determining a vehicle pose for an autonomous vehicle in a geographical area, wherein determining the vehicle pose includes;

obtaining sensor data from one or more sensors of the autonomous vehicle; and

identifying a position and orientation of the autonomous vehicle within the geographical area using the sensor data;

obtaining data from a relative atlas, the data being associated with the geographical area;

identifying, based on the data obtained from the relative atlas, a first element and a second element in the geographical area, wherein the first element represents a first gate and the second element represents a second gate, each of the first gate and the second gate representing a respective vehicle pose for the autonomous vehicle in the geographical area;

determining, based upon the data obtained from the relative atlas, a relative pose that associates the first gate with the second gate in the geographical area;

inserting, in a digital map, the first gate and the second gate using the relative pose, wherein inserting the first gate and the second gate in the digital map using the relative pose includes;

inserting the first gate at a first position in the digital map;

determining a second position for the second gate relative to the first position using the relative pose; and

inserting the second gate at the second position in the digital map;

determining a particular path with respect to the vehicle pose using the first gate and the second gate in the digital map; and

in response to determining the particular path, providing data identifying the particular path to the autonomous vehicle such that the autonomous vehicle is operated autonomously based on the particular path.

2. The method of claim 1, wherein the data obtained from the relative atlas comprises a relative atlas graph that includes:

a first element node and a second element node that respectively correspond to the first element and the second element, and

an edge that represents the relative pose, the relative pose associating the first gate with the second gate in the geographical area.

3. The method of claim 2, wherein the relative atlas graph includes a plurality of element nodes, the method further comprising:

identifying, from the plurality of element nodes in the relative atlas graph, a third element node that corresponds to a third element, wherein the third element is positioned closest to the vehicle pose in the geographical area,

accessing one or more edges in the relative atlas graph to identify one or more element nodes from the plurality of element nodes in the relative atlas graph, the one or more element nodes corresponding to one or more elements that are positioned proximate to the third element, and

inserting, in the digital map, the one or more elements using one or more relative poses respectively represented by the one or more edges.

4. The method of claim 2, wherein the relative atlas graph includes a fourth element node that represents a boundary node, the boundary node representing a boundary that restricts vehicle movement within the boundary.

5. The method of claim 2, wherein the relative atlas graph includes a fifth element node that represents a traffic device node, the traffic device node being associated with a traffic control within the geographical area and representing a traffic device.

6. The method of claim 1, wherein the data obtained from the relative atlas comprises a relative atlas graph that includes:

a plurality of element nodes that respectively represent a plurality of elements in the geographical area, wherein at least two of the element nodes have different element node types, and

a plurality of edges that respectively represent relative poses, each relative pose associating two element nodes of the element nodes, wherein at least two of the edges have different edge types.

7. The method of claim 1, wherein determining the vehicle pose further includes:

building a surface model using the relative atlas,

assembling received sensor data into a point cloud,

aligning the point cloud with the surface model, and

determining the vehicle pose based on the alignment of the point cloud with the surface model.

8. An autonomous vehicle, comprising:

a memory storing a relative atlas; and

an autonomous vehicle control system coupled to the memory and configured to;

determine a vehicle pose for the autonomous vehicle in a geographical area, wherein the autonomous vehicle control system is configured to determine the vehicle pose by;

obtaining sensor data from one or more sensors of the autonomous vehicle; and

identifying a position and orientation of the autonomous vehicle within the geographical area using the sensor data;

obtain data from the relative atlas, the data being associated with the geographical area;

identify, based on the data obtained from the relative atlas, a first element and a second element in the geographical area, wherein the first element represents a first gate and the second element represents a second gate, each of the first gate and the second gate representing a respective vehicle pose for the autonomous vehicle in the geographical area;

determine, based upon the data obtained from the relative atlas, a relative pose that associates the first gate with the second gate in the geographical area;

insert, in a digital map, the first gate and the second gate using the relative pose, wherein the autonomous vehicle control system is configured to insert the first gate and the second gate in the digital map using the relative pose by;

inserting the first gate at a first position in the digital map;

determining a second position for the second gate relative to the first position using the relative pose; and

inserting the second gate at the second position in the digital map;

determine a particular path with respect to the vehicle pose using the first gate and the second gate in the digital map; and

in response to determining the particular path, providing data identifying the particular path to the autonomous vehicle such that the autonomous vehicle is operated autonomously based on the particular path.

9. The autonomous vehicle of claim 8, wherein the data obtained from the relative atlas comprises a relative atlas graph that includes:

a first element node and a second element node that respectively correspond to the first element and the second element, and

an edge that represents the relative pose, the relative pose associating the first gate with the second gate in the geographical area.

10. The autonomous vehicle of claim 9, wherein the relative atlas graph includes a plurality of element nodes, the autonomous vehicle control system further configured to:

identify, from the plurality of element nodes in the relative atlas graph, a third element node that corresponds to a third element, wherein the third element is positioned closest to the vehicle pose in the geographical area,

access one or more edges in the relative atlas graph to identify one or more element nodes from the plurality of element nodes in the relative atlas graph, the one or more element nodes corresponding to one or more elements that are positioned proximate to the third element, and

insert, in the digital map, the one or more elements using one or more relative poses respectively represented by the one or more edges.

11. The autonomous vehicle of claim 9, wherein the relative atlas graph includes a fourth element node that represents a boundary node, the boundary node representing a boundary that restricts vehicle movement within the boundary.

12. The autonomous vehicle of claim 9, wherein the relative atlas graph includes a fifth element node that represents a traffic device node, the traffic device node being associated with a traffic control within the geographical area and representing a traffic device.

13. The autonomous vehicle of claim 8, wherein the data obtained from the relative atlas comprises a relative atlas graph that includes:

a plurality of element nodes that respectively represent a plurality of elements in the geographical area, wherein at least two of the element nodes have different element node types, and

a plurality of edges that respectively represent relative poses, each relative pose associating two element nodes of the element nodes, wherein at least two of the edges have different edge types.

14. The autonomous vehicle of claim 8, wherein the autonomous vehicle control system is configured to determine the vehicle pose further by:

building a surface model using the relative atlas,

assembling received sensor data into a point cloud,

aligning the point cloud with the surface model, and

determining the vehicle pose based on the alignment of the point cloud with the surface model.

15. A non-transitory computer readable storage medium storing computer instructions executable by one or more processors to perform a method to operate an autonomous vehicle, the method comprising:

determining a vehicle pose for an autonomous vehicle in a geographical area, wherein determining the vehicle pose includes;

obtaining sensor data from one or more sensors of the autonomous vehicle; and

identifying a position and orientation of the autonomous vehicle within the geographical area using the sensor data;

obtaining data from a relative atlas, the data being associated with the geographical area;

identifying, based on the data obtained from the relative atlas, a first element and a second element in the geographical area, wherein the first element represents a first gate and the second element represents a second gate, each of the first gate and the second gate representing a respective vehicle pose for the autonomous vehicle in the geographical area;

determining, based upon the data obtained from the relative atlas, a relative pose that associates the first gate with the second gate in the geographical area;

inserting, in a digital map, the first gate and the second gate using the relative pose, wherein inserting the first gate and the second gate in the digital map using the relative pose includes;

inserting the first gate at a first position in the digital map;

determining a second position for the second gate relative to the first position using the relative pose; and

inserting the second gate at the second position in the digital map;

determining a particular path with respect to the vehicle pose using the first gate and the second gate in the digital map; and

in response to determining the particular path, providing data identifying the particular path to the autonomous vehicle such that the autonomous vehicle is operated autonomously based on the particular path.

16. The non-transitory computer readable storage medium of claim 15, wherein the data obtained from the relative atlas comprises a relative atlas graph that includes:

a first element node and a second element node that respectively correspond to the first element and the second element, and an edge that represents the relative pose, the relative pose associating the first gate with the second gate in the geographical area.

17. The non-transitory computer readable storage medium of claim 16, wherein the relative atlas graph includes a plurality of element nodes, the method further comprising:

identifying, from the plurality of element nodes in the relative atlas graph, a third element node that corresponds to a third element, wherein the third element is positioned closest to the vehicle pose in the geographical area, accessing one or more edges in the relative atlas graph to identify one or more element nodes from the plurality of element nodes in the relative atlas graph, the one or more element nodes corresponding to one or more elements that are positioned proximate to the third element, and inserting, in the digital map, the one or more elements using one or more relative poses respectively represented by the one or more edges.

18. The non-transitory computer readable storage medium of claim 16, wherein the relative atlas graph includes a fourth element node that represents a boundary node, the boundary node representing a boundary that restricts vehicle movement within the boundary.

19. The non-transitory computer readable storage medium of claim 16, wherein the relative atlas graph includes a fifth element node that represents a traffic device node, the traffic device node being associated with a traffic control within the geographical area and representing a traffic device.

20. The non-transitory computer readable storage medium of claim 15, wherein the data obtained from the relative atlas comprises a relative atlas graph that includes:

a plurality of element nodes that respectively represent a plurality of elements in the geographical area, wherein at least two of the element nodes have different element node types, and a plurality of edges that respectively represent relative poses, each relative pose associating two element nodes of the element nodes, wherein at least two of the edges have different edge types.