Method and apparatus for determining velocity of obstacle, device and medium

Inventors: Hao Wang (Beijing, CN); Liang Wang (Beijing, CN); Yu Ma (Beijing, CN)

Assignee: Apollo Intelligent Driving Technology (Beijing) Co., Ltd.

G01P3/64 G01S13/89 G01S13/931

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 11,353,476
App. No.: 17/030,838
Granted: Jun 7, 2022
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Embodiments of the present disclosure provide a method and apparatus for determining a velocity of an obstacle, a device, and a medium. An implementation includes: acquiring a first point cloud data of the obstacle at a first time and a second point cloud data of the obstacle at a second time; registering the first point cloud data and the second point cloud data by moving the first point cloud data or the second point cloud data; and determining a moving velocity of the obstacle based on a distance between two data points in a registered data point pair.

Claims (74)

1. A computer-implemented method for determining a velocity of an obstacle, the method comprising:

acquiring, by a sensor configured in a vehicle, a first point cloud data of the obstacle at a first time and a second point cloud data of the obstacle at a second time;

determining first point cloud distribution information of the first point cloud data and second point cloud distribution information of the second point cloud data, the determining comprising:

projecting the first point cloud data into grids of a set size in a first projection plane, to obtain first grid projection data;

in response to a number of data points projected into a grid being greater than 0, determining a distance parameter between the grid and an obstacle boundary as 0;

in response to the number of the data points projected into the grid is less than or equal to 0, searching, in a row direction, for a target grid closest to the grid and having a number of projected data points greater than 0;

determining the distance parameter of the grid based on a number of grids between the grid and the target grid; and

using the determined distance parameter as the first point cloud distribution information; and

registering the first point cloud data and the second point cloud data, based on the first point cloud distribution information and the second point cloud distribution information;

determining a moving velocity of the obstacle based on a distance between two data points in a registered data point pair; and

controlling autonomous driving of the vehicle based on the moving velocity of the obstacle.

2. The method according to claim 1 , wherein the determining first point cloud distribution information of the first point cloud data further comprises:

determining the first projection plane of the first point cloud data.

3. The method according to claim 2 , wherein the determining a first projection plane of the first point cloud data, comprises:

determining at least one projection direction according to at least one direction of the moving velocity;

combining a direction perpendicular to a ground with the at least one projection direction, respectively; and

constructing at least one first projection plane based on a direction pair obtained by the combining.

4. The method according to claim 1 , wherein the projecting the first point cloud data into the grids of the set size in the first projection plane to obtain the first grid projection data comprises:

converting the first point cloud data into a three-dimensional coordinate system, the three-dimensional coordinate system being with a centroid of the first point cloud data as an origin, and a plane constructed by two coordinate axes of the coordinate system being the first projection plane;

partitioning, with the origin of the coordinate system as a center, the first projection plane into the grids of the set size; and

projecting the converted first point cloud data into the partitioned grids to obtain the first grid projection data.

5. The method according to claim 1 , wherein the projecting the first point cloud data into the grids of the set size in the first projection plane to obtain the first grid projection data comprises:

determining a display scale of the first point cloud data in the grids based on a size of the first point cloud data and the size of the grid; and

projecting the first point cloud data into the grids to obtain the first grid projection data according to the display scale.

6. The method according to claim 1 , wherein the point cloud distribution information comprises at least one of: numbers of data points projected into the grids, distance parameters between the grids and an obstacle boundary, numbers of data points projected into columns of grids, or a length of grids in a row direction of the obstacle.

7. The method according to claim 1 , wherein the determining a moving velocity of the obstacle based on the distance between two data points in the registered data point pair comprises:

determining a target moving distance of the obstacle between the first time and the second time, based on the distance between the two data points in the registered data point pair; and

determining the moving velocity of the obstacle, based on the target moving distance.

8. An apparatus for determining a velocity of an obstacle, the apparatus comprising:

at least one processor; and

a memory storing instructions, the instructions when executed by the at least one processor, causing the at least one processor to perform operations, the operations comprising:

acquiring, by a sensor configured in a vehicle, a first point cloud data of an obstacle at a first time and a second point cloud data of the obstacle at a second time;