Radar inter-pulse doppler phase generation using performant bounding volume hierarchy micro-step scene interpolation

Patent metadata

Field	Value
Publication number	US-12072437-B2
Application number	US-202117555414-A
Country	US
Kind code	B2
Filing date	Dec 18, 2021
Priority date	Dec 18, 2021
Publication date	Aug 27, 2024
Grant date	Aug 27, 2024

Abstract

The present disclosure is directed to simulating patterns of reflected radar energy off of reference objects using motion data associated with these reference objects. This motion data may identify start times, start locations, end times, and end locations of a limited number reference objects in a set of discrete scenes. Each of these discrete scenes may also have a same time duration. Motion of these specific objects between a start time and an end time of each discrete scene may be interpolated. Once the locations of the objects are interpolated for a given scene, simulations may be performed to estimate the appearance of reflected radar signals that would be received by a radar apparatus. These simulations may identify patterns of reflected radar energy after radar signals have been emitted from the radar apparatus and these patterns may then be provided to train a machine learning apparatus.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
accessing data that associates a first scene with a start time and an end time of the first scene and that associates each respective object of a set of objects in the first scene with a respective starting location and a respective ending location;
generating simulated radar data for each of the set of objects at the start time based on simulated radar energy being reflected off of each of the objects in the set of objects at each of the respective starting locations;
calculating interpolated positions of movement of a first object in the set of objects from the start time to the end time based on an identification that the first object has moved in the first scene from a start location to an end location of the first object, wherein each of the interpolated positions of the movement of the first object are associated with a respective interpolated location of the first object from the start location and the end location of the first object;
generating simulated movement radar data associated with the movement of the first object at each of the interpolated positions; and

generating simulated radar data for each of the objects in the set of objects inclusive of the first object at the end time based on simulated energy being reflected off of each of the objects in the set of objects at each of the respective ending locations.

2. The computer-implemented method of claim 1 , further comprising:
identifying that a second object of the set of objects has moved in the first scene between the start time and the end time; and
calculating interpolated positions of motion of the second object from the start time to the end time, wherein the generated simulated radar data is also generated based on the motion of the second object.

3. The computer implemented method of claim 1 , further comprising associating the first object with a plurality of boxes that represent a part of the first object.

4. The computer implemented method of claim 3 , wherein the plurality of boxes include a first box that corresponds to a torso of a person and a second box that corresponds to an appendage of the person.

5. The computer implemented method of claim 1 , further comprising:
accessing data associated with a second scene that begins at the start time of the second scene and that ends at an end time of the second scene, wherein the start time of the second scene corresponds to the end time of the first scene;
identifying that the first object has moved between the start time and end time of the second scene; and
calculating interpolated position of movement of the first object from the start time of the second scene to the end time of the second scene, wherein the generated simulated movement radar data is also associated with the movement of the first object from the start and end times of the second scene.

6. The computer implemented method of claim 1 , further comprising receiving motion data of a computer model approximates the movement of the first object.

7. The computer implemented method of claim 6 , wherein the motion data is associated with the first object moving in a direction that affects a Doppler shift of simulated radar signals.

8. The computer implemented method of claim 6 , wherein the motion data of the computer model includes a representation of rotation of the first object based on the motion data being associated with a first box that corresponds to a first part of the first object and a box that corresponds to a second part.

9. The computer implemented method of claim 8 , wherein changes in relative locations of the first part of the first object and the second part of the first object between the start time and the end time of the first scene correspond to the rotation of the first object.

10. The computer implemented method of claim 1 , further comprising:
receiving data that changes a relative speed of the first object; and
generating simulated radar data for motion data associated with the changed relative speed of the first object.

11. The computer implemented method of claim 1 , further comprising:
receiving data that changes the start location of the first object; and
generating simulated radar data for motion data associated with the changed start location of the first object.

12. The computer implemented method of claim 1 , wherein the simulated movement radar data of the first object is provided to train the machine learning apparatus.

13. A non-transitory computer-readable storage medium for implementing a computer implemented method for collecting data for training a machine learning apparatus, the computer implemented method comprising:
accessing data that associates a first scene with a start time and an end time of the first scene and that associates each respective object of a set of objects in the first scene with a respective starting location and a respective ending location;
generating simulated radar data for each of the set of objects at the start time based on simulated radar energy being reflected off of each of the objects in the set of objects at each of the respective starting locations;
calculating interpolated positions of movement of a first object in the set of objects from the start time to the end time based on an identification that the first object has moved in the first scene from a start location to an end location of the first object, wherein each of the interpolated positions of the movement of the first object are associated with a respective interpolated location of the first object from the start location and the end location of the first object;
generating simulated movement radar data associated with the movement of the first object at each of the interpolated positions; and

generating simulated radar data for each of the objects in the set of objects inclusive of the first object at the end time based on simulated energy being reflected off of each of the objects in the set of objects at each of the respective ending locations.

14. The non-transitory computer-readable storage medium of claim 13 , the program further executable to:
identify that a second object of the set of objects has moved in the first scene between the start time and the end time; and
calculate interpolated positions of motion of the second object from the start time to the end time, wherein the generated simulated radar data is also generated based on the motion of the second object.

15. The non-transitory computer-readable storage medium of claim 13 , the program further executable to associate the first object with a plurality of boxes that represent a part of the first object.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the plurality of boxes include a first box that corresponds to a torso of a person and a second box that corresponds to an appendage of the person.

17. The non-transitory computer-readable storage medium of claim 13 , the program further executable to:
access data associated with a second scene that begins at the start time of the second scene and that ends at an end time of the second scene, wherein the start time of the second scene corresponds to the end time of the first scene;
identify that the first object has moved between the start time and end time of the second scene; and
calculate interpolated position of movement of the first object from the start time of the second scene to the end time of the second scene, wherein the generated simulated movement radar data is also associated with the movement of the

Assignees

• Gm Cruise Holdings Llc

Inventors

• Gross Joel
• Hamilton Michael

Classifications

• G01S7/415

  Identification of targets based on measurements of movement associated with the target · CPC title

• G01S7/412

  based on a comparison between measured values and known or stored values · CPC title

• G01S7/417

  involving the use of neural networks · CPC title

• G01S7/406

  using internally generated reference signals, e.g. via delay line, via RF or IF signal injection or via integrated reference reflector or transponder · CPC title

• G01S7/40 Primary

  Means for monitoring or calibrating · CPC title