Identifying suspicious entities using autonomous vehicles

• US 10,755,111 B2
• Filed: 01/29/2018
• Issued: 08/25/2020
• Est. Priority Date: 01/29/2018
• Status: Active Grant

• Current Assignee: Micron Technology, Inc.
• Original Assignee: Micron Technology, Inc.
• Inventors: Golov, Gil, Szubbocsev, Zoltan
• Primary Examiner(s): Ismail, Mahmoud S
• Application Number:
  US15/882,168
• Publication Number:
  US 20190236379A1
• Time in Patent Office: 939 Days
• Field of Search: 701 26, 348148
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0291 Fleet control monitoring fleets in traffic control systems for road vehicles G08G1/127, G08G1/127
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names

Abstract

Systems and methods for identifying suspicious entities using autonomous vehicles are disclosed. In one embodiment, a method is disclosed comprising identifying a suspect vehicle using at least one digital camera equipped on an autonomous vehicle; identifying a set of candidate autonomous vehicles; enabling, on each of the candidate autonomous vehicles, a search routine, the search routine instructing each respective autonomous vehicle to coordinate tracking of the suspect vehicle; recording, while tracking the suspect vehicle, a plurality of images of the suspect vehicle; periodically re-calibrating the search routines executed by the autonomous vehicles based on the plurality of images; and re-routing the autonomous vehicles based on the re-calibrated search routines.

Claims

1. A method comprising:

identifying a suspect vehicle using at least one digital camera equipped on an autonomous vehicle;

identifying a set of candidate autonomous vehicles;

enabling, on each of the candidate autonomous vehicles, a search routine, the search routine instructing each respective autonomous vehicle to coordinate tracking of the suspect vehicle;

recording, while tracking the suspect vehicle, a plurality of images of the suspect vehicle;

periodically re-calibrating the search routines executed by the autonomous vehicles based on the plurality of images; and

re-routing the autonomous vehicles based on the re-calibrated search routines.

2. The method of claim 1, wherein identifying a suspect vehicle comprises analyzing at least one image captured by the digital camera using a deep neural network.

3. The method of claim 2, wherein identifying a suspect vehicle comprises identifying a suspect vehicle based on detecting a license plate number, make, model, or color of the suspect vehicle appearing within the image.

4. The method of claim 1, wherein identifying a suspect vehicle further comprises identifying the suspect vehicle using one or more sensors of the autonomous vehicle, the sensors comprising one or more of radar, Lidar, or sonar sensors.

5. The method of claim 1, wherein identifying a suspect vehicle using at least one digital camera equipped on an autonomous vehicle comprises identifying a license plate number of the suspect vehicle and confirming that the license plate number is associated with a known suspect vehicle.

6. The method of claim 1, wherein enabling a search routine comprises one or more of:

setting a maximum time to spend tracking the suspect vehicle;

setting a maximum deviation from a pre-defined route for an autonomous vehicle;

setting a level of adherence to traffic rules;

setting a proximity threshold; and

setting an autonomous vehicle fleet pattern and an autonomous vehicle fleet speed profile.

7. The method of claim 1, wherein identifying a set of candidate autonomous vehicles comprises identifying a set of autonomous vehicles that are not occupied by passengers.

8. The method of claim 1, wherein periodically re-calibrating the search routines executed by the autonomous vehicles comprises:

identifying a new image in the recorded images that includes the suspect vehicle;

determining a location associated with an autonomous vehicle that captured the new image; and

generating updated routing information based on the location.

9. The method of claim 1, wherein enabling a search routine further comprises predicting a future route of the suspect vehicle.

10. An autonomous vehicle comprising:

at least one digital camera;

a processor; and

a storage medium for tangibly storing thereon program logic for execution by the processor, the stored program logic comprising;

logic, executed by the processor, for identifying a suspect vehicle using the least one digital camera;

logic, executed by the processor, for receiving a search routine from a central server, the search routine instructing each respective autonomous vehicle to coordinate tracking of the suspect vehicle;

logic, executed by the processor, for executing the search routine;

logic, executed by the processor, for recording, while tracking the suspect vehicle, a plurality of images of the suspect vehicle;

logic, executed by the processor, for periodically receiving a re-calibrated the search routine based on the plurality of images; and

logic, executed by the processor, for re-routing the autonomous vehicle based on the re-calibrated search routine.

11. The autonomous vehicle of claim 10, wherein the logic for identifying a suspect vehicle comprises logic, executed by the processor, for analyzing at least one image captured by the digital camera using a deep neural network.

12. The autonomous vehicle of claim 11, wherein the logic for identifying a suspect vehicle comprises logic, executed by the processor, for identifying a suspect vehicle based on detecting a license plate number, make, model, or color of the suspect vehicle appearing within the image.

13. The autonomous vehicle of claim 10, further comprising one or more sensors including radar, Lidar, and sonar sensors, and wherein the logic for identifying a suspect vehicle further comprises logic, executed by the processor, for identifying the suspect vehicle using the one or more sensors.

14. The autonomous vehicle of claim 10, wherein the logic for identifying a suspect vehicle using the at least one digital camera comprises logic, executed by the processor, for identifying a license plate number of the suspect vehicle and confirming that the license plate number is associated with a known suspect vehicle.

15. The autonomous vehicle of claim 10, wherein the logic for executing a search routine comprises one or more of:

setting a maximum time to spend tracking the suspect vehicle;

setting a maximum deviation from a pre-defined route for an autonomous vehicle;

setting a level of adherence to traffic rules;

setting a proximity threshold; and

setting an autonomous vehicle fleet pattern and an autonomous vehicle fleet speed profile.

16. A device comprising:

a processor; and

a storage medium for tangibly storing thereon program logic for execution by the processor, the stored program logic comprising;

logic, executed by the processor, for identifying a suspect vehicle using images captured by at least one digital camera equipped on an autonomous vehicle;

logic, executed by the processor, for identifying a set of candidate autonomous vehicles;

logic, executed by the processor, for transmitting, to each of the candidate autonomous vehicles, a search routine, the search routine instructing each respective autonomous vehicle to coordinate tracking of the suspect vehicle;

logic, executed by the processor, for receiving a plurality of images recorded by the candidate autonomous vehicles while tracking the suspect vehicle;

logic, executed by the processor, for periodically re-calibrating the search routines executed by the autonomous vehicles based on the plurality of images; and

logic, executed by the processor, for transmitting re-routing information to the autonomous vehicles based on the re-calibrated search routines.

17. The device of claim 16, wherein the logic for identifying a set of candidate autonomous vehicles comprises identifying a set of autonomous vehicles that are not occupied by passengers.

18. The device of claim 16, wherein the logic for periodically re-calibrating the search routines executed by the autonomous vehicles comprises:

logic, executed by the processor, for identifying a new image in the plurality of images that includes the suspect vehicle;

logic, executed by the processor, for determining a location associated with an autonomous vehicle that captured the new image; and

logic, executed by the processor, for generating updated routing information based on the location.

19. The device of claim 16, wherein the logic for transmitting a search routine further comprises logic, executed by the processor, for predicting a future route of the suspect vehicle.

20. The device of claim 16, wherein the logic for identifying a suspect vehicle using images captured by at least one digital camera equipped on an autonomous vehicle comprises logic for inputting the images into one or more deep neural networks.