Approaches for mapping geographic regions

1. A computer-implemented method comprising:

determining, by a computing system, sensor data of a location of a geographic region collected by one or more vehicles while navigating the location of the geographic region, wherein the collected sensor data includes sensor readings generated at least in part by a surface interaction between the one or more vehicles and a road surface of the location;

determining, by the computing system, a sensor map representing the geographic region, wherein the sensor map segments a plurality of locations associated with the geographic region into a grid of cells;

associating, by the computing system, the collected sensor data with at least one cell in the grid of cells corresponding to the location of the geographic region navigated by the one or more vehicles;

determining, by the computing system, at least one corresponding fingerprint for the at least one cell based at least in part on the collected sensor data associated with the at least one cell;

localizing, by the computing system, at least one vehicle traveling within the geographic region based on the at least one corresponding fingerprint, wherein the localizing further comprises:

determining, by the computing system, correlations between cells in the grid of cells and positions associated with a trajectory of the at least one vehicle; and

determining, by the computing system, scores for the correlations between the cells in the grid of cells and the positions associated with the trajectory of the at least one vehicle based on degrees to which the cells correspond with the positions, wherein the localizing the at least one vehicle is based at least in part on the scores; and

controlling, by the computing system, operation of the at least one vehicle based at least in part on the localizing.

2. The computer-implemented method of claim 1 , wherein the collected sensor data corresponds to acoustic data collected by one or more audio sensors of the one or more vehicles, and wherein the sensor map representing the geographic region corresponds to an acoustic map.

3. The computer-implemented method of claim 2 , wherein the at least one corresponding fingerprint for the at least one cell corresponds to an acoustic fingerprint that represents acoustic properties associated with the location of the geographic region.

4. The computer-implemented method of claim 1 , wherein the sensor data corresponds to acceleration data collected by one or more acceleration sensors of the one or more vehicles, and wherein the sensor map representing the geographic region corresponds to an acceleration map.

5. The computer-implemented method of claim 4 , wherein the at least one corresponding fingerprint for the at least one cell corresponds to an acceleration fingerprint that represents acceleration properties associated with the location of the geographic region.

6. The computer-implemented method of claim 1 , wherein the collected sensor data associated with the at least one cell was collected by the one or more vehicles navigating a portion of the geographic region that is represented by the at least one cell.

7. The computer-implemented method of claim 1 , wherein the at least one corresponding fingerprint for the at least one cell is determined based at least in part on a machine learning model, and wherein the machine learning model determines the at least one corresponding fingerprint based on sensor properties that are shared between the collected sensor data associated with the at least one cell.

8. The computer-implemented method of claim 1 , wherein the cells in the grid of cells vary in size.

9. The computer-implemented method of claim 1 , wherein the at least one cell is associated with at least a first fingerprint determined based on (i) a first layer of sensor data associated with the at least one cell and (ii) a second fingerprint determined based on a second layer of sensor data associated with the at least one cell.

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

routing, by the computing system, at least one vehicle navigating the geographic region based at least in part on the localization of the at least one vehicle and the at least one corresponding fingerprint.

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:

determining sensor data of a location of a geographic region collected by one or more vehicles while navigating the location of the geographic region, wherein the collected sensor data includes sensor readings generated at least in part by a surface interaction between the one or more vehicles and a road surface of the location;

determining a sensor map representing the geographic region, wherein the sensor map segments a plurality of locations associated with the geographic region into a grid of cells;

associating the collected sensor data with at least one cell in the grid of cells corresponding to the location of the geographic region navigated by the one or more vehicles;

determining at least one corresponding fingerprint for the at least one cell based at least in part on the collected sensor data associated with the at least one cell; and

localizing at least one vehicle traveling within the geographic region based on the at least one corresponding fingerprint, wherein the localizing further comprises:

determining correlations between cells in the grid of cells and positions associated with a trajectory of the at least one vehicle; and

determining scores for the correlations between the cells in the grid of cells and the positions associated with the trajectory of the at least one vehicle based on degrees to which the cells correspond with the positions, wherein the localizing the at least one vehicle is based at least in part on the scores; and

controlling operation of the at least one vehicle based at least in part on the localizing.

12. The system of claim 11 , wherein the collected sensor data corresponds to acoustic data collected by one or more audio sensors of the one or more vehicles, and wherein the sensor map representing the geographic region corresponds to an acoustic map.

13. The system of claim 12 , wherein the at least one corresponding fingerprint for the at least one cell corresponds to an acoustic fingerprint that represents acoustic properties associated with the location of the geographic region.

14. The system of claim 11 , wherein the sensor data corresponds to acceleration data collected by one or more acceleration sensors of the one or more vehicles, and wherein the sensor map representing the geographic region corresponds to an acceleration map.

15. The system of claim 14 , wherein the at least one corresponding fingerprint for the at least one cell corresponds to an acceleration fingerprint that represents acceleration properties associated with the location of the geographic region.

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:

determining sensor data of a location of a geographic region collected by one or more vehicles while navigating the location of the geographic region, wherein the collected sensor data includes sensor readings generated at least in part by a surface interaction between the one or more vehicles and a road surface of the location;

determining a sensor map representing the geographic region, wherein the sensor map segments a plurality of locations associated with the geographic region into a grid of cells;

associating the collected sensor data with at least one cell in the grid of cells corresponding to the location of the geographic region navigated by the one or more vehicles;

determining at least one corresponding fingerprint for the at least one cell based at least in part on the collected sensor data associated with the at least one cell; and

localizing at least one vehicle traveling within the geographic region based on the at least one corresponding fingerprint, wherein the localizing further comprises:

determining correlations between cells in the grid of cells and positions associated with a trajectory of the at least one vehicle; and

determining scores for the correlations between the cells in the grid of cells and the positions associated with the trajectory of the at least one vehicle based on degrees to which the cells correspond with the positions, wherein the localizing the at least one vehicle is based at least in part on the scores; and

controlling operation of the at least one vehicle based at least in part on the localizing.

17. The non-transitory computer-readable storage medium of claim 16 , wherein the collected sensor data corresponds to acoustic data collected by one or more audio sensors of the one or more vehicles, and wherein the sensor map representing the geographic region corresponds to an acoustic map.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the at least one corresponding fingerprint for the at least one cell corresponds to an acoustic fingerprint that represents acoustic properties associated with the location of the geographic region.

19. The non-transitory computer-readable storage medium of claim 16 , wherein the sensor data corresponds to acceleration data collected by one or more acceleration sensors of the one or more vehicles, and wherein the sensor map representing the geographic region corresponds to an acceleration map.

20. The non-transitory computer-readable storage medium of claim 19 , wherein the at least one corresponding fingerprint for the at least one cell corresponds to an acceleration fingerprint that represents acceleration properties associated with the location of the geographic region.