Multi-mode visual geometry localization

1. A computer-implemented method comprising:

determining, by a computing system, visual geometry detections associated with geometry corresponding with a map;

aligning, by the computing system, the visual geometry detections with the geometry based on transformations associated with selected degrees of freedom;

generating, by the computing system, a grid map based on the geometry, wherein the grid map includes a grid of cells and the cells are associated with values based on presence or absence of a boundary line in the geometry; and

determining, by the computing system, a pose of a vehicle based on alignment of the visual geometry detections with the geometry.

2. The computer-implemented method of claim 1 ,

wherein the cells are associated with values based on whether the cells are adjacent to the boundary line.

3. The computer-implemented method of claim 1 , further comprising:

generating, by the computing system, a score for the visual geometry detections based on the visual geometry detections overlaid on the grid map.

4. The computer-implemented method of claim 1 , further comprising:

determining, by the computing system, a set of poses, including the pose, based on a set of visual geometry detections, including the visual geometry detections, wherein the pose is determined from the set of poses based on a trajectory of the vehicle.

5. The computer-implemented method of claim 1 , further comprising:

loading, by the computing system, a high definition (HD) map based on a GPS position.

6. The computer-implemented method of claim 1 , wherein the transformations associated with selected degrees of freedom are transformations with respect to pitch, yaw, x-axis, and y-axis, and wherein a transformation with respect to yaw is determined based on transformation with respect to pitch.

7. The computer-implemented method of claim 6 , wherein the transformation with respect to yaw is based on a median angle difference determined based on alignment of the visual geometry detections with the geometry with respect to pitch.

8. The computer-implemented method of claim 1 , wherein the aligning the visual geometry detections comprises:

aligning, by the computing system, the visual geometry detections based on transformations with respect to pitch and yaw; and

subsequent to the aligning the visual geometry detections based on transformations with respect to pitch and yaw, aligning, by the computing system, the visual geometry detections based on transformations with respect to the x-axis and y-axis.

9. The computer-implemented method of claim 1 , wherein the aligning the visual geometry detections does not perform transformations with respect to roll and z-axis.

10. The computer-implemented method of claim 1 , wherein the visual geometry detections include detected lane lines and the geometry includes lane boundary lines.

11. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:

determining visual geometry detections associated with geometry corresponding with a map;

aligning the visual geometry detections with the geometry based on transformations associated with selected degrees of freedom;

generating a grid map based on the geometry, wherein the grid map includes a grid of cells and the cells are associated with values based on presence or absence of a boundary line in the geometry; and

determining a pose of a vehicle based on alignment of the visual geometry detections with the geometry.

12. The system of claim 11 , wherein the

cells are associated with values based on whether the cells are adjacent to the boundary line.

13. The system of claim 11 , wherein the operations further comprise:

generating a score for the visual geometry detections based on the visual geometry detections overlaid on the grid map.

14. The system of claim 11 , wherein the operations further comprise:

determining a set of poses, including the pose, based on a set of visual geometry detections, including the visual geometry detections, wherein the pose is determined from the set of poses based on a trajectory of the vehicle.

15. The system of claim 11 , wherein the operations further comprise:

loading a high definition (HD) map based on a GPS position.

16. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform operations comprising:

determining visual geometry detections associated with geometry corresponding with a map;

aligning the visual geometry detections with the geometry based on transformations associated with selected degrees of freedom;

generating a grid map based on the geometry, wherein the grid map includes a grid of cells and the cells are associated with values based on presence or absence of a boundary line in the geometry; and

determining a pose of a vehicle based on alignment of the visual geometry detections with the geometry.

17. The non-transitory computer-readable storage medium of claim 16 , wherein the

cells are associated with values based on whether the cells are adjacent to the boundary line.

18. The non-transitory computer-readable storage medium of claim 16 , wherein the operations further comprise:

generating a score for the visual geometry detections based on the visual geometry detections overlaid on the grid map.

19. The non-transitory computer-readable storage medium of claim 16 , wherein the operations further comprise:

determining a set of poses, including the pose, based on a set of visual geometry detections, including the visual geometry detections, wherein the pose is determined from the set of poses based on a trajectory of the vehicle.

20. The non-transitory computer-readable storage medium of claim 16 , wherein the operations further comprise:

loading a high definition (HD) map based on a GPS position.