CN-121995368-A - Detection method and related equipment for travelable area based on millimeter wave radar

CN121995368ACN 121995368 ACN121995368 ACN 121995368ACN-121995368-A

Abstract

The application provides a method for detecting a travelable area based on millimeter wave radar and related equipment, comprising the following steps: acquiring a first point cloud acquired by a left radar and a second point cloud acquired by a right radar on a vehicle, and fusing the first point cloud and the second point cloud to obtain a fused point cloud. Wherein, left radar and right radar are millimeter wave radar. Based on the distribution of the fusion point cloud in the grid map, an observation of each grid in the grid map is determined. That is, the fused point clouds may be distributed in the corresponding grids in the grid map based on the coordinates of each fused point cloud, so that the observation result of each grid, that is, whether the point cloud is observed in the grid, may be determined. Based on the observation of the grid, a probability of fusion point clouds being present in the grid is determined. A drivable region of the vehicle is determined based on the path planning algorithm and the probability corresponding to each grid.

Inventors

JIN YINXIN
Lian Shenxiao
WANG DONGFENG
ZHENG BO
YU SONGSHAN
YANG BO
HUANG DONGPING
SUN ZELIN

Assignees

北京川速微波科技有限公司

Dates

Publication Date: 20260508
Application Date: 20260225

Claims (10)

1. A method for detecting a travelable region based on millimeter wave radar, the method comprising: fusing a first point cloud acquired by a left radar and a second point cloud acquired by a right radar on a vehicle to obtain a fused point cloud, wherein the left radar and the right radar are millimeter wave radars; determining an observation result of each grid in the grid map based on the distribution of the fusion point cloud in the grid map; Determining the probability of the fusion point cloud existing in the grid based on the observation result; a drivable region of the vehicle is determined based on a path planning algorithm and the probability.
2. The method of claim 1, wherein the determining the drivable region of the vehicle based on the path planning algorithm and the probability comprises: determining a field angle corresponding to fusion of the left radar and the right radar; Determining a plurality of preset angles based on the field angle; along any preset angle, carrying out path planning by utilizing the path planning algorithm, and determining the furthest travelable target distance based on the probability corresponding to the grid in the planned path; and determining the drivable area based on a plurality of target distances corresponding to the preset angles respectively.
3. The method according to claim 2, wherein the step of performing path planning along any predetermined angle by using the path planning algorithm, and determining the furthest travelable target distance based on the probability corresponding to the grid in the planned path comprises: taking the position of the vehicle as a starting point, taking a preset radius as a maximum planning distance, and carrying out path planning from the starting point along the preset angle by utilizing a Blueson-Ham straight line algorithm to determine an ith candidate grid; Judging whether the probability corresponding to the ith candidate grid exceeds a probability threshold, if so, stopping path planning, and determining the ith candidate grid as a target grid; otherwise, continuing to execute path planning, and determining an (i+1) th candidate grid; Judging whether the probability corresponding to the (i+1) th candidate grid exceeds the probability threshold value, if so, stopping path planning, and determining the (i+1) th candidate grid as the target grid; otherwise, repeating the above process until the furthest grid corresponding to the preset radius is reached or the probability corresponding to the (i+1) th candidate grid exceeds the probability threshold, stopping iteration, and determining the grid corresponding to the stopped iteration as the target grid; the target distance is determined based on a distance between the location of the vehicle and the target grid.
4. A method according to claim 3, further comprising one or more of the following: For a first preset angle, calculating a first target distance corresponding to the first preset angle based on a second target distance corresponding to a second preset angle and a third target distance corresponding to a third preset angle, wherein the first preset angle belongs to a preset large angle range, the second preset angle is a previous angle of the first preset angle, and the third preset angle is a subsequent angle of the first preset angle, or And calculating an average value of a plurality of target distances corresponding to the target preset angles when a saw-tooth area exists in a drivable area corresponding to the target preset angles, and determining the average value as a final distance corresponding to the target preset angles.
5. The method of claim 1, wherein the determining, based on the observations, a probability that the fused point cloud is present in the grid comprises: Acquiring a history state parameter corresponding to the grid at the last moment, wherein the initial state parameter corresponding to the initial moment is a known number; When the observation result is that the fusion point cloud is observed, determining a first update coefficient based on the detection probability and the false alarm probability; calculating a current state parameter corresponding to the grid at the current moment based on the product of the first update coefficient and the historical state parameter; and when the observation result is that the fusion point cloud is not observed, determining a second update coefficient based on the false alarm probability and the detection probability, calculating the current state parameter based on the product of the second update coefficient and the historical state parameter, and determining the probability based on the current state parameter.
6. The method of claim 5, wherein the determining a first update factor based on a detection probability and a false alarm probability when the observation is that the fusion point cloud is observed comprises: Calculating a first ratio of the detection probability to the false alarm probability to obtain the first update coefficient; And when the observation result is that the fusion point cloud is not observed, determining a second update coefficient based on the false alarm probability and the detection probability, including: Calculating a first difference value between 1 and the detection probability, and calculating a second difference value between 1 and the false alarm probability; And calculating a second ratio of the first difference value to the second difference value to obtain the second updating coefficient.
7. The method of claim 1, wherein fusing the first point cloud acquired by the left radar and the second point cloud acquired by the right radar on the vehicle to obtain a fused point cloud, comprises: acquiring the first point cloud acquired at a first moment and the second point cloud acquired at a second moment, wherein the first moment and the second moment belong to adjacent moments; determining a distance of movement of the vehicle between the first time and the second time based on a speed of the vehicle; Determining a heading angle of the vehicle that varies between the first time and the second time based on an angular velocity of the vehicle; determining a translation matrix and a rotation matrix based on the movement distance and the heading angle; and converting the first point cloud based on the translation matrix and the rotation matrix, and determining the fusion point cloud based on the converted point cloud and the second point cloud.
8. A millimeter wave radar-based detection device for a travelable region, the device comprising: The fusion unit is used for fusing the first point cloud acquired by the left radar and the second point cloud acquired by the right radar on the vehicle to obtain fusion point cloud; the observation unit is used for determining an observation result of each grid in the grid map based on the distribution of the fusion point cloud in the grid map; The probability determining unit is used for determining the probability of the fusion point cloud existing in the grid based on the observation result; And the area determining unit is used for determining the drivable area of the vehicle based on a path planning algorithm and the probability.
9. An electronic device comprising a memory and a processor; the memory is used for storing related program codes; The processor is configured to invoke the program code to perform the method of detecting a travelable region as claimed in any one of claims 1-7.
10. A computer-readable storage medium storing a computer program for executing the method of detecting a travelable region as claimed in any one of claims 1-7.

Description

Detection method and related equipment for travelable area based on millimeter wave radar Technical Field The application relates to the technical field of radar application, in particular to a method for detecting a travelable area based on millimeter wave radar and related equipment. Background Currently, sensors for intelligent driving mainly comprise cameras, laser radars and millimeter wave radars, and sensors for detecting a drivable area of a vehicle still mainly comprise the cameras and the laser radars. The cost of the camera is low, but the positioning error of the target distance is larger, and the camera is easily influenced by illumination or bad weather, so that the accuracy of detecting the drivable area is influenced. The laser radar collects data accurately, but the cost is high, the point cloud data is large in scale, and data processing has obvious delay, so that the time for detecting a travelable area is long. The number of point clouds detected by the millimeter wave radar is sparse compared with that of the laser radar, but the point clouds usually only play an auxiliary role in a multi-sensor fusion scheme at present. Disclosure of Invention In view of the above, the present application is directed to providing a method for detecting a travelable region based on millimeter wave radar and related apparatus, so as to realize detection of a travelable region of a vehicle using millimeter wave radar, reduce cost, and improve detection efficiency and accuracy. In a first aspect, the present application provides a method for detecting a travelable region based on millimeter wave radar, the method comprising: fusing a first point cloud acquired by a left radar and a second point cloud acquired by a right radar on a vehicle to obtain a fused point cloud; determining an observation result of each grid in the grid map based on the distribution of the fusion point cloud in the grid map; Determining the probability of the fusion point cloud existing in the grid based on the observation result; a drivable region of the vehicle is determined based on a path planning algorithm and the probability. In one possible implementation manner, the determining the drivable area of the vehicle based on the path planning algorithm and the probability includes: determining a field angle corresponding to fusion of the left radar and the right radar; Determining a plurality of preset angles based on the field angle; along any preset angle, carrying out path planning by utilizing the path planning algorithm, and determining the furthest travelable target distance based on the probability corresponding to the grid in the planned path; and determining the drivable area based on a plurality of target distances corresponding to the preset angles respectively. In one possible implementation manner, the path planning is performed by using the path planning algorithm along any preset angle, and determining the target distance that can be driven furthest based on the probability corresponding to the grid in the planned path includes: taking the position of the vehicle as a starting point, taking a preset radius as a maximum planning distance, and carrying out path planning from the starting point along the preset angle by utilizing a Blueson-Ham straight line algorithm to determine an ith candidate grid; Judging whether the probability corresponding to the ith candidate grid exceeds a probability threshold, if so, stopping path planning, and determining the ith candidate grid as a target grid; otherwise, continuing to execute path planning, and determining an (i+1) th candidate grid; Judging whether the probability corresponding to the (i+1) th candidate grid exceeds the probability threshold value, if so, stopping path planning, and determining the (i+1) th candidate grid as the target grid; otherwise, repeating the above process until the furthest grid corresponding to the preset radius is reached or the probability corresponding to the (i+1) th candidate grid exceeds the probability threshold, stopping iteration, and determining the grid corresponding to the stopped iteration as the target grid; the target distance is determined based on a distance between the location of the vehicle and the target grid. In one possible implementation, the method further comprises one or more of the following: For a first preset angle, calculating a first target distance corresponding to the first preset angle based on a second target distance corresponding to a second preset angle and a third target distance corresponding to a third preset angle, wherein the first preset angle belongs to a preset large angle range, the second preset angle is a previous angle of the first preset angle, and the third preset angle is a subsequent angle of the first preset angle, or And calculating an average value of a plurality of target distances corresponding to the target preset angles when a saw-tooth area exists in a drivable area corresponding to