Ground-penetrating radar sensors on vehicles for detecting underground features and road surface features

1. A method for identifying road surface features and underground features using a ground penetrating radar (GPR) sensor, the method comprising:

activating the GPR sensor on a vehicle to transmit a pulsed electromagnetic signal toward a ground surface, wherein the vehicle comprises more than one GPR sensor;

receiving the pulsed electromagnetic signal reflected from the road surface features and the underground features by the GPR sensor;

filtering the pulsed electromagnetic signal to generate shallow-GPR data or deep-GPR data, wherein the shallow-GPR data is used to identify the road surface features and the deep-GPR data is used to identify the underground features;

selectively activate one GPR sensor of the more than one GPR sensors based on a map of the underground features and coordinating with a map of surface localization features, when a location of the vehicle on the surface indicates that the one GPR sensor of the more than one GPR sensors is best positioned to detect the underground features; and

adjusting operational parameters based on at least one of the road surface features and the underground features.

2. The method of claim 1 , further comprising comparing the deep-GPR data identifying the underground features with the map of underground features; and

locating the vehicle to a position on a road based upon the comparison of the deep-GPR data identifying the underground features with the map of the underground features; and

adjusting the operational parameters based on the position.

3. The method of claim 1 , wherein the underground features have a depth up to 30 meters.

4. The method of claim 1 , further comprising generating a GPR map by combining the deep-GPR data with surface localization features.

5. The method of claim 4 , wherein the surface localization features comprise coordinates that correspond to a location on a road or road boundaries.

6. The method of claim 4 , wherein the generating the GPR map comprises updating the map of underground features by adding the deep-GPR data.

7. A system for identifying road surface features and underground features using a ground penetrating radar (GPR) sensor, the system comprising:

a storage device configured to store instructions;

a processor configured to execute the instructions and cause the processor to:

activate the GPR sensor on a vehicle to transmit a pulsed electromagnetic signal toward a ground surface, wherein the vehicle comprises more than one GPR sensor;

receive the pulsed electromagnetic signal reflected from the road surface features and the underground features by the GPR sensor;

filter the pulsed electromagnetic signal to generate shallow-GPR data or deep-GPR data, wherein the shallow-GPR data is used to identify the road surface features and the deep-GPR data is used to identify the underground features;

selectively activate one GPR sensor of the more than one GPR sensors based on a map of the underground features and coordinating with a map of surface localization features, when a location of the vehicle on the surface indicates that the one GPR sensor of the more than one GPR sensors is best positioned to detect the underground features; and

adjust operational parameters based on the at least one of the road surface features and the underground features.

8. The system of claim 7 , wherein a position of the underground features is known relative to the surface localization features, wherein the vehicle is an autonomous vehicle (AV).

9. The system of claim 7 , wherein the processor is configured to execute the instructions and cause the processor to provide the deep-GPR data to a localization stack, wherein the operational parameters are adjusted based on the provided deep-GPR data.

10. The method of claim 9 , wherein the localization stack uses the deep-GPR data along with the map of underground features relative to the map of surface localization features.

11. The system of claim 7 , wherein the processor is configured to execute the instructions and cause the processor to selectively deactivate the GPR sensor when the underground features are not distinct enough to be used to locate the vehicle to the position on the road.

12. The system of claim 7 , wherein the electromagnetic signal has a frequency from 1 MHz to 10 GHz.

13. The system of claim 7 , wherein the processor is configured to execute the instructions and cause the processor to provide the road surface features to a planning stack.

14. A non-transitory computer readable medium for identifying road surface features and underground features using a ground penetrating radar (GPR) sensor, the non-transitory computer readable medium comprising instructions, the instructions, when executed by a computing system, cause the computing system to:

activate the GPR sensor on a vehicle to transmit a pulsed electromagnetic signal toward a ground surface, wherein the vehicle comprises more than one GPR sensor;

receive the pulsed electromagnetic signal reflected from the road surface features and the underground features by the GPR sensor;

filter the pulsed electromagnetic signal to generate shallow-GPR data or deep-GPR data, wherein the shallow-GPR data is used to identify the road surface features and the deepGPR data is used to identify the underground features;

selectively activate one GPR sensor of the more than one GPR sensors based on a map of the underground features and coordinating with a map of surface localization features, when a location of the vehicle on the surface indicates that the one GPR sensor of the more than one GPR sensors is best positioned to detect the underground features; and

adjust operational parameters based on at least one of the road surface features and the underground features.

15. The non-transitory computer readable medium of claim 14 , wherein the computer readable medium further comprises instructions that, when executed by the computing system, cause the computing system to:

compare the deep-GPR data identifying the underground features with the map of underground features; and

locate the vehicle to a position on a road based upon the comparison of the deep-GPR data identifying the underground features with the map of the underground features; and

adjust operational parameters based on the position.

16. The non-transitory computer readable medium of claim 15 , wherein the computer readable medium further comprises instructions that, when executed by the computing system, cause the computing system to locate the vehicle to a position in a lane.

17. The non-transitory computer readable medium of claim 14 , wherein the GPR sensor is on the vehicle and is suspended above the ground surface.

18. The non-transitory computer readable medium of claim 14 , wherein the computer readable medium further comprises instructions that, when executed by the computing system, cause the computing system to adjust a height of the GPR sensor to avoid damage to the GPR sensor based upon the ground surface features.

19. The non-transitory computer readable medium of claim 14 , wherein the computer readable medium further comprises instructions that, when executed by the computing system, cause the computing system to adjust a frequency of the GPR sensor based upon the ground surface features.