Granted Patent B2

US 10,677,900 · App. 16/196,632 · Granted Jun 9, 2020

Abstract

Claims (68)

1. A computer-implemented method of detecting object distortion, the method comprising:

receiving sensor data generated by one or more sensors of a vehicle, wherein the one or more sensors are configured to sense an environment through which the vehicle is moving by following a scan pattern;

obtaining, based on the sensor data and by one or more processors, a point cloud frame representative of the environment;

identifying, by one or more processors, a point cloud object within the point cloud frame;

analyzing, by the one or more processors, the point cloud object to identify a feature of the point cloud object that corresponds to an expected shape;

comparing, by the one or more processors, the feature of the point cloud object to the expected shape; and

identifying, by the one or more processors, that the point cloud object is distorted based on the feature of the point cloud object not matching the expected shape, wherein the distortion of the point cloud object comprises a skew arising from rolling shutter distortion.

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

determining, by the one or more processors, that the skew of the point cloud object corresponds to a skewed version of the expected shape; and

determining, by the one or more processors, a skew factor indicative of an amount of skew introduced by the rolling shutter distortion.

3. The computer-implemented method of claim 2 , further comprising:

correcting, by the one or more processors, the point cloud object based on the determined skew factor.

4. The computer-implemented method of claim 3 , wherein the skew factor is a three-dimensional vector.

5. The computer-implemented method of claim 2 , further comprising:

determining, based on the skew factor and by the one or more processors, a relative velocity of the point cloud object.

6. The computer-implemented method of claim 5 , further comprising:

associating, by the one or more processors, the point cloud object with the determined relative velocity.

7. The computer-implemented method of claim 5 , further comprising:

generating, based on the determined relative velocity of the point cloud object, a predicted future state of the environment of the vehicle.

8. The computer-implemented method of claim 7 , further comprising:

generating, based upon the predicted future state, one or more control signals to control operation of the vehicle.

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

classifying, by the one or more processors, the point cloud object as a particular type of object.

10. The computer-implemented method of claim 9 , further comprising:

determining, by the one or more processors, an expected shape of the feature of the point cloud object based on the particular type of object.

11. A system within an autonomous vehicle, the system comprising:

a set of sensors configured to generate a set of sensor data by sensing an environment of the vehicle by following a scan pattern comprising component scan lines; and

a computing system configured to:

receive the set of sensor data;

obtain, based on the sensor data, a point cloud frame representative of the environment;

identify a point cloud object within the point cloud frame;

analyze the point cloud object to identify a feature of the point cloud object that corresponds to an expected shape;

compare the feature of the point cloud object to the expected shape; and

identify that the point cloud object is distorted based on the feature of the point cloud object not matching the expected shape, wherein the distortion of the point cloud object comprises a skew arising from rolling shutter distortion.

12. The system of claim 11 , wherein the computing system is configured to:

determine that the skew of the point cloud object corresponds to a skewed version of the expected shape; and

determine a skew factor indicative of an amount of skew introduced by the rolling shutter distortion.

13. The system of claim 12 , wherein the computing system is configured to:

correct the point cloud object based on the determined skew factor.

14. The system of claim 13 , wherein the skew factor is a three-dimensional vector.

15. The system of claim 12 , wherein the computing system is configured to:

determine, based on the skew factor, a relative velocity of the point cloud object.

16. The system of claim 15 , wherein the computing system is configured to:

associate the point cloud object with the determined relative velocity.

17. The system of claim 15 , wherein the computing system is configured to:

generate, based on the determined relative velocity of the point cloud object, a predicted future state of the environment of the vehicle.

18. The system of claim 17 , wherein the computing system is configured to:

generate, based upon the predicted future state, one or more control signals to control operation of the vehicle.

19. The system of claim 11 , wherein the computing system is configured to:

classify the point cloud object as a particular type of object.

20. The system of claim 19 , wherein the computing system is configured to:

determine an expected shape of the feature of the point cloud object based on the particular type of object.

21. A non-transitory computer-readable medium storing thereon instructions executable by one or more processors to implement a software architecture of a vehicle, the software architecture comprising:

instructions for receiving a set of sensor data;

instructions for obtaining, based on the sensor data, a point cloud frame representative of an environment of the vehicle;

instructions for identifying a point cloud object within the point cloud frame;

instructions for analyzing the point cloud object to identify a feature of the point cloud object that corresponds to an expected shape;

instructions for comparing the feature of the point cloud object to the expected shape; and

instructions for identifying that the point cloud object is distorted based on the feature of the point cloud object not matching the expected shape, wherein the distortion of the point cloud object comprises a skew arising from rolling shutter distortion.

22. The non-transitory computer-readable medium of claim 21 , wherein the software architecture further comprises:

instructions for determining that the skew of the point cloud object corresponds to a skewed version of the expected shape; and

instructions for determining a skew factor indicative of an amount of skew introduced by the rolling shutter distortion.

23. The non-transitory computer-readable medium of claim 22 , wherein the software architecture further comprises:

instructions for correcting the point cloud object based on the determined skew factor.

24. The non-transitory computer-readable medium of claim 22 , wherein the software architecture further comprises:

instructions for determining, based on the skew factor, a relative velocity of the point cloud object.

25. The non-transitory computer-readable medium of claim 24 , wherein the software architecture further comprises instructions for generating, based on the determined relative velocity of the point cloud object, a predicted future state of the environment of the vehicle.

26. The non-transitory computer-readable medium of claim 25 , wherein the software architecture further comprises instructions for generating, based upon the predicted future state, one or more control signals to control operation of the vehicle.

Assignments (9)