Laser point cloud positioning method and system
The present disclosure provides a laser point cloud positioning method and system. The method comprises: converting laser point cloud reflection value data and height value data matched with a current location of an autonomous vehicle into laser point cloud projection data in a ground plane; assigning a weight for a reflection value matching probability and a height value matching probability of the laser point cloud projection data and a laser point cloud two-dimensional grid map, and determining a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map; determining a location of the autonomous vehicle in the laser point cloud two-dimensional grid map based on a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map. The present disclosure is employed to solve the problem in the prior art that when the laser point cloud matches with the map, an undesirable matching effect is achieved by individually considering the reflection value matching or height value matching, or superimposing the two simply. The present disclosure can improve the laser point cloud positioning precision, and enhance robustness of the positioning system.
1. A laser point cloud positioning method, wherein the method comprises:
converting laser point cloud reflection value data and height value data matched with a current location of an autonomous vehicle into laser point cloud projection data in a ground plane;
assigning a weight for a reflection value matching probability and a height value matching probability of the laser point cloud projection data and a laser point cloud two-dimensional grid map, and determining a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map;
determining a location of the autonomous vehicle in the laser point cloud two-dimensional grid map based on a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map.
2. The method according to claim 1 , wherein
the laser point cloud reflection value data comprises coordinates of respective laser points and laser reflection intensity values corresponding to respective laser points;
the laser point cloud height value data comprises coordinates of respective laser points and height values corresponding to respective laser points.
3. The method according to claim 1 , wherein
the converting laser point cloud reflection value data and height value data into laser point cloud projection data in a ground plane comprises:
projecting laser point cloud reflection values of respective coordinate positions in a three-dimensional space to a ground plane, to obtain laser point cloud reflection values of respective coordinate positions in the ground plane;
project laser point cloud height values of respective coordinate positions in the three-dimensional space to the ground plane, to obtain laser point cloud height values of respective coordinate positions in the ground plane.
4. The method according to claim 1 , wherein the laser point cloud two-dimensional grid map is generated in the following manner:
gridding the map to obtain map grids;
collecting laser point cloud reflection value data and laser point cloud height value data corresponding to positioned locations of respective map grids;
storing, in respective map grids, map data corresponding thereto;
the map data comprise an average value of laser reflection intensity values of respective laser points in the positioned locations corresponding to the map grids, a variance of laser reflection intensity values of respective laser points in the positioned locations corresponding to the map grids, an average value of height values of respective laser points in the positioned locations corresponding to the map grids, and the number of respective laser points in the positioned locations corresponding to the map grids.
5. The method according to claim 1 , wherein
the assigning a weight for a reflection value matching probability and a height value matching probability of the laser point cloud projection data and a laser point cloud two-dimensional grid map, and determining a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map comprises:
calculating a reflection value matching probability and a height value matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map;
according to a variance of distribution of the reflection value matching probability and a variance of distribution of the height value matching probability, calculate an adaptive weight of the reflection value matching probability and an adaptive weight of the height value matching probability;
calculating a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map, according to the reflection value matching probability, the height value matching probability and the adaptive weights obtained from the calculation.
6. The method according to claim 5 , wherein the adaptive weight γ of the reflection value matching probability is calculated from the following equation:
γ
=
σ
x
2
(
a
)
σ
y
2
(
a
)
σ
x
2
(
a
)
σ
y
2
(
a
)
+
σ
x
2
(
r
)
σ
y
2
(
r
)
,
where σ x 2 (r) is a variance of the distribution of the reflection value matching probability in a direction x, σ y 2 (a) is a variance of the distribution of the reflection value matching probability in a direction y, σ x 2 (a) is a variance of the distribution of the height value matching probability in a direction x, and σ y 2 (a) is a variance of the distribution of the height value matching probability in a direction y;
the adaptive weight of the height value matching probability is 1−γ.
7. The method according to claim 1 , wherein the determining a location of the autonomous vehicle in the laser point cloud two-dimensional grid map based on the matching probability comprises:
updating the matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map based on a previous positioned location, and calculating a posterior probability of the laser point cloud projection data in a predetermined range of the laser point cloud two-dimensional grid map;
determining a location of the autonomous vehicle in the laser point cloud two-dimensional grid map based on distribution of the posterior probability.
8. A computer device, comprising a memory, a processor and a computer program which is stored on the memory and runnable on the processor, wherein the processor, upon executing the program, implements a laser point cloud positioning method, wherein the method comprises:
converting laser point cloud reflection value data and height value data matched with a current location of an autonomous vehicle into laser point cloud projection data in a ground plane;
assigning a weight for a reflection value matching probability and a height value matching probability of the laser point cloud projection data and a laser point cloud two-dimensional grid map, and determining a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map;
determining a location of the autonomous vehicle in the laser point cloud two-dimensional grid map based on a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map.
9. The computer device according to claim 8 , wherein
the laser point cloud reflection value data comprises coordinates of respective laser points and laser reflection intensity values corresponding to respective laser points;
the laser point cloud height value data comprises coordinates of respective laser points and height values corresponding to respective laser points.
10. The computer device according to claim 8 , wherein
the converting laser point cloud reflection value data and height value data into laser point cloud projection data in a ground plane comprises:
projecting laser point cloud reflection values of respective coordinate positions in a three-dimensional space to a ground plane, to obtain laser point cloud reflection values of respective coordinate positions in the ground plane;
project laser point cloud height values of respective coordinate positions in the three-dimensional space to the ground plane, to obtain laser point cloud height values of respective coordinate positions in the ground plane.
11. The computer device according to claim 8 , wherein the laser point cloud two-dimensional grid map is generated in the following manner:
gridding the map to obtain map grids;
collecting laser point cloud reflection value data and laser point cloud height value data corresponding to positioned locations of respective map grids;
storing, in respective map grids, map data corresponding thereto;
the map data comprise an average value of laser reflection intensity values of respective laser points in the positioned locations corresponding to the map grids, a variance of laser reflection intensity values of respective laser points in the positioned locations corresponding to the map grids, an average value of height values of respective laser points in the positioned locations corresponding to the map grids, and the number of respective laser points in the positioned locations corresponding to the map grids.
12. The computer device according to claim 8 , wherein
the assigning a weight for a reflection value matching probability and a height value matching probability of the laser point cloud projection data and a laser point cloud two-dimensional grid map, and determining a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map comprises:
calculating a reflection value matching probability and a height value matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map;
according to a variance of distribution of the reflection value matching probability and a variance of distribution of the height value matching probability, calculate an adaptive weight of the reflection value matching probability and an adaptive weight of the height value matching probability;
calculating a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map, according to the reflection value matching probability, the height value matching probability and the adaptive weights obtained from the calculation.
13. The computer device according to claim 12 , wherein the adaptive weight γ of the reflection value matching probability is calculated from the following equation:
γ
=
σ
x
2
(
a
)
σ
y
2
(
a
)
σ
x
2
(
a
)
σ
y
2
(
a
)
+
σ
x
2
(
r
)
σ
y
2
(
r
)
,
where σ x 2 (r) is a variance of the distribution of the reflection value matching probability in a direction x, σ y 2 (r) is a variance of the distribution of the reflection value matching probability in a direction y, σ x 2 (a) is a variance of the distribution of the height value matching probability in a direction x, and σ y 2 (a) is a variance of the distribution of the height value matching probability in a direction y;
the adaptive weight of the height value matching probability is 1−γ.
14. The computer device according to claim 8 , wherein the determining a location of the autonomous vehicle in the laser point cloud two-dimensional grid map based on the matching probability comprises:
updating the matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map based on a previous positioned location, and calculating a posterior probability of the laser point cloud projection data in a predetermined range of the laser point cloud two-dimensional grid map;
determining a location of the autonomous vehicle in the laser point cloud two-dimensional grid map based on distribution of the posterior probability.
15. A non-transitory computer-readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a laser point cloud positioning method, wherein the method comprises:
converting laser point cloud reflection value data and height value data matched with a current location of an autonomous vehicle into laser point cloud projection data in a ground plane;
assigning a weight for a reflection value matching probability and a height value matching probability of the laser point cloud projection data and a laser point cloud two-dimensional grid map, and determining a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map;
determining a location of the autonomous vehicle in the laser point cloud two-dimensional grid map based on a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map.
16. The non-transitory computer-readable storage medium according to claim 15 , wherein
the laser point cloud reflection value data comprises coordinates of respective laser points and laser reflection intensity values corresponding to respective laser points;
the laser point cloud height value data comprises coordinates of respective laser points and height values corresponding to respective laser points.
17. The non-transitory computer-readable storage medium according to claim 15 , wherein
the converting laser point cloud reflection value data and height value data into laser point cloud projection data in a ground plane comprises:
projecting laser point cloud reflection values of respective coordinate positions in a three-dimensional space to a ground plane, to obtain laser point cloud reflection values of respective coordinate positions in the ground plane;
project laser point cloud height values of respective coordinate positions in the three-dimensional space to the ground plane, to obtain laser point cloud height values of respective coordinate positions in the ground plane.
18. The non-transitory computer-readable storage medium according to claim 15 , wherein the laser point cloud two-dimensional grid map is generated in the following manner:
gridding the map to obtain map grids;
collecting laser point cloud reflection value data and laser point cloud height value data corresponding to positioned locations of respective map grids;
storing, in respective map grids, map data corresponding thereto;
the map data comprise an average value of laser reflection intensity values of respective laser points in the positioned locations corresponding to the map grids, a variance of laser reflection intensity values of respective laser points in the positioned locations corresponding to the map grids, an average value of height values of respective laser points in the positioned locations corresponding to the map grids, and the number of respective laser points in the positioned locations corresponding to the map grids.
19. The non-transitory computer-readable storage medium according to claim 15 , wherein
the assigning a weight for a reflection value matching probability and a height value matching probability of the laser point cloud projection data and a laser point cloud two-dimensional grid map, and determining a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map comprises:
calculating a reflection value matching probability and a height value matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map;
according to a variance of distribution of the reflection value matching probability and a variance of distribution of the height value matching probability, calculate an adaptive weight of the reflection value matching probability and an adaptive weight of the height value matching probability;
calculating a matching probability of the laser point cloud projection data and the laser point cloud two-dimensional grid map, according to the reflection value matching probability, the height value matching probability and the adaptive weights obtained from the calculation.
20. The non-transitory computer-readable storage medium according to claim 19 , wherein the adaptive weight γ of the reflection value matching probability is calculated from the following equation:
γ
=
σ
x
2
(
a
)
σ
y
2
(
a
)
σ
x
2
(
a
)
σ
y
2
(
a
)
+
σ
x
2
(
r
)
σ
y
2
(
r
)
,
where σ x 2 (r) is a variance of the distribution of the reflection value matching probability in a direction x, σ y 2 (r) is a variance of the distribution of the reflection value matching probability in a direction y, σ x 2 (a) is a variance of the distribution of the height value matching probability in a direction x, and σ y 2 (a) is a variance of the distribution of the height value matching probability in a direction y;
the adaptive weight of the height value matching probability is 1−γ.