Using measure of constrainedness in high definition maps for localization of vehicles

1. A computer-implemented method, comprising:

accessing a set of vehicle poses of one or more vehicles, each vehicle pose of the set of vehicle poses comprising a geographic location and an orientation of the one or more vehicles;

for each vehicle pose of the set of vehicle poses:

accessing a high definition (HD) map of a geographical region surrounding the vehicle pose, the HD map comprising a three-dimensional (3D) representation of the geographical region,

determining a measure of constrainedness for the vehicle pose, the measure of constrainedness representing a confidence for performing localization for the vehicle pose and being based on a presence of 3D structures surrounding the vehicle pose, the measure of constrainedness indicating an increased confidence when the presence of 3D structures is higher as compared to when the presence of 3D structures is lower, and

storing the measure of constrainedness for the vehicle pose;

for each geographical region surrounding each vehicle pose of the set of vehicle poses:

determining a measure of constrainedness for the geographical region based on measures of constrainedness of vehicle poses within the geographical region, and

storing the measure of constrainedness for the geographical region; and

providing at least one measure of constrainedness to an autonomous vehicle such that the autonomous vehicle uses the at least one measure of constrainedness in performing one or more driving operations.

2. The computer-implemented method of claim 1 , wherein the measure of constrainedness for a geographical region may be employed as a measure of uncertainty in a Kalman filter used for localization of a vehicle located in the geographical region.

3. The computer-implemented method of claim 1 , wherein the measure of constrainedness for each geographical region surrounding each vehicle pose of the set of vehicle poses is stored in a layer of the HD map of the geographical region.

4. The computer-implemented method of claim 1 , wherein the measure of constrainedness for each vehicle pose of the set of vehicle poses is determined based on a rate of convergence of a localization process along a particular direction.

5. The method of claim 1 , wherein the measure of constrainedness for each vehicle pose of the set of vehicle poses comprises a plurality of constrainedness values corresponding to a plurality of directions.

6. The method of claim 1 , wherein the measure of constrainedness is determined with respect to a LIDAR sensor and is configured to be employed as a measure of uncertainty in a LIDAR-based localization of a vehicle located in the geographical region.

7. The method of claim 1 , wherein the measure of constrainedness is determined with respect to a camera sensor and is configured to be employed as a measure of uncertainty in a camera-based localization of a vehicle located in the geographical region.

8. One or more non-transitory computer readable storage media storing instructions that in response to being executed by one or more processors, cause a computer system to perform operations, the operations comprising:

accessing a set of vehicle poses of one or more vehicles, each vehicle pose of the set of vehicle poses comprising a geographic location and an orientation of the one or more vehicles;

for each vehicle pose of the set of vehicle poses:

accessing a high definition (HD) map of a geographical region surrounding the vehicle pose, the HD map comprising a three-dimensional (3D) representation of the geographical region,

determining a measure of constrainedness for the vehicle pose, the measure of constrainedness representing a confidence for performing localization for the vehicle pose and being based on a presence of 3D structures surrounding the vehicle pose such that the measure of constrainedness indicates differences in confidence according to differences in presence of the 3D structures, and

storing the measure of constrainedness for the vehicle pose;

for each geographical region surrounding each vehicle pose of the set of vehicle poses:

determining a measure of constrainedness for the geographical region based on measures of constrainedness of vehicle poses within the geographical region, and

storing the measure of constrainedness for the geographical region; and

providing at least one measure of constrainedness to an autonomous vehicle such that the autonomous vehicle uses the at least one measure of constrainedness in performing one or more localization operations.

9. The one or more non-transitory computer-readable storage media of claim 8 , wherein the measure of constrainedness for a geographical region may be employed as a measure of uncertainty in a Kalman filter used for localization of a vehicle located in the geographical region.

10. The one or more non-transitory computer-readable storage media of claim 8 , wherein the measure of constrainedness for each geographical region surrounding each vehicle pose of the set of vehicle poses is stored in a layer of the HD map of the geographical region.

11. The one or more non-transitory computer-readable storage media of claim 8 , wherein the measure of constrainedness for each vehicle pose of the set of vehicle poses is determined based on a rate of convergence of a localization process along a particular direction.

12. The one or more non-transitory computer-readable storage media of claim 8 , wherein the measure of constrainedness for each vehicle pose of the set of vehicle poses comprises a plurality of constrainedness values corresponding to a plurality of directions.

13. The one or more non-transitory computer-readable storage media of claim 8 , wherein the measure of constrainedness is determined with respect to a LIDAR sensor and is configured to be employed as a measure of uncertainty in a LIDAR-based localization of a vehicle located in the geographical region.

14. The one or more non-transitory computer-readable storage media of claim 8 , wherein the measure of constrainedness is determined with respect to a camera sensor and is configured to be employed as a measure of uncertainty in a camera-based localization of a vehicle located in the geographical region.

15. A computer system comprising:

one or more processors; and

one or more non-transitory computer readable media storing instructions that in response to being executed by the one or more processors, cause the computer system to perform operations, the operations comprising:

accessing a set of vehicle poses of one or more vehicles, each vehicle pose of the set of vehicle poses comprising a geographic location and an orientation of the one or more vehicles;

for each vehicle pose of the set of vehicle poses:

accessing a high definition (HD) map of a geographical region surrounding the vehicle pose, the HD map comprising a three-dimensional (3D) representation of the geographical region,

determining a measure of constrainedness for the vehicle pose, the measure of constrainedness representing a confidence for performing localization for the vehicle pose and being based on a presence of 3D structures surrounding the vehicle pose such that the measure of constrainedness indicates differences in confidence according to differences in the presence of the 3D structures, and

storing the measure of constrainedness for the vehicle pose;

for each geographical region surrounding each vehicle pose of the set of vehicle poses:

determining a measure of constrainedness for the geographical region based on measures of constrainedness of vehicle poses within the geographical region, and

storing the measure of constrainedness for the geographical region; and

providing at least one measure of constrainedness to an autonomous vehicle such that the autonomous vehicle uses the at least one measure of constrainedness in performing one or more driving operations.

16. The computer system of claim 15 , wherein the measure of constrainedness for a geographical region may be employed as a measure of uncertainty in a Kalman filter used for localization of a vehicle located in the geographical region.

17. The computer system of claim 15 , wherein the measure of constrainedness for each vehicle pose of the set of vehicle poses is determined based on a rate of convergence of a localization process along a particular direction.

18. The computer system of claim 15 , wherein the autonomous vehicle uses the measure of constrainedness in performing the one or more driving operations by using the measure of constrainedness in performing one or more localization operations to determine its pose and uses its determined pose to perform the one or more driving operations.

19. The computer system of claim 15 , wherein the measure of constrainedness for each vehicle pose of the set of vehicle poses comprises a plurality of constrainedness values corresponding to a plurality of directions.

20. The computer system of claim 19 , wherein the measure of constrainedness is determined with respect to a LIDAR sensor and is configured to be employed as a measure of uncertainty in a LIDAR-based localization of a vehicle located in the geographical region.

21. The computer system of claim 15 , the measure of constrainedness is determined with respect to a camera sensor and is configured to be employed as a measure of uncertainty in a camera-based localization of a vehicle located in the geographical region.