Detecting motion of an autonomous vehicle using radar technology

• US 10,691,135 B2
• Filed: 09/22/2017
• Issued: 06/23/2020
• Est. Priority Date: 09/22/2017
• Status: Active Grant

• Current Assignee: Waymo LLC (Alphabet Inc.)
• Original Assignee: Waymo LLC (Alphabet Inc.)
• Inventors: Campbell, Timothy, Smith, L. Donnie
• Primary Examiner(s): Armand, Marc Anthony
• Application Number:
  US15/713,500
• Publication Number:
  US 20190094878A1
• Time in Patent Office: 1,005 Days
• CPC Class Codes: B60W 2420/408 Radar; Laser, e.g. lidar
• CPC Class Codes: B60W 2520/04 Vehicle stop
• CPC Class Codes: B60W 30/08 Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
• CPC Class Codes: B60W 30/18109 Braking
• CPC Class Codes: G01S 13/867 Combination of radar systems with cameras
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 2013/9318 Controlling the steering
• CPC Class Codes: G01S 2013/93185 Controlling the brakes
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0257 using a radar radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931

Abstract

Examples relating to vehicle motion detection using radar technology are described. An example method may involve a computing system receiving, from a radar sensor mounted on an autonomous vehicle, radar data representative of an environment of the vehicle. The method may involve the computing system, based on the radar data, detecting at least one scatterer present in the environment. The method may involve the computing system making a determination of a likelihood that the at least one scatterer is stationary with respect to the vehicle. The method may involve the computing system, based on the determination being that the likelihood is at least equal to a predefined confidence threshold, determining an indication that the vehicle is stationary. And the method may involve the computing system controlling movement of the vehicle based on the determined indication.

Claims

1. A method performed by a computing system configured to control an autonomous vehicle, the method comprising:

receiving, by the computing system, from a radar sensor mounted on the autonomous vehicle, radar data representative of a physical environment of the autonomous vehicle;

based on the radar data, detecting, by the computing system, at least one scatterer present in the environment;

determining, by the computing system, an indication that the autonomous vehicle is stationary, based on a determination of a likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle; and

based on the determined indication, controlling, by the computing system, movement of the autonomous vehicle.

2. The method of claim 1, wherein the determining the indication that the autonomous vehicle is stationary is performed in response to receiving an indication that a velocity of the autonomous vehicle is below a predefined velocity threshold.

3. The method of claim 1, wherein controlling the movement of the autonomous vehicle comprises providing, to a movement module of the computing system, an instruction that, upon receipt by the movement module, causes the autonomous vehicle to remain stationary.

4. The method of claim 3, wherein the movement module of the computing system includes an inertial measurement unit (IMU) including one or more of an accelerometer and a gyroscope, and

wherein the instruction includes an instruction for the movement module to deny receipt of signals from the IMU.

5. The method of claim 1, wherein detecting the at least one scatterer present in the environment comprises isolating the at least one scatterer from a remainder of the radar data.

6. The method of claim 1, wherein the radar data includes Doppler measurements captured in at least one frame, wherein the determination of the likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle is based on the Doppler measurements in a single frame of the at least one frame.

7. The method of claim 1, wherein the radar data includes Doppler measurements captured in two frames, wherein the determination of the likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle is based on the Doppler measurements in the two frames, wherein the Doppler measurements comprise one of amplitude and phase measurements.

8. The method of claim 7, wherein the Doppler measurements comprise Doppler measurements that are estimated to be associated with the at least one scatterer, and wherein the determination of the likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle comprises a determination of whether a change in the Doppler measurements between the two frames is less than a predefined threshold,

wherein determining the indication that the autonomous vehicle is stationary based on the determination of the likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle comprises determining the indication that the autonomous vehicle is stationary based on the determination being that the change in the Doppler measurements between the two frames is less than the predefined threshold.

9. The method of claim 7, wherein determining the indication that the autonomous vehicle is stationary based on the determination of the likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle comprises (i) determining that at least one Doppler measurement associated with the at least one scatterer is approximately zero in the two frames and (ii) in response to determining that the at least one Doppler measurement associated with the at least one scatterer is approximately zero in the two frames, determining the indication that the autonomous vehicle is stationary.

10. The method of claim 7, wherein the two frames are two consecutive frames.

11. An article of manufacture including a non-transitory computer-readable medium having stored thereon instructions that, when executed by a processor in a computing system, causes the computing system to perform operations comprising:

receiving, from a radar sensor mounted on an autonomous vehicle, radar data representative of a physical environment of the autonomous vehicle;

based on the radar data, detecting at least one scatterer present in the environment;

determining an indication that the autonomous vehicle is stationary, based on a determination of a likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle; and

based on the determined indication, controlling movement of the autonomous vehicle.

12. The article of manufacture of claim 11, wherein the determination of the likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle is based on image data received from at least one camera mounted on the autonomous vehicle.

13. The article of manufacture of claim 11, wherein the determination of the likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle is based on optical data received from at least one light detection and ranging sensor mounted on the autonomous vehicle.

14. The article of manufacture of claim 11, wherein the determination of the likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle is based on predefined map data accessible by the computing system, wherein the predefined map data includes a known location of the at least one scatterer in the environment.

15. The article of manufacture of claim 11, wherein detecting the at least one scatterer present in the environment comprises isolating the at least one scatterer from a remainder of the radar data.

16. The article of manufacture of claim 11, wherein determining the indication that the autonomous vehicle is stationary based on the determination of the likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle comprises (i) determining that at least one Doppler measurement associated with the at least one scatterer is approximately zero in at least one frame of the radar data and (ii) in response to determining that the at least one Doppler measurement associated with the at least one scatterer is approximately zero in the at least one frame of the radar data, determining the indication that the autonomous vehicle is stationary.

17. A computing system configured to control an autonomous vehicle, the computing system comprising:

a radar sensor mounted on the autonomous vehicle;

a processor configured to perform operations comprising;

receiving, from the radar sensor, radar data representative of a physical environment of the autonomous vehicle;

based on the radar data, detecting at least one scatterer present in the environment;

determining an indication that the autonomous vehicle is stationary, based on a determination of a likelihood that the at least one scatterer is stationary with respect to the autonomous vehicle; and

based on the determined indication, controlling movement of the autonomous vehicle.

18. The computing system of claim 17, wherein the determining the indication that the autonomous vehicle is stationary is performed in response to receiving an indication that a velocity of the autonomous vehicle is below a predefined velocity threshold.

19. The computing system of claim 17, wherein the computing system further comprises a movement module, and

wherein controlling the movement of the autonomous vehicle comprises providing, to the movement module, an instruction that, upon receipt by the movement module, causes the autonomous vehicle to remain stationary.

20. The computing system of claim 19, wherein the movement module includes an inertial measurement unit (IMU) including one or more of an accelerometer and a gyroscope, and

wherein the instruction includes an instruction for the movement module to deny receipt of signals from the IMU.