Determining relative velocity based on an expected configuration

Patent metadata

Field	Value
Publication number	US-11435479-B2
Application number	US-201816196597-A
Country	US
Kind code	B2
Filing date	Nov 20, 2018
Priority date	Aug 6, 2018
Publication date	Sep 6, 2022
Grant date	Sep 6, 2022

Abstract

A computer-implemented method of determining relative velocity between a vehicle and an object. The method includes receiving sensor data generated by one or more sensors of the vehicle. The one or more sensors are configured to sense an environment through which the vehicle is moving by following a scan pattern comprising component scan lines. The method includes obtaining, by one or more processors, a point cloud frame based on the sensor data and representative of the environment and identifying, by the one or more processors, a point cloud object within the point cloud frame. The method further includes determining, by the one or more processors, that the point cloud object is skewed relative to an expected configuration of the point cloud object, and determining, by the one or more processors, a relative velocity of the point cloud object by analyzing the skew of the object.

First claim

What is claimed is:

1. A computer-implemented method of determining relative velocity between a vehicle and an object, the method comprising:
receiving sensor data generated by one or more sensors of the vehicle, wherein the one or more sensors are configured to sense an environment through which the vehicle is moving by following a scan pattern comprising component scan lines;
obtaining, by one or more processors, a point cloud frame based on the sensor data and representative of the environment;
identifying, by the one or more processors, a point cloud object within the point cloud frame;
determining, by the one or more processors, that the point cloud object is skewed relative to an expected configuration of the point cloud object; and
determining, by the one or more processors, a relative velocity of the point cloud object by analyzing the skew of the object.

2. The computer-implemented method of claim 1 , wherein determining the relative velocity comprises:
determining, by the one or more processors, a lateral component of relative velocity based upon an amount of lateral skew associated with successive scan lines overlapping the point cloud object.

3. The computer-implemented method of claim 1 , wherein determining the relative velocity comprises:
determining, by the one or more processors, a longitudinal component of relative velocity based upon an amount of longitudinal skew associated with successive scan lines overlapping the point cloud object.

4. The computer-implemented method of claim 1 , wherein determining the relative velocity comprises:
determining, using a machine learning model executed by the one or more processors, the relative velocity.

5. The computer-implemented method of claim 1 , further comprising:
determining, by the one or more processors, that the point cloud object is skewed at least in part due to distortion arising from a time delay between scanning different portions of the scan pattern.

6. The computer-implemented method of claim 1 , further comprising:
correcting, by the one or more processors, the skew of the point cloud object based upon the determined relative velocity of the point cloud object.

7. The computer-implemented method of claim 6 , further comprising:
generating, based upon the predicted future state, one or more control signals to control operation of the vehicle.

8. The computer-implemented method of claim 1 , further comprising:
generating, based on the determined relative velocity of the point cloud object, a predicted future state of the environment 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, the expected configuration of the point cloud object based on the particular type of object.

11. The computer-implemented method of claim 10 , wherein determining that the point cloud object is skewed relative to the expected configuration of the point cloud object comprises:
comparing, by the one or more processors, the point cloud object to a generic model of the point cloud object of the particular type of object.

12. The computer-implemented method of claim 11 , further comprising:
determining, by the one or more processors, an orientation or scale of the generic model of the point cloud object based on a relative position between the point cloud object and the vehicle.

13. The computer-implemented method of claim 10 , wherein determining that the point cloud object is skewed relative to the expected configuration of the point cloud object comprises:
comparing, by the one or more processors, a bound of the point cloud object to an expected bound for objects of the particular type of object.

14. The computer-implemented method of claim 1 , wherein determining that the point cloud object is skewed relative to the expected configuration of the point cloud object comprises:
comparing, by the one or more processors, the point cloud object to map data of the environment through which the vehicle is moving.

15. 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 a point cloud frame based on the sensor data and representative of the environment;
identify a point cloud object within the point cloud frame;
determine that the point cloud object is skewed relative to an expected configuration of the point cloud object; and
determine a relative velocity of the point cloud object by analyzing the skew of the object.

16. The system of claim 15 , wherein to determine the relative velocity, the computing system is configured to:
determine a lateral component of relative velocity based upon an amount of lateral skew associated with successive scan lines overlapping the point cloud object.

17. The system of claim 15 , wherein to determine the relative velocity, the computing system is configured to:
determine a longitudinal component of relative velocity based upon an amount of longitudinal skew associated with successive scan lines overlapping the point cloud object.

18. The system of claim 15 , wherein to determine the relative velocity, the computing system is configured to:
determine, using a machine learning model, the relative velocity.

19. The system of claim 15 , wherein the computing system is configured to:
correct the skew of the point cloud object based upon the determined relative velocity of the point cloud object.

20. 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.

21. The system of claim 20 , 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.

22. The system of claim 15 , wherein the computing system is configured to:
classify the point cloud object as a particular type of object.

23. The system of claim 22 , wherein the computing system is configured to:
determine the expected configuration of the point cloud object based on the particular type of object.

24. The system of claim 23 , wherein to determine that the point cloud object is skewed relative to the expected configuration of the point cloud object, the computing system is configured to:
compare the point cloud object to a generic model of the point cloud object of the particular type of object.

25. The system of claim 24 , wherein the computing system is configured to:
determine an orientation or scale of the generic model of the point cloud object based on a relative position between the point cloud object and the vehicle.

26. The system of claim 23 , wherein to determine that the point cloud object is skewed relative to the expected configuration of the point cloud object, the computing system is configured to:
compare a bound of the point cloud object to an expected bound for objects of the particular type of object.

Assignees

• Luminar Llc

Inventors

• Danziger Eric C
• Russell Austin K
• Englard Benjamin

Classifications

• G01S17/58

  Velocity or trajectory determination systems; Sense-of-movement determination systems · CPC title

• G01S17/931

  of land vehicles · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• G01S17/87

  Combinations of systems using electromagnetic waves other than radio waves · CPC title