Radar tracking association with velocity matching by leveraging kinematics priors

Patent metadata

Field	Value
Publication number	US-12560696-B2
Application number	US-202117554624-A
Country	US
Kind code	B2
Filing date	Dec 17, 2021
Priority date	Dec 17, 2021
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

The present disclosure is directed to focusing processing resources of a radar apparatus to radar data associated with specific locations around an autonomous vehicle (AV). Data associated with a type of sensing apparatus that is not a radar (e.g. a camera and/or a LiDAR apparatus) that tracks motion of specific objects around the AV may be used by a processor to identify specific sets of radar data to process. Locations associated with a specific set of tracked objects may be used to identify sets of received radar signals that will be processed by the radar apparatus. Radar signals received by the radar apparatus that are associated with locations that do not correspond to a location of a tracked object may be ignored by the radar apparatus to reduce a number of computational tasks that a processor of the radar apparatus must process.

First claim

What is claimed is:

1 . A method for evaluating tracked objects, the method comprising:
associating radar points of radar detection data included in sets of reflected radar signal data with respective first grid cells of a grid, the grid segmenting an area around an autonomous vehicle (AV) into grid cells; associating particular sets of tracked object data with respective second grid cells of the grid, the tracked object data including information associated with motion of a first object as detected by at least one of a camera or a light detection and ranging (LiDAR) sensor; and based on determining that at least one of the first grid cells overlaps at least one of the second grid cells:
associating the radar points of the radar detection data included in the sets of reflected radar signal data with the particular sets of tracked object data;
processing only the radar points of the radar detection data associated with the particular sets of tracking object data together to identify a measurement to associate with the motion of the first object to reduce a number of computational tasks; and
ignoring radar points included in the radar detection data that are associated with first grid cells that do not overlap the second grid cells.

2 . The method of claim 1 , further comprising:
identifying a first range rate measurement to associate with a first point of the sets of reflected radar signals associated with a first set of cells in the respective first grid cells; identifying a second range rate measurement to associate with a second point of the sets of reflected radar signals associated with the first set of cells; and identifying that a set of objects that includes a second object located at the first set of cells based on the second range rate measurement being different from the first range rate measurement.

3 . The method of claim 1 , further comprising:
identifying a first location of a first point of the first object based on the processing of the sets of reflected radar signals; identifying a second location of the first point of the first object based on the processing of the sets of reflected radar signals; and identifying a first velocity associated with the first object based on the first point of the first object moving from the first location of the first point to the second location of the first point in a time frame.

4 . The method of claim 3 , further comprising:
identifying a first location of a second point of the first object based on the processing of the sets of reflected radar signals; identifying a second location of the second point of the first object based on the processing of the sets of reflected radar signals; and identifying a second velocity with the first object based on the second point of the first object moving from the first location of the second point to the second location of the second point in the time frame.

5 . The method of claim 4 , further comprising identifying a linear velocity and a rotational velocity associated with the first object based on the first velocity being different from the second velocity.

6 . The method of claim 4 , further comprising identifying a linear velocity based on the first velocity matching the second velocity.

7 . The method of claim 4 , further comprising identifying a rotational velocity based on the first velocity of the first point being associated with motion in a first direction and the second velocity being associated with motion of the second point being in a second direction.

8 . The method of claim 1 , wherein the grid is a two-dimensional grid from a perspective above the AV.

9 . A non-transitory computer-readable storage medium having embodied thereon a program executable by a processor for implementing a method for evaluating tracked objects, the method comprising:
associating radar points of radar detection data included in sets of reflected radar signal data with respective first grid cells of a grid, the grid segmenting an area around an autonomous vehicle (AV) into grid cells; associating particular sets of tracked object data with respective second grid cells of the grid, the tracked object data including information associated with motion of a first object as detected by at least one of a camera or a light detection and ranging (LiDAR) sensor; and based on determining that at least one of the first grid cells overlaps at least one of the second grid cells:
associating the radar points of the radar detection data included in the sets of reflected radar signal data with the particular sets of tracked object data;
processing only the radar points of the radar detection data associated with the particular sets of tracking object data together to identify a measurement to associate with the motion of the first object to reduce a number of computational tasks; and
ignoring radar points included in the radar detection data that are associated with first grid cells that do not overlap the second grid cells.

10 . The non-transitory computer-readable storage medium of claim 9 , wherein the method further comprises:
identify a first range rate measurement to associate with a first point of the sets of reflected radar signals associated with a first set of cells in the respective first grid cells; identify a second range rate measurement to associate with a second point of the sets of reflected radar signals associated with the first set of cells; and identify that a set of objects that includes a second object located at the first set of cells based on the second range rate measurement being different from the first range rate measurement.

11 . The non-transitory computer-readable storage medium of claim 9 , wherein the method further comprises:
identifying a first location of a first point of the first object based on the processing of the sets of reflected radar signals; identifying a second location of the first point of the first object based on the processing of the sets of reflected radar signals; and identifying a first velocity associated with the first object based on the first point of the first object moving from the first location of the first point to the second location of the first point in a time frame.

12 . The non-transitory computer-readable storage medium of claim 11 , wherein the method further comprises:
identify a first location of a second point of the first object based on the processing of the sets of reflected radar signals; identify a second location of the second point of the first object based on the processing of the sets of reflected radar signals; and identify a second velocity with the first object based on the second point of the first object moving from the first location of the second point to the second location of the second point in the time frame.

13 . The non-transitory computer-readable storage medium of claim 12 , wherein the method further comprises identifying a linear velocity and a rotational velocity associated with the first object based on the first velocity being different from the second velocity.

14 . The non-transitory computer-readable storage medium of claim 12 , wherein the method further comprises identifying a linear velocity based on the first velocity matching the second velocity.

15 . The non-transitory computer-readable storage medium of claim 12 , wherein the method further comprises identifying a rotational velocity based on the first velocity of the first point being associated with motion in a first direction and the second velocity being associated with motion of the second point being in a second dir

Assignees

• Gm Cruise Holdings Llc

Inventors

• Zhou Zhengrong
• Wang Shaogang
• Pierce Brian

Classifications

• G01S13/931

  of land vehicles · CPC title

• G01S13/865

  Combination of radar systems with lidar systems · CPC title

• G01S13/867

  Combination of radar systems with cameras · CPC title

• G01S13/588

  deriving the velocity value from the range measurement · CPC title

• G01S13/89

  for mapping or imaging · CPC title