Control of autonomous vehicle based on environmental object classification determined using phase coherent LIDAR data

Patent metadata

Field	Value
Publication number	US-12535594-B2
Application number	US-202418415049-A
Country	US
Kind code	B2
Filing date	Jan 17, 2024
Priority date	Apr 11, 2018
Publication date	Jan 27, 2026
Grant date	Jan 27, 2026

Abstract

Determining classification(s) for object(s) in an environment of autonomous vehicle, and controlling the vehicle based on the determined classification(s). For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be controlled based on determined pose(s) and/or classification(s) for objects in the environment. The control can be based on the pose(s) and/or classification(s) directly, and/or based on movement parameter(s), for the object(s), determined based on the pose(s) and/or classification(s). In many implementations, pose(s) and/or classification(s) of environmental object(s) are determined based on data from a phase coherent Light Detection and Ranging (LIDAR) component of the vehicle, such as a phase coherent LIDAR monopulse component and/or a frequency-modulated continuous wave (FMCW) LIDAR component.

First claim

What is claimed is:

1 . A method implemented by one or more processors, the method comprising:
receiving, from a phase coherent frequency-modulated continuous wave (FMCW) Light Detection and Ranging (LIDAR) component of a vehicle, a group of FMCW LIDAR data points collectively capturing a plurality of points in an area of an environment of the vehicle; processing the group of FMCW LIDAR data points to generate an altered version of the group of FMCW LIDAR data points; determining, based on applying the altered version of the group of FMCW LIDAR data points as input to a classification model, that a subgroup, of the altered version of the group of the FMCW LIDAR data points, corresponds to an object of a particular classification; and adapting autonomous control of the vehicle based on determining that the subgroup corresponds to the object of the particular classification.

2 . The method of claim 1 , wherein processing the group of FMCW LIDAR data points to generate the altered version of the group of FMCW LIDAR data points comprises:
decreasing a resolution of the group of FMCW LIDAR data points to generate the altered version of the group of FMCW LIDAR data points.

3 . The method of claim 2 , wherein decreasing the resolution of the group of FMCW LIDAR data points conforms a size of the altered version of the group of FMCW LIDAR data points with an input dimension of the classification model.

4 . The method of claim 1 , wherein processing the group of FMCW LIDAR data points to generate the altered version of the group of FMCW LIDAR data points comprises:
performing principal component analysis (PCA) on the group of FMCW LIDAR data points to generate the altered version of the group of FMCW LIDAR data points.

5 . The method of claim 1 , wherein processing the group of FMCW LIDAR data points to generate the altered version of the group of FMCW LIDAR data points comprises:
padding the group of FMCW LIDAR data points to generate the altered version of the group of FMCW LIDAR data points.

6 . The method of claim 5 , wherein padding the group of FMCW LIDAR data points conforms a size of the altered version of the group of FMCW LIDAR data points with an input dimension of the classification model.

7 . The method of claim 1 , further comprising:
prior to processing the group of FMCW LIDAR data points to generate the altered version of the group of FMCW LIDAR data points:
determining whether a size of the group of FMCW LIDAR data points conforms with an input dimension of the classification model,
wherein processing the group of FMCW LIDAR data points to generate the altered version of the group of FMCW LIDAR data points is in response to determining that the size of the group of FMCW LIDAR data points does not conform with the input dimension of the classification model.

8 . The method of claim 1 , wherein each of the FMCW LIDAR data points, of the group, indicate a corresponding instantaneous corresponding range and an instantaneous corresponding velocity for a corresponding one of the plurality of points in the environment, and wherein each of the FMCW LIDAR data points, of the group, are generated based on a sensing event of the FMCW LIDAR component.

9 . The method of claim 1 , wherein determining, based on applying the altered version of the group of FMCW LIDAR data points as input to the classification model, that the subgroup, of the altered version of the group of the FMCW LIDAR data points, corresponds to the object of a particular classification comprises:
determining, based on applying the altered version of the group of FMCW LIDAR data points as input to the classification model, output; and determining, based on the output, that the subgroup, of the altered version of the group of the FMCW LIDAR data points, corresponds to the object of the particular classification.

10 . The method of claim 9 , wherein output a corresponding probability for a plurality of classifications and for each of a plurality of spatial regions of the environment of the vehicle.

11 . The method of claim 10 , wherein each of the plurality of spatial regions of the environment of the vehicle correspond to a portion of the environment of the vehicle.

12 . The method of claim 10 , wherein the plurality of classifications comprise two or more of: a vehicle classification, a pedestrian classification, and/or a bicyclist classification.

13 . The method of claim 9 , further comprising:
determining, based on the output, a pose for the object of the particular classification.

14 . The method of claim 13 , wherein adapting the autonomous control of the vehicle is further based on determining the pose for the object of the particular classification.

15 . The method of claim 1 , wherein adapting the autonomous control of the vehicle comprises:
controlling steering, acceleration, deceleration of the vehicle based on determining that the subgroup corresponds to the object of the particular classification.

16 . The method of claim 1 , further comprising:
determining, based on applying the altered version of the group of FMCW LIDAR data points as input to a classification model, that a subgroup, of the altered version of the group of the FMCW LIDAR data points, a pose for the object of the particular classification.

17 . The method of claim 16 , wherein adapting the autonomous control of the vehicle comprises:
controlling steering, acceleration, deceleration of the vehicle based on determining that the subgroup corresponds to the object of the particular classification and based on determining the pose for the object of the particular classification.

18 . An autonomous vehicle, comprising:
a phase coherent frequency-modulated continuous wave (FMCW) Light Detection and Ranging (LIDAR) component of a vehicle; and one or more processor executing stored computer instructions to:
receive, from the phase coherent FMCW LIDAR component, a group of FMCW LIDAR data points collectively capturing a plurality of points in an area of an environment of the vehicle;
process the group of FMCW LIDAR data points to generate an altered version of the group of FMCW LIDAR data points;
determine, based on applying the altered version of the group of FMCW LIDAR data points as input to a classification model, that a subgroup, of the altered version of the FMCW LIDAR data points, corresponds to an object of a particular classification; and
adapt autonomous control of the vehicle based on determining that the subgroup corresponds to the object of the particular classification.

19 . A method implemented by one or more processors, the method comprising:
receiving, from a phase coherent frequency-modulated continuous wave (FMCW) Light Detection and Ranging (LIDAR) component of a vehicle, a group of FMCW LIDAR data points collectively capturing a plurality of points in an area of an environment of the vehicle; prior to determining, based on applying the group of FMCW LIDAR data points as input to a classification model, that a subgroup, of the FMCW LIDAR data points, corresponds to an object of a particular classification:
determining whether a size of the group of FMCW LIDAR data points conforms with an input dimension of the classification model; and
in response to determining that the size of the group of FMCW LIDAR data points does not conform with the input dimension of the classification model:
processing the group of FMCW LIDAR data points to generate an altered version of the group of FMCW LIDAR data points; and
determinin

Assignees

• Aurora Operations Inc

Inventors

• Smith Warren
• Eade Ethan
• Anderson Sterling J
• Bagnell James Andrew
• Nabbe Bartholomeus C
• Urmson Christopher Paul

Classifications

• G06T2207/30261

  Obstacle · CPC title

• G06T2207/10028

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

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G05D1/247

  using signals provided by artificial sources external to the vehicle, e.g. navigation beacons · CPC title