Three-dimensional motion grid system for autonomous vehicle perception

Patent metadata

Field	Value
Publication number	US-12062135-B2
Application number	US-202217841439-A
Country	US
Kind code	B2
Filing date	Jun 15, 2022
Priority date	Jun 15, 2022
Publication date	Aug 13, 2024
Grant date	Aug 13, 2024

Abstract

A method is described and includes receiving a frame of point cloud data from at least one onboard light detection and ranging (LIDAR) sensor of a vehicle; discarding points of the received frame of point cloud data that are outside a defined geographic area around the vehicle; and, subsequent to the discarding, performing ray tracing in connection with the remaining points of the received frame of point cloud data. The method may further include characterizing an occupancy condition of each of a plurality of cells of a three-dimensional (3D) grid corresponding to the defined geographic area based on the ray tracing of the received frame of point cloud data, wherein the 3D grid corresponds to the received frame of point cloud data.

First claim

What is claimed is:

1. A method comprising:
receiving a frame of point cloud data from at least one onboard light detection and ranging (LIDAR) sensor of a vehicle;
discarding points of the received frame of point cloud data that are outside a defined geographic area around the vehicle;
subsequent to the discarding, performing ray tracing in connection with the remaining points of the received frame of point cloud data;
characterizing an occupancy condition of each of a plurality of cells of a three-dimensional (3D) grid corresponding to the defined geographic area based on the ray tracing of the received frame of point cloud data as one of occupied, freespace, overhang, and unknown, wherein the 3D grid corresponds to the received frame of point cloud data; and
recharacterizing the occupancy condition of a cell in the plurality cells of the 3D grid based on the occupancy condition of another cell in a same column as the cell in the 3D grid.

2. The method of claim 1 , further comprising comparing the 3D grid to a 3D grid corresponding to a previous frame of point cloud data to determine motion of an object within the defined geographic area by determining whether a status of the cell of the 3D grid has toggled between freespace and occupied or toggled between occupied and freespace.

3. The method of claim 1 , further comprising providing the 3D grid to a tracking system for the vehicle.

4. The method of claim 1 , wherein the cell comprises a 3D cell and each column of the 3D grid comprises a plurality of 3D cells.

5. The method of claim 1 , wherein the occupancy condition of one of the cells comprises at least one of occupied and freespace.

6. The method of claim 5 , wherein the occupancy condition of the cell has an occupancy condition recharacterized to overhang when the occupancy condition of the cell is initially characterized as occupied and the another cell is below the cell and is characterized as freespace.

7. The method of claim 1 , wherein the motion comprises a direction of movement.

8. The method of claim 1 , wherein the motion comprises a speed of movement.

9. The method of claim 1 , wherein the ray tracing and characterizing is performed using a graphics processing unit (GPU).

10. The method of claim 9 , wherein the ray tracing is performed using parallel processing.

11. The method of claim 1 , further comprising converting the 3D grid into a two-dimensional (2D) occupancy grid, wherein each cell of the 2D occupancy grid comprises a consolidation of the cells of a corresponding column of the 3D grid.

12. The method of claim 11 , further comprising comparing the 2D occupancy grid with an immediately preceding 2D occupancy grid to detect motion of an object over time within a geographic area represented by the 2D occupancy grid.

13. The method of claim 1 , wherein the discarding points of the received frame of point cloud data that are outside the defined geographic area comprises discarding points that are indicated as corresponding to a point in space located above a maximum height above a ground level, wherein the maximum height above the ground is based on a height of the vehicle.

14. A control system for a vehicle, the control system comprising:
a plurality of onboard light ranging and detection (LIDAR) sensors for generating LIDAR data comprising a frame of a point cloud related to an environment of the vehicle; and
a motion grid module comprising a graphics processing unit (GPU) configured to:
discard points of the point cloud frame that fall outside a defined geographic area around the vehicle;
subsequent to the discarding, process the remaining points using ray tracing to characterize an occupancy condition of each of a plurality of cells of a three-dimensional (3D) grid corresponding to the defined geographic area, wherein the 3D grid corresponds to the point cloud data frame as one of occupied, freespace, overhang, and unknown recharacterize a cell in the plurality cells of the 3D grid based on the characterizations of other cells in a same column as the cell in the 3D grid; and
convert the 3D grid to a two-dimensional (2D) grid, wherein each of a plurality of cells of the 2D grid represents a collective occupancy condition of a portion of the plurality of cells comprising a corresponding column of the 3D grid.

15. The control system of claim 14 , further comprising providing at least one of the 3D grid and the 2D grid to a tracking system for the vehicle.

16. The control system of claim 14 , wherein the occupancy condition comprises at least one of an occupied condition, a freespace condition, an occluded condition, an overhang condition, and a ground condition.

Assignees

• Gm Cruise Holdings Llc

Inventors

• Fasola Juan
• Kushwaha Shreyans
• Lo Eugene
• Zhou Xiaoyu

Classifications

• B60W2420/408

  Radar; Laser, e.g. lidar · CPC title

• B60W60/00253

  Taxi operations · CPC title

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• G06T2207/10028

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

• G06T2210/56

  Particle system, point based geometry or rendering · CPC title