Detecting of navigation data spoofing based on sensor data

• US 9,849,978 B1
• Filed: 09/25/2015
• Issued: 12/26/2017
• Est. Priority Date: 09/25/2015
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Carmack, Scott Gerard, Lakkakula, Narasimha Rao, Sharifi Mehr, Nima
• Primary Examiner(s): Edwards, Jerrah
• Assistant Examiner(s): William, Kelly D
• Application Number:
  US14/866,706
• Time in Patent Office: 823 Days
• CPC Class Codes: B64C 39/024 of the remote controlled vehicle type, i.e. RPV
• CPC Class Codes: B64U 10/10 Rotorcrafts
• CPC Class Codes: B64U 2201/104 using satellite radio beacon positioning systems, e.g. GPS
• CPC Class Codes: G01C 21/005 with correlation of navigation data from several sources, e.g. map or contour matching G01C21/30 takes precedence
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01S 19/215 issues related to spoofing
• CPC Class Codes: G08G 5/0008 with other aircraft
• CPC Class Codes: G08G 5/0013 with a ground station
• CPC Class Codes: G08G 5/0056 in an emergency situation, e.g. hijacking
• CPC Class Codes: G08G 5/0069 specially adapted for an unmanned aircraft

Abstract

Techniques for determining whether data associated with an autonomous operation of an unmanned vehicle may be trusted. For example, a first set of data may be provided from a source external to the unmanned vehicle. A second set of data may be accessed. This second set may be provided from a source internal to the unmanned vehicle and may be associated with the same autonomous operation. The two sets may be compared to determine whether the first set of data may be trusted or not. If untrusted, the autonomous navigation may be directed based on the second set of data and independently of the first set.

Claims

1. A computer-implemented method comprising:

receiving, by a computer system of an unmanned aerial vehicle (UAV), global positioning system (GPS) data, the computer system configured to direct a flight of the UAV to deliver an item from a source to a destination based at least in part on the GPS data;

receiving, by the computer system from one or more sensors of the UAV, sensor data associated with the flight, the one or more sensors having respective accuracies;

determining, by the computer system, a discrepancy between the GPS data and the sensor data;

detecting, by the computer system, that the discrepancy exceeds a threshold, the threshold defined based at least in part on an aggregation of the accuracies;

determining, by the computer system, that the GPS data is spoofed based at least in part on the discrepancy exceeding the threshold; and

directing, by the computer system, a portion of the flight based at least in part on the sensor data and independently of the GPS data that is spoofed.

2. The computer-implemented method of claim 1, wherein the sensor data comprises at least one of:

an altitude of the UAV or a cardinal direction of the UAV, and wherein the discrepancy comprises a mismatch between the GPS data and the at least one of;

the altitude or the cardinal direction.

3. The computer-implemented method of claim 1, wherein determining the discrepancy comprises:

tracking, by the computer system, a state of the flight based at least in part on the sensor data; and

determining, by the computer system, that the GPS data is inconsistent with the state of the flight.

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

receiving, by the computer system, additional sensor data and additional GPS data based at least in part on the portion of the flight being completed;

detecting, by the computer system, that the additional sensor data and the additional GPS data are consistent based at least in part on the threshold; and

directing, by the computer system, a remainder of the flight to the destination or to the source by using the additional GPS data based at least in part on the additional sensor data and the additional GPS data being consistent.

5. One or more non-transitory computer readable media comprising instructions that, when executed with a computer system, cause the computer system to at least:

perform a calibration of a sensor of an unmanned aerial vehicle (UAV) based at least in part on an environmental condition;

access external navigation data of a source external to the UAV, the external navigation data associated with directing an autonomous navigation of the UAV;

access internal navigation data of the sensor of the UAV;

determine that the external navigation data is untrusted based at least in part on a comparison of a threshold and a discrepancy between the external navigation data and the internal navigation data, the threshold defined based at least in part on the calibration of the sensor; and

direct the autonomous navigation of the UAV independently of the external navigation data based at least in part on the external navigation data being untrusted.

6. The one or more non-transitory computer readable media of claim 5, wherein the UAV is configured to deliver an item available from an electronic marketplace, wherein the source external to the UAV comprises a global positioning system (GPS).

7. The one or more non-transitory computer readable media of claim 5, wherein the source external to the UAV comprises at least one of:

a satellite-based navigation system or a terrestrial wireless network, and wherein the internal navigation data comprises at least one of;

an altitude, a cardinal direction, a speed, or an acceleration.

8. The one or more non-transitory computer readable media of claim 5, wherein determining that the external navigation data is untrusted comprises determining that the discrepancy between the external navigation data and the internal navigation data exceeds the threshold, wherein the threshold is further defined based at least in part on accuracy of the sensor.

9. The one or more non-transitory computer readable media of claim 5, wherein the external navigation data is received by the computer system when the UAV is located within an area, wherein determining that the external navigation data is untrusted comprises determining that the discrepancy between the external navigation data and the internal navigation data exceeds the threshold, and wherein the threshold is further defined based at least in part on a report from another UAV of untrusted navigation data within the area.

10. A system associated with an unmanned vehicle, the system comprising:

one or more processors; and

one or more non-transitory computer readable media comprising instructions that, when executed with the one or more processors, cause the system to at least;

access external navigation data of a source external to the unmanned vehicle that is configured to deliver an item, the external navigation data associated with directing an autonomous navigation of the unmanned vehicle;

access internal navigation data of a source internal to the unmanned vehicle;

determine that the external navigation data is untrusted based at least in part on a comparison of a threshold and a discrepancy between the external navigation data and the internal navigation data, the comparison indicating that the discrepancy exceeds the threshold, the threshold defined based at least in part on historical item deliveries of the unmanned vehicle; and

generate a corrective action associated with directing the autonomous navigation of the unmanned vehicle independently of the external navigation data that is untrusted.

11. The system of claim 10, wherein the corrective action comprises:

directing the autonomous navigation to use the internal navigation data instead of the external navigation data until the unmanned vehicle enters an idle state; and

reporting the idle state to a central station.

12. The system of claim 10, wherein the external navigation data is determined to be untrusted in association with a location of the unmanned vehicle, and wherein the corrective action comprises:

directing the unmanned vehicle to navigate to a different location without using the external navigation data; and

upon a detection that the external navigation data is trusted at the different location, directing the unmanned vehicle to resume using the external navigation data.

13. The system of claim 10, wherein the corrective action comprises:

reporting that the external navigation data is untrusted to a central station; and

facilitating remote navigation of the unmanned vehicle from the central station.

14. The system of claim 10, wherein the external navigation data is determined to be untrusted in association with a location of the unmanned vehicle, and wherein the corrective action comprises sending an identifier of the location to a central station to cause the central station to generate a map identifying the location as being untrusted.

15. The system of claim 10, wherein the corrective action comprises confirming that the external navigation data is untrusted based at least in part on maintaining a location of the unmanned vehicle and detecting that the external navigation data changes over time while the location is maintained.

16. One or more non-transitory computer readable media comprising instructions that, when executed with a computer system, cause the computer system to at least:

access external navigation data of a source external to an unmanned vehicle that is associated with an attribute, the external navigation data associated with directing an autonomous navigation of the unmanned vehicle;

access internal navigation data of a source internal to the unmanned vehicle;

determine that the external navigation data is untrusted based at least in part on a comparison of a threshold and a discrepancy between the external navigation data and the internal navigation data, the threshold defined based at least in part on historical navigation data of a plurality of unmanned vehicles associated with the attribute; and

direct the autonomous navigation of the unmanned vehicle independently of the external navigation data based at least in part on the external navigation data being untrusted.

17. The one or more non-transitory computer readable media of claim 16, wherein the source internal to the unmanned vehicle comprises a plurality of sensors having respective accuracies, and the threshold is further defined based at least in part on an aggregation of the accuracies.

18. The one or more non-transitory computer readable media of claim 16, wherein the source internal to the unmanned vehicle comprises a sensor, wherein the instructions, when executed with the computer system, further cause the computer system to perform a calibration of the sensor based at least in part on an environmental condition, and wherein the threshold is further defined based at least in part on the calibration of the sensor.

19. The one or more non-transitory computer readable media of claim 16, wherein the unmanned vehicle is configured to deliver an item, and wherein the threshold is defined based at least in part on the item.

20. One or more non-transitory computer readable media comprising instructions that, when executed with a computer system, cause the computer system to at least:

access external navigation data of a source external to an unmanned vehicle that is configured to deliver an item, the external navigation data associated with directing an autonomous navigation of the unmanned vehicle;

access internal navigation data of a source internal to the unmanned vehicle;

determine that the external navigation data is untrusted based at least in part on a comparison of a threshold and a discrepancy between the external navigation data and the internal navigation data, the comparison indicating that the discrepancy exceeds the threshold, the threshold defined based at least in part on the item; and

direct the autonomous navigation of the unmanned vehicle independently of the external navigation data based at least in part on the external navigation data being untrusted.

21. The one or more non-transitory computer readable media of claim 20, wherein the threshold is further defined based at least in part on historical item deliveries of the unmanned vehicle.

22. The one or more non-transitory computer readable media of claim 20, wherein the unmanned vehicle is associated with an attribute, and wherein the threshold is further defined based at least in part on historical navigation data of a plurality of unmanned vehicles associated with the attribute.