Systems and methods for updating highly automated driving maps

Patent metadata

Field	Value
Publication number	US-10896539-B2
Application number	US-201816217988-A
Country	US
Kind code	B2
Filing date	Dec 12, 2018
Priority date	Jun 22, 2018
Publication date	Jan 19, 2021
Grant date	Jan 19, 2021

Abstract

Embodiments of the disclosure provide methods and systems for updating a HAD map using a plurality of terminals. The system may include a communication interface configured to communicate with the plurality of terminals via a network. The system may further include a storage configured to store the HAD map. The system may also include at least one processor. The at least one processor may be configured to identify a target region including at least one changing object. The at least one processor may be further configured to instruct the plurality of terminals to acquire data of the target region at varying view positions, and receive the acquired data from the plurality of terminals. The at least one processor may be further configured to construct a three-dimensional model for the at least one changing object from the acquired data, and update the HAD map based on the three-dimensional model.

First claim

What is claimed is:

1. A system for updating a HAD map using a plurality of terminals, comprising:
a communication interface configured to communicate with the plurality of terminals via a network, the plurality of terminals being positioned based on the HAD map;
a storage configured to store the HAD map; and
at least one processor, configured to:
identify a target region including at least one changing object;
instruct the plurality of terminals to acquire data of the target region at varying view positions;
receive the acquired data from the plurality of terminals;
construct a three-dimensional model for the at least one changing object from the acquired data; and
update the HAD map based on the three-dimensional model.

2. The system of claim 1 , wherein the plurality of terminals include at least one camera configured to acquire image data.

3. The system of claim 1 , wherein the plurality of terminals are configured to:
acquire image data indicative of objects associated with the HAD map;
detect the at least one changing object based on the image data; and
report the at least one changing object to the at least one processor.

4. The system of claim 1 , wherein the at least one processor is further configured to reconstruct the at least one changing object using a Structure from Motion algorithm.

5. The system of claim 4 , wherein a predetermined shape is used as a constraint for the Structure from Motion algorithm.

6. The system of claim 1 , wherein the three-dimensional model is a point cloud model.

7. The system of claim 1 , wherein the at least one processor is further configured to cause to adjust the plurality of terminals to acquire supplemental data based on the three-dimensional model.

8. The system of claim 1 , wherein to update the HAD map, the at least one processor is further configured to match a first point cloud associated with the at least one changing object with a second point cloud associated with the HAD map.

9. The system of claim 1 , wherein to update the HAD map, the at least one processor is further configured to transform the three-dimensional model into a coordinate of the HAD map.

10. A method for updating a HAD map using a plurality of terminals, comprising:
identifying, by at least one processor, a target region including at least one changing object;
instructing, by the at least one processor, the plurality of terminals to acquire data of the target region at varying view positions, the plurality of terminals being positioned based on the HAD map;
receiving the acquired data from the plurality of terminals;
constructing, by the at least one processor, a three-dimensional model for the at least one changing object from the acquired data; and
updating, by the at least one processor, the HAD map based on the three-dimensional model.

11. The method of claim 10 , further including:
acquiring, by the plurality of terminals, image data indicative of objects associated with the HAD map; and
detecting, by the plurality of terminals, the at least one changing object based on the image data.

12. The method of claim 10 , further including reconstructing the at least one changing object using a Structure from Motion algorithm.

13. The method of claim 12 , wherein a predetermined shape is used as a constraint for the Structure from Motion algorithm.

14. The method of claim 10 , wherein the three-dimensional model is a point cloud model.

15. The method of claim 10 , further including causing to adjust the plurality of terminals to acquire supplemental data based on the three-dimensional model.

16. The method of claim 10 , wherein updating the HAD map further includes matching a first point cloud associated with the target region with a second point cloud associated with the HAD map.

17. The method of claim 10 , wherein updating the HAD map further includes transforming the three-dimensional model into a coordinate of the HAD map.

18. A non-transitory computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by at least one processor, performs a method for updating a HAD map using a plurality of terminals, the method comprising:
identifying a target region including at least one changing object;
instructing the plurality of terminals to acquire data of the target region at varying view positions, the plurality of terminals being positioned based on the HAD map;
receiving the acquired data from the plurality of terminals;
constructing a three-dimensional model for the at least one changing object from the acquired data; and
updating the HAD map based on the three-dimensional model.

Assignees

• Beijing Didi Infinity Technology & Dev Co Ltd

Inventors

• Ma Teng
• Qu Xiaozhi
• Li Baoli

Classifications

• G01C21/3848

  Data obtained from both position sensors and additional sensors · CPC title

• G01C21/3841 Primary

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

• G01C21/3807

  characterised by the type of data · CPC title

• G01C11/00 Primary

  Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title