Method, device and apparatus for acquiring map, and computer readable storage medium

1. A method for acquiring a map, applicable to a server, comprising:

receiving by the server, raw data for mapping in an acquisition area acquired by a plurality of sensors mounted on a first acquisition entity;

generating by the server, a reference map of the acquisition area based on the raw data;

dividing by the server, the acquisition area into a plurality of sub-areas based on the reference map;

generating by the server, a plurality of acquisition tasks corresponding to the plurality of sub-areas, wherein each of the plurality of acquisition tasks is configured to instruct each of a plurality of second acquisition entities to acquire a set of point cloud data of each sub-area to generate a map of each of the plurality of sub-areas;

assigning by the server, each of the plurality of acquisition tasks to each of the plurality of second acquisition entities;

receiving by the server, the map of each of the plurality of sub-areas sent by each of the plurality of second acquisition entities in response to determining that an accuracy of the map of each sub-area is within a predetermined range; and

performing by the server, map conflation based on the map of each of the plurality of sub-areas acquired by each of the plurality of second acquisition entities to update the reference map;

wherein the accuracy of the map of each sub-area is determined by:

simulating with a virtual object, motion of the second acquisition entity when acquiring the set of point cloud data;

determining a second set of poses of the virtual object when simulating the motion based on the map of the sub-area; and

matching the second set of poses with a first set of poses of the second acquisition entity when acquiring the set of point cloud data.

2. The method according to claim 1 , wherein each of the plurality of sub-areas is a polygonal area.

3. The method according to claim 1 , wherein each of the plurality of sub-areas comprises only one driving path, and the driving path comprises an entrance and an exit.

4. The method according to claim 1 , wherein dividing the acquisition area into the plurality of sub-areas comprises:

recognizing a road element of the reference map; and

dividing the acquisition area into the plurality of sub-areas based on the recognized road element.

5. The method according to claim 4 , wherein the road element comprises at least one of a lane line, and a junction.

6. A device for acquiring a map, applicable to a server, comprising:

one or more processors; and

a memory, configured to store one or more programs;

wherein when the one or more programs are executed by the one or more processors, causes the one or more processors to:

receive raw data for mapping in an acquisition area acquired by sensors on a first acquisition entity;

generate a reference map of an acquisition area based on the raw data;

divide the acquisition area into a plurality of sub-areas based on the reference map;

generate a plurality of acquisition tasks corresponding to the plurality of sub-areas, wherein each of the plurality of acquisition tasks is configured to instruct each of a plurality of second acquisition entities to acquire a set of point cloud data of each sub-area to generate a map of each of the plurality of sub-areas;

assign each of the plurality of acquisition tasks to each of the plurality of second acquisition entities;

receive the map of each of the plurality of sub-areas sent by each of the plurality of second acquisition entities in response to determining that an accuracy of the map of each sub-area is within a predetermined range; and

perform map conflation based on the map of each of the plurality of sub-areas acquired by each of the plurality of second acquisition entities to update the reference map;

wherein the accuracy of the map of each sub-area is determined by:

simulating with a virtual object, motion of the second acquisition entity when acquiring the set of point cloud data;

determining a second set of poses of the virtual object when simulating the motion based on the map of the sub-area; and

matching the second set of poses with a first set of poses of the second acquisition entity when acquiring the set of point cloud data.

7. The device according to claim 6 , wherein each of the plurality of sub-areas is a polygonal area.

8. The device according to claim 6 , wherein each of the plurality of sub-areas comprises only one driving path, and the driving path comprises an entrance and an exit.

9. The device according to claim 6 , wherein the one or more processors further configured to:

recognize a road element of the reference map; and

divide the acquisition area into the plurality of sub-areas based on the recognized road element.

10. The device according to claim 9 , wherein the road element comprises at least one of a lane line, and a junction.

11. A device for acquiring a map, applicable to an acquisition entity, comprising:

one or more processors; and

a memory, configured to store one or more programs;

wherein when the one or more programs are executed by the one or more processors, causes the one or more processors to:

acquire an acquisition task assigned to the acquisition entity from a server, wherein the acquisition area is divided into a plurality of sub-areas based on a reference map of the acquisition area, the reference map is generated by the server based on raw data acquired by a plurality of sensors, and the acquisition task is configured to instruct the acquisition entity to acquire a map of a sub-area of the plurality of sub-areas;

determine whether the acquisition entity is within the sub-area;

acquire a set of point cloud data of the sub-area to generate the map of the sub-area in response to determining that the acquisition entity is within the sub-area; and

send the map of the sub-area to the server in response to an accuracy of the map of the sub-area being within a predetermined range;

wherein the one or more processors are further configured to

simulate with a virtual object, motion of the acquisition entity when acquiring the set of point cloud data;

determine a second set of poses of the virtual object when simulating the motion based on the map of the sub-area; and

determine the accuracy by matching the second set of poses with a first set of poses of the acquisition entity when acquiring the set of point cloud data.

12. The device according to claim 11 , wherein the one or more processors are further configured to:

determine a first location where the acquisition entity is located;

determine a number of intersections at which a line connecting from a second location outside the sub-area to the first location intersects a perimeter of the sub-area; and

determine that the acquisition entity is not within the sub-area in response to the number of intersections being even; and determine that the acquisition entity is within the sub-area in response to the number of intersections being odd.

13. The device according to claim 11 , wherein the one or more processors are further configured to:

acquire the set of point cloud data of the sub-area during an acquisition period in response to determining that the acquisition entity is within the sub-area;

store the acquired set of point cloud data at the acquisition entity; and

generate the map of the sub-area based on the stored set of point cloud data during a non-acquisition period.

14. The device according to claim 13 , wherein the one or more processors are further configured to:

generate a point cloud map of the sub-area by determining a first set of poses of the acquisition entity when acquiring the set of point cloud data;

wherein the first set of poses is determined by minimizing an objective function expressed by:

{

X

}

←

argmin

⁢

{

∑

i

⁢



(

Δ

⁢

⁢

p

i

·

x

i

2

-

x

i

1

)

pair

+

(

Δ

⁢

⁢

p

_

i

·

x

i

2

-

x

i

1

)

pair



2

}

where Δ{circumflex over (p)} i represents priori pose adjustment quantity provided by a GPS module and an inertial measurement unit on the acquisition entity, X i 1 denotes a target pose corresponding to target point cloud in the i th point cloud pair to be solved, X i 2 denotes a source pose corresponding to source point cloud in the i th point cloud pair to be solved, and {X} denotes a set of poses.

15. The device according to claim 14 , wherein the one or more processors are further configured to:

convert the point cloud map to a reflection value map by projecting the point cloud map into a coordinate system.

16. The device according to claim 15 , wherein the one or more processors are further configured to:

determine an initial predicted location of the virtual object based on GPS signals of the acquisition entity;

calculate a matching probability of each possible location in a preset range centering on the initial predicted location, in which the matching probability indicates a probability based on a matching between a laser reflection value and a height value of each point cloud scanned by the virtual object and a reflection value and a height value included in the reflection value map;

determine a precise location of the virtual vehicle based on a distribution of matching probabilities.