Operation-security system for an automated vehicle

Patent metadata

Field	Value
Publication number	US-12013694-B2
Application number	US-202117541774-A
Country	US
Kind code	B2
Filing date	Dec 3, 2021
Priority date	Aug 5, 2016
Publication date	Jun 18, 2024
Grant date	Jun 18, 2024

Abstract

An operation-security system for an automated vehicle includes an object-detector and a controller. The object-detector includes at least three sensors. Each sensor is one of a camera used to determine an image-location of an object proximate to a host-vehicle, a lidar-unit used to determine a lidar-location of the object proximate to the host-vehicle, and a radar-unit used to determine a radar-location of the object proximate to the host-vehicle. The controller is in communication with the at least three sensors. The controller is configured to determine a composite-location based on a comparison of locations indicated by the at least three sensors. Information from one sensor is ignored when a respective location indicated by the one sensor differs from the composite-location by greater than an error-threshold. If a remote sensor not on the host-vehicle is used, V2V or V2I communications may be used to communicate a location to the host-vehicle.

First claim

We claim:

1. A system, comprising:
at least one processor, and
at least one non-transitory storage media storing instructions that, when executed by the at least one processor, cause the at least one processor to:
determine a first-location of an object proximate to a host-vehicle at a first-time, and a second-location of the object at a second-time characterized as a sampling-interval after the first-time;
determine a motion-vector of the host-vehicle;
estimate an expected-location of the object at the second-time based on the motion-vector, the first-location, and the sampling-interval, wherein information at the second-time is ignored when the expected-location differs from the second-location by greater than an error-threshold; and
determine an object-vector based on a prior-difference between the first-location and a prior-location of the object proximate to the host-vehicle at a prior-time prior to the first-time, wherein the expected-location is also determined based on the object-vector.

2. The system of claim 1 , wherein the motion-vector is based on a yaw rate of the host-vehicle.

3. The system of claim 1 , wherein the first-location and the second-location are determined using one or more sensors comprising:
a camera used to determine an imager-location of the object proximate to the host-vehicle;
a light detection and ranging (lidar)-unit used to determine a lidar-location of the object proximate to the host-vehicle; and
a radio detection and ranging (radar)-unit used to determine a radar-location of the object proximate to the host-vehicle.

4. The system of claim 3 , wherein the first-location is based on at least one of an average range from the host-vehicle to the imager-location, the radar-location, and the lidar-location, an average azimuth angle from the host-vehicle to the imager-location, the radar-location, and the lidar-location, an average latitude of the imager-location, the radar-location, and the lidar-location, or an average longitude of the imager-location, the radar-location, and the lidar-location.

5. The system of claim 3 , wherein at least one of the one or more sensors comprises at least one remote sensor not mounted on or within the host-vehicle.

6. The system of claim 5 , comprising a transceiver configured to receive at least one of the imager-location, the radar-location, or the lidar-location from the at least one remote sensor.

7. The system of claim 1 , comprising instructions that cause the at least one processor to:
monitor location information during operation of the host-vehicle, including looking for sudden, unusual, or unexpected changes in the motion-vector, the object-vector, and the expected-location over time; and
determine, using the monitored location information, that the system has been hacked.

8. The system of claim 7 , comprising instructions that cause the at least one processor to:
in response to determining that the system has been hacked, take action to avoid erratic operation of the host-vehicle.

9. A method, comprising:
determining, using at least one processor, a first-location of an object proximate to a host-vehicle at a first-time, and a second-location of the object at a second-time characterized as a sampling-interval after the first-time; and
determining, using the at least one processor, a motion-vector of the host-vehicle;
estimating, using the at least one processor, an expected-location of the object at the second-time based on the motion-vector, the first-location, and the sampling-interval, wherein information from the second-time is ignored when the expected-location differs from the second-location by greater than an error-threshold; and
determining, using the at least one processor, an object-vector based on a prior-difference between the first-location and a prior-location of the object proximate to the host-vehicle at a prior-time prior to the first-time, wherein the expected-location is also determined based on the object-vector.

10. The method of claim 9 , wherein the motion-vector is based on a yaw rate of the host-vehicle.

11. The method of claim 9 , wherein the first-location and the second-location are determined using one or more sensors comprising:
a camera used to determine an imager-location of the object proximate to the host-vehicle;
a light detection and ranging (lidar) unit used to determine a lidar-location of the object proximate to the host-vehicle; or
a radio detection and ranging (radar)-unit used to determine a radar-location of the object proximate to the host-vehicle.

12. The method of claim 11 , wherein the first-location is based on at least one of an average range from the host-vehicle to the imager-location, the radar-location, and the lidar-location, an average azimuth angle from the host-vehicle to the imager-location, the radar-location, and the lidar-location, an average latitude of the imager-location, the radar-location, and the lidar-location, or an average longitude of the imager-location, the radar-location, and the lidar-location.

13. The method of claim 11 , wherein at least one of the one or more sensors comprises at least one remote sensor not mounted on or within the host-vehicle.

14. The method of claim 9 , comprising:
monitoring location information during operation of the host-vehicle, including looking for sudden, unusual or unexpected changes in the motion-vector, the object-vector, and the expected-location over time; and
determining, using the monitored location information, that a system of the host-vehicle has been hacked.

15. The method of claim 14 , comprising:
in response to determining that the system of the host-vehicle has been hacked, taking action to avoid erratic operation of the host-vehicle.

16. At least one non-transitory computer-readable medium storing instructions which, when executed by at least one processor, cause the at least one processor to perform operations comprising:
determining a first-location of an object proximate to a host-vehicle at a first-time, and a second-location of the object at a second-time characterized as a sampling-interval after the first-time; and
determining a motion-vector of the host-vehicle;
estimating an expected-location of the object at the second-time based on the motion-vector, the first-location, and the sampling-interval wherein information from the second-time is ignored when the expected-location differs from the second-location by greater than an error-threshold; and
determining an object-vector based on a prior-difference between the first-location and a prior-location of the object proximate to the host-vehicle at a prior-time prior to the first-time, wherein the expected-location is also determined based on the object-vector.

17. The at least one non-transitory computer-readable medium of claim 16 , wherein the first-location and the second-location are determined using one or more sensors comprising:
a camera used to determine an imager-location of the object proximate to the host-vehicle;
a light detection and ranging (lidar)-unit used to determine a lidar-location of the object proximate to the host-vehicle; or
a radio detection and ranging (radar)-unit used to determine a radar-location of the object proximate to the host-vehicle.

18. The at least one non-transitory computer-readable medium of claim 17 , wherein at least one of the one or more sensors comprises at least one remote sensor not mounted on or within the host-vehicle.

19. The at least one non-transitory computer-readable medium of claim 16 stori

Assignees

• Motional Ad Llc

Inventors

• Lambermont Serge
• Kim Junsung
• Wei Junqing
• Bhatia Gaurav

Classifications

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• G01S13/931

  of land vehicles · CPC title

• G01S13/867

  Combination of radar systems with cameras · CPC title

• G01S13/865

  Combination of radar systems with lidar systems · CPC title

• G05D1/247

  using signals provided by artificial sources external to the vehicle, e.g. navigation beacons · CPC title