Autonomous Driving Certification Generalizer

• US 20170059335A1
• Filed: 09/02/2015
• Published: 03/02/2017
• Est. Priority Date: 09/02/2015
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Levine, Daniel, Jain, Jinesh J.
• Granted Patent: US 9,940,625 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01C 21/3819 Road shape data, e.g. outline of a route
• CPC Class Codes: G01C 21/3822 Road feature data, e.g. slope data
• CPC Class Codes: G01C 21/3841 Data obtained from two or more sources, e.g. probe vehicles
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06Q 30/016 After-sales

Abstract

Methods, devices and apparatuses pertaining to identifying the candidate road segments for autonomous operations are described. A method may involve obtaining data of a first plurality of road segments that are permitted for one or more autonomous operations. The method may further include generating a road segment template based on the data of the first plurality of road segments, and reconstructing a second plurality of road segments based on the road segment template to obtain a plurality of reconstructed road segments.

Claims

1. A computer-implemented method, comprising:

obtaining data of a first plurality of road segments permitted for one or more autonomous operations in an autonomous level;

generating a road segment template based on the data; and

reconstructing a second plurality of road segments, that have not been permitted for the one or more autonomous operations in the autonomous level, based on the road segment template to provide a plurality of reconstructed road segments.

2. The method of claim 1, further comprising:

selecting one or more road segments from the plurality of reconstructed road segments; and

scheduling a road test on the selected one or more road segments.

3. The method of claim 1, further comprising:

submitting one or more road segments of the plurality of reconstructed road segments as one or more candidate road segments to a regulatory body for a permit for the one or more autonomous operations on the one or more candidate road segments in the autonomous level.

4. The method of claim 1, wherein the generating of the road segment template based on the first plurality of road segments comprises:

partitioning the first plurality of road segments using a nonparametric clustering technique to identify a plurality of road network configurations; and

imposing a constraint on the plurality of road network configurations to generate the road segment template.

5. The method of claim 4, wherein the plurality of road network configurations comprise a plurality of attributes and a plurality of values corresponding to the plurality of attributes.

6. The method of claim 5, wherein the plurality of attributes are associated with at least one of topology, geometry, visibility, mobility profiles, traffic patterns, traffic signage and signals, or environmental factors associated with the first plurality of road segments.

7. The method of claim 4, wherein the constraint comprises either or both of a contiguity condition and a continuity condition.

8. The method of claim 7, wherein the contiguity condition indicates connectedness of each of one or more individual road segments of the first plurality of road segments with respect to one or more other road segments of the first plurality of road segments, and wherein the continuity condition indicates a similarity of mobility profiles of two road segments of the first plurality of road segments.

9. The method of claim 1, further comprising:

ranking the plurality of reconstructed road segments based on a contiguity condition indicating connectedness of each of one or more individual road segments of the plurality of reconstructed road segments.

10. The method of claim 1, further comprising:

obtaining data of the second plurality of road segments.

11. The method of claim 1, wherein the autonomous level comprises driver assistance, partial automation, conditional automation, high automation, full automation, or a combination thereof.

12. One or more computer-readable media storing computer-executable instructions that, when executed on one or more processors, causes the one or more processors to perform operations comprising:

obtaining data of a first plurality of road segments that are permitted for one or more autonomous operations;

generating one or more road segment templates based on the data of the first plurality of road segments;

obtaining data of a second plurality of road segments that have not been permitted for the one or more autonomous operations; and

reconstructing the second plurality of road segments based on the one or more road segment templates to obtain a plurality of reconstructed road segments.

13. The one or more computer-readable media of claim 12, wherein the operations further comprise:

selecting one or more road segments from the plurality of reconstructed road segments; and

scheduling a road test on the selected one or more candidate road segments;

14. The one or more computer-readable media of claim 12, wherein the operations further comprise:

submitting one or more road segments of the plurality of reconstructed road segments as one or more candidate road segments to a regulatory body for a permit for the one or more autonomous operations on the one or more candidate road segments.

15. The one or more computer-readable media of claim 12, wherein the operations further comprise:

ranking the plurality of reconstructed road segments based on a contiguity condition indicating connectedness of each of one or more individual road segments of the plurality of reconstructed road segments with respect to one or more other road segments of the first plurality of road segments.

16. A system, comprising:

one or more processors; and

a memory configured to maintain a plurality of components executable by the one or more processors, the plurality of components comprising;

a road segment handler configured to perform operations comprising;

obtaining data of a first plurality of road segments that are permitted for one or more autonomous operations, and

obtaining data of a second plurality of road segments that have not been permitted for the one or more autonomous operations; and

a template generator configured to perform operations comprising;

generating one or more road segment templates based on the data of the first plurality of road segments, and

reconstructing the second plurality of road segments based on the one or more road segment templates to obtain a plurality of reconstructed road segments.

17. The system of claim 16, wherein the plurality of components further comprise:

a ranking module configured to select one or more road segments from the plurality of reconstructed road segments; and

a scheduler configured to schedule a road test on the selected one or more candidate road segments.

18. The system of claim 16, wherein the plurality of components further comprise a reporting module configured to submit one or more road segments of the plurality of reconstructed road segments as one or more candidate road segments to a regulatory body for a permit for the one or more autonomous operations on the one or more candidate road segments.

19. The system of claim 16, wherein the plurality of components further comprise a ranking module configured to rank the plurality of reconstructed road segments based on a contiguity condition indicating connectedness of each of one or more individual road segments of the plurality of reconstructed road segments with respect to one or more other road segments of the first plurality of road segments.

20. The system of claim 16, wherein the generating of the one or more road segment templates based on the first plurality of road segments comprises clustering the first plurality of road segments using nonparametric clustering and geometric hashing techniques to establish the one or more road segment templates.