CN116136599A - Determination method and device for drivable area and storage medium - Google Patents
Determination method and device for drivable area and storage medium Download PDFInfo
- Publication number
- CN116136599A CN116136599A CN202111360333.1A CN202111360333A CN116136599A CN 116136599 A CN116136599 A CN 116136599A CN 202111360333 A CN202111360333 A CN 202111360333A CN 116136599 A CN116136599 A CN 116136599A
- Authority
- CN
- China
- Prior art keywords
- point
- grid
- ground
- fan
- grids
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The utility model discloses a determination method, a determination device and a storage medium for a drivable area, which relate to the technical field of automatic driving. The method comprises the following steps: dividing the point cloud data into point clusters, wherein the division result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map; screening candidate ground grids from the fan-shaped annular grids according to the degree of the spread of each point in the point cluster in the direction vertical to the ground; screening the ground grids capable of running from the candidate ground grids according to the distance between the candidate ground grids and the central point of the fan-shaped grid map and the height value of each point in the point cluster corresponding to the candidate ground grids in the direction vertical to the ground; the travelable region is determined from the travelable ground grid.
Description
Technical Field
The embodiment of the application relates to the technical field of automatic driving, in particular to a method and a device for determining a drivable area and a storage medium.
Background
The detection of the drivable area of the vehicle is a key technology in the field of automatic driving of the vehicle, and the effective detection of the drivable area not only can provide a safe and reliable drivable area for the vehicle which drives automatically, but also can greatly reduce the effective range of the vehicle for judging the obstacle, and improve the accuracy of obstacle avoidance of the vehicle.
The existing detection method of the drivable area generally comprises the steps of acquiring point cloud data based on a laser radar, partitioning the point cloud data, then carrying out ground point segmentation on the point cloud in each partition, and determining the drivable area by adopting a mode of fitting planes with all ground points.
However, the above-mentioned detection method for the drivable area is poor in robustness of the detection result in complex road conditions such as rough road surface, large fluctuation and the like.
Disclosure of Invention
The invention provides a method, a device and a storage medium for determining a drivable region, which can improve the robustness of the method for determining the drivable region.
In order to achieve the above purpose, the present application adopts the following technical scheme:
in a first aspect, the present application provides a method for determining a drivable area, including: dividing the point cloud data into point clusters, wherein the division result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map; screening candidate ground grids from the fan-shaped annular grids according to the degree of the spread of each point in the point cluster in the direction vertical to the ground; screening the ground grids capable of running from the candidate ground grids according to the distance between the candidate ground grids and the central point of the fan-shaped grid map and the height value of each point in the point cluster corresponding to the candidate ground grids in the direction vertical to the ground; the travelable region is determined from the travelable ground grid.
In the technical scheme provided by the application, the acquired point cloud data can be divided into a plurality of point clusters, and each point cluster corresponds to one fan-shaped annular grid in the fan-shaped annular grid map respectively. Then, candidate ground grids can be screened out according to the spread degree of each point in the point cluster in the direction vertical to the ground. The degree of spread of each point in the point cluster in the direction vertical to the ground can represent the degree of concave-convex of the land form of the actual area of the fan-shaped annular grid corresponding to the point cluster, so that the flatter candidate ground grid of the land form of the actual area can be screened out from the fan-shaped annular grid according to the degree of spread. And then, according to the distance between the candidate ground grids and the central point of the fan-shaped annular grid map and the height value of each point in the point cluster corresponding to the candidate ground grids in the direction vertical to the ground, selecting the drivable ground grids with smaller relative ground height values from the candidate ground grids. It can be seen that through the screening of many steps, the present application can obtain that the topography of actual region is comparatively even to the ground grid that can travel that relative ground height value is less, so the technical scheme that this application provided can be applicable to the road surface roughness, and it is great that fluctuation is in the regional detection that can travel among the complicated road conditions. Therefore, the technical scheme can improve the robustness of the determination method of the drivable area. In addition, the fan-shaped annular grid map is divided into the fan-shaped annular grids with higher precision, so that the point clusters corresponding to each fan-shaped annular grid can be analyzed and processed with higher precision, and the accuracy of the determination result of the drivable area can be improved.
Optionally, in one possible design manner, before the "screening the candidate ground grids from the fan-ring grids according to the degree of spread of each point in the point cluster in the direction perpendicular to the ground", the method for determining the improved travelable area of the present application may further include:
determining the average height of each point in the point cluster in the direction vertical to the ground;
determining fan-shaped annular grids corresponding to the point clusters with the average height smaller than or equal to the first preset height as grids in the first grid set;
according to the degree of the spread of each point in the point cluster in the direction vertical to the ground, candidate ground grids are screened from the fan-shaped annular grids, and the method comprises the following steps: and screening candidate ground grids from the first grid set according to the degree of spread of each point in the point cluster corresponding to each grid in the first grid set in the direction vertical to the ground.
Alternatively, in another possible design manner, the "screening candidate ground grids from the fan-ring grid according to the degree of spread of each point in the cluster of points in the direction perpendicular to the ground" may include:
determining curvature and normal vector of a curved surface which is synthesized by each point in the point cluster according to the three-dimensional coordinates of each point in the point cluster; the curvature is used for representing the spread degree of each point in the point cluster in the direction vertical to the ground; the normal vector is used for representing the proximity degree of the curved surface and the plane which are synthesized by each point in the point cluster;
Candidate ground grids are screened from the fanned annular grids according to the curvature and the normal vector.
Alternatively, in another possible design manner, "screening candidate ground grids from the fan-ring grid according to curvature and normal vector" may include:
determining a point cluster with the minimum curvature as a target point cluster, and determining a fan-shaped annular grid corresponding to the target point cluster as a target grid;
determining a normal angle difference according to normal vectors of point clusters corresponding to other fan-ring grids in the fan-ring grid map and normal vectors of target point clusters, and determining a second grid set from the fan-ring grids according to the normal angle difference;
and screening candidate ground grids from the second grid set according to the curvature of the point cluster corresponding to each fan-shaped annular grid in the second grid set.
Optionally, in another possible design manner, the "screening the drivable ground grid from the candidate ground grids according to the distance between the candidate ground grid and the center point of the fan-shaped ring grid map and the height value of each point in the point cluster corresponding to the candidate ground grid in the direction perpendicular to the ground" includes:
determining the local height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground according to the maximum height and the minimum height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground;
Determining the gradient of the point cluster corresponding to the candidate ground grid relative to the ground according to the average height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground and the distance between the center point of the candidate ground grid and the center point of the fan-shaped annular grid map;
and determining the candidate ground grids with the gradient belonging to the preset gradient range and the local height smaller than the second preset height as the drivable ground grids.
Optionally, in another possible design manner, the "dividing the point cloud data into the point clusters, where the dividing result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map" includes:
determining a sector partition and an annular partition of each point in the point cloud data in a sector annular grid map based on coordinates of each point in the point cloud data in a first preset direction and a second preset direction; the first preset direction and the second preset direction are mutually perpendicular, and are parallel to the ground;
and determining a sector ring grid to which each point in the point cloud data belongs in the sector ring grid map according to the sector partition and the ring partition, and determining the points belonging to the same sector ring grid as the points in the same point cluster.
Alternatively, in another possible design manner, the above-mentioned "determining the drivable area according to the drivable floor grid" may include:
if the third grid is determined to be a drivable ground grid according to at least two clusters of point cloud data, determining an area corresponding to the third grid as a drivable sub-area; the third grid is any grid in the fan-shaped annular grid map;
and superposing the drivable subareas to obtain the drivable area.
In a second aspect, the present application provides a determination device for a drivable area, including: the device comprises a dividing module, a screening module and a determining module;
the division module is used for dividing the point cloud data into point clusters, and the division result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map;
the screening module is used for screening candidate ground grids from the fan-shaped annular grids according to the degree of the spread of each point in the point cluster divided by the dividing module in the direction vertical to the ground;
the screening module is also used for screening the ground grids capable of running from the candidate ground grids according to the distance between the candidate ground grids and the central point of the fan-shaped annular grid map and the height value of each point in the point cluster corresponding to the candidate ground grids in the direction vertical to the ground;
And the determining module is used for determining the drivable area according to the drivable ground grids screened by the screening module.
Optionally, in one possible design manner, the determining module is further configured to: before a screening module screens candidate ground grids from the fan-shaped ring grids according to the degree of the spread of each point in the point cluster in the direction vertical to the ground, determining the average height of each point in the point cluster in the direction vertical to the ground; determining fan-shaped annular grids corresponding to the point clusters with the average height smaller than or equal to the first preset height as grids in the first grid set;
the screening module is specifically used for: and screening candidate ground grids from the first grid set according to the degree of spread of each point in the point cluster corresponding to each grid in the first grid set in the direction vertical to the ground.
Alternatively, in another possible design, the screening module is specifically configured to:
determining curvature and normal vector of a curved surface which is synthesized by each point in the point cluster according to the three-dimensional coordinates of each point in the point cluster; the curvature is used for representing the spread degree of each point in the point cluster in the direction vertical to the ground; the normal vector is used for representing the proximity degree of the curved surface and the plane which are synthesized by each point in the point cluster;
Candidate ground grids are screened from the fanned annular grids according to the curvature and the normal vector.
Alternatively, in another possible design, the screening module is specifically configured to:
determining a point cluster with the minimum curvature as a target point cluster, and determining a fan-shaped annular grid corresponding to the target point cluster as a target grid;
determining a normal angle difference according to normal vectors of point clusters corresponding to other fan-ring grids in the fan-ring grid map and normal vectors of target point clusters, and determining a second grid set from the fan-ring grids according to the normal angle difference;
and screening candidate ground grids from the second grid set according to the curvature of the point cluster corresponding to each fan-shaped annular grid in the second grid set.
Alternatively, in another possible design, the screening module is specifically configured to:
determining the local height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground according to the maximum height and the minimum height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground;
determining the gradient of the point cluster corresponding to the candidate ground grid relative to the ground according to the average height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground and the distance between the center point of the candidate ground grid and the center point of the fan-shaped annular grid map;
And determining the candidate ground grids with the gradient belonging to the preset gradient range and the local height smaller than the second preset height as the drivable ground grids.
Alternatively, in another possible design manner, the dividing module is specifically configured to:
determining a sector partition and an annular partition of each point in the point cloud data in a sector annular grid map based on coordinates of each point in the point cloud data in a first preset direction and a second preset direction; the first preset direction and the second preset direction are mutually perpendicular, and are parallel to the ground;
and determining a sector ring grid to which each point in the point cloud data belongs in the sector ring grid map according to the sector partition and the ring partition, and determining the points belonging to the same sector ring grid as the points in the same point cluster.
Alternatively, in another possible design manner, the determining module is specifically configured to:
if the third grid is determined to be a drivable ground grid according to at least two clusters of point cloud data, determining an area corresponding to the third grid as a drivable sub-area; the third grid is any grid in the fan-shaped annular grid map;
and superposing the drivable subareas to obtain the drivable area.
In a third aspect, the present application provides a determination apparatus for a drivable region, including a memory, a processor, a bus, and a communication interface; the memory is used for storing computer execution instructions, and the processor is connected with the memory through a bus; when the determination means for a travelable region is operated, the processor executes computer-executable instructions stored in the memory to cause the determination means for a travelable region to perform the determination method for a travelable region as provided in the first aspect described above.
Alternatively, the determination device of the drivable region may be for the vehicle itself or may be a part of the devices in the vehicle, for example a chip system in the vehicle. The chip system is used for supporting the determination device of the drivable area to realize the functions involved in the first aspect, such as receiving, transmitting or processing the data and/or information involved in the determination method of the drivable area. The chip system includes a chip, and may also include other discrete devices or circuit structures.
In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored therein, which when executed by a computer, cause the computer to perform the method of determining a travelable region as provided in the first aspect.
In a fifth aspect, the present application provides a computer program product comprising computer instructions which, when run on a computer, cause the computer to perform the method of determining a travelable region as provided in the first aspect.
It should be noted that the above-mentioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer readable storage medium may be packaged together with the processor of the determination device of the drivable area, or may be packaged separately from the processor of the determination device of the drivable area, which is not limited in this application.
The description of the second, third, fourth and fifth aspects of the present application may refer to the detailed description of the first aspect; further, the advantageous effects described in the second aspect, the third aspect, the fourth aspect, and the fifth aspect may refer to the advantageous effect analysis of the first aspect, and are not described herein.
In the present application, the names of the above-mentioned determination means of the drivable region do not constitute a limitation on the devices or function modules themselves, which may appear under other names in an actual implementation. Insofar as the function of each device or function module is similar to the present application, it is within the scope of the claims of the present application and the equivalents thereof.
These and other aspects of the present application will be more readily apparent from the following description.
Drawings
Fig. 1 is a flow chart of a method for determining a travelable region according to an embodiment of the present application;
fig. 2 is a schematic diagram of a fan-ring grid map according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating another method for determining a travelable region according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a determination device for a travelable region according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of another device for determining a travelable region according to an embodiment of the present application.
Detailed Description
The following describes a method, an apparatus, and a storage medium for determining a travelable region according to embodiments of the present application in detail with reference to the accompanying drawings.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone.
The terms "first" and "second" and the like in the description and in the drawings are used for distinguishing between different objects or for distinguishing between different processes of the same object and not for describing a particular sequential order of objects.
Furthermore, references to the terms "comprising" and "having" and any variations thereof in the description of the present application are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed but may optionally include other steps or elements not listed or inherent to such process, method, article, or apparatus.
It should be noted that, in the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
In the description of the present application, unless otherwise indicated, the meaning of "a plurality" means two or more.
The detection of the drivable area of the vehicle is a key technology in the field of automatic driving of the vehicle, and the effective detection of the drivable area not only can provide a safe and reliable drivable area for the vehicle which drives automatically, but also can greatly reduce the effective range of the vehicle for judging the obstacle, and improve the accuracy of obstacle avoidance of the vehicle.
The existing detection method of the drivable area generally comprises the steps of acquiring point cloud data based on a laser radar, partitioning the point cloud data, then carrying out ground point segmentation on the point cloud in each partition, and determining the drivable area by adopting a mode of fitting planes with all ground points.
However, the above-mentioned detection method for the drivable area is poor in robustness of the detection result in complex road conditions such as rough road surface, large fluctuation and the like.
Aiming at the problems in the prior art, the embodiment of the application provides a determination method of a drivable area, and the method can obtain a drivable ground grid with a relatively flat actual area topography and a relatively small ground height value through screening in multiple steps, so that the method can be suitable for detecting the drivable area in complex road conditions with rough road surfaces and large fluctuation. Therefore, the robustness of the determination method of the drivable region can be improved.
The method for determining the drivable area provided by the embodiment of the application can be applied to a vehicle and also can be applied to a chip system of the vehicle. The determination method of the travelable area can be suitable for detecting the travelable area in the unmanned strip mine. Of course, in practical application, the method and the device can be also suitable for other scenes of complex road conditions with rough road surfaces and large fluctuation, and the embodiment of the application is not limited to the scenes.
The following describes in detail a method for determining a travelable region provided in an embodiment of the present application.
Referring to fig. 1, the method for determining a drivable area provided in the embodiment of the present application includes S101-S104:
s101, dividing point cloud data into point clusters, wherein the division result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map.
In order to improve accuracy of a determination result of a drivable area, in the embodiment of the present application, a sector-ring grid map may be divided into sector-ring grids with higher precision, so that higher-precision analysis processing may be performed on a cluster of points corresponding to each sector-ring grid.
Optionally, the method for determining a drivable area provided in the embodiment of the present application may divide a point cluster for point cloud data in the following manner: determining a sector partition and an annular partition of each point in the point cloud data in a sector annular grid map based on coordinates of each point in the point cloud data in a first preset direction and a second preset direction; and determining a sector ring grid to which each point in the point cloud data belongs in the sector ring grid map according to the sector partition and the ring partition, and determining the points belonging to the same sector ring grid as the points in the same point cluster.
The first preset direction and the second preset direction may be two directions which are manually predetermined and are perpendicular to each other, and the first preset direction and the second preset direction are both parallel to the ground, for example, the first preset direction may correspond to an x-axis direction in a cartesian coordinate system, and the second preset direction may correspond to a y-axis direction in the cartesian coordinate system.
Illustratively, the three-dimensional coordinates of any point P in the point cloud data in a Cartesian coordinate system can be obtained using (x i ，y i ，z i ) And (3) representing. Wherein x is i ，y i And z i Representing coordinates in the x-axis, y-axis and z-axis, respectively. The sector and ring partitions to which each point belongs in the sector ring grid map can be determined based on the coordinates of each point in the point cloud data in the x-axis direction and the y-axis direction. Specifically, the sector partition to which each point belongs may be determined according to the expression (1), and the annular partition to which each point belongs may be determined according to the expression (2):
wherein, angel local Represents the sector partition to which the P point belongs, alpha represents a preset partition angle, radius local The method is characterized in that the method comprises the steps of representing an annular partition to which a P point belongs, and d represents a preset partition distance.
Illustratively, referring to fig. 2, there is provided a fan ring-shaped grid map which is divided into a plurality of ring-shaped partitions from inside to outside, and the circumferential direction is divided into a plurality of sector-shaped partitions by angles. The preset dividing angle may be an angle determined in advance according to the number of required sector areas, for example, when the number of required sector areas is 16, the preset dividing angle is 360 °/16=22.5 °. The preset dividing distance may be a distance determined in advance according to the number of annular partitions required. As shown in fig. 2, the device may rotate counterclockwise with the positive x-axis direction as the starting side, divide into a sector-shaped partition every 22.5 ° of rotation, divide the annular partition outwards with the center point of the sector-shaped grid map as the starting point, and specifically divide an annular partition every preset dividing distance. After determining the sector and ring partitions to which each point belongs in the sector-ring grid map according to the expression (1) and the expression (2), the corresponding sector-ring grid can be determined in fig. 2. For example, the annular partition to which the P point belongs is the annular partition of the outermost ring in fig. 2, the sector partition to which the P point belongs is the first sector partition in the counterclockwise direction of fig. 2 with the positive x-axis direction as the starting side, and the sector annular grid to which the P point belongs is shown as the label in fig. 2.
Similarly, a fan ring grid to which each point in the point cloud data belongs in the fan ring grid map may be determined, and then points belonging to the same fan ring grid may be determined as points in the same point cluster, thereby dividing the point cloud data into a plurality of point clusters.
In the embodiment of the application, when the point cloud data is classified into the point clusters, the point clusters are determined based on three-dimensional coordinates of each point P in the point cloud data in a cartesian coordinate system, and the point cloud data collected by the laser radar is generally coordinates in a polar coordinate system. Therefore, optionally, the point cloud data acquired under the laser radar coordinate system may be converted into coordinates under the vehicle coordinate system.
Illustratively, the three-dimensional polar coordinates of the P-point in the lidar coordinate system are (ρ i ，θ i ，γ i ) Wherein ρ is i Representing the Euclidean distance, θ, of the center of the lidar to the detected object i Indicating yaw emission angle of laser radar, gamma i Representing the pitch firing angle of the lidar. The lidar coordinate system may be converted to a vehicle coordinate system according to expression (3):
the x-axis direction of the vehicle coordinate system is the vehicle forward direction, the y-axis direction is the vehicle right direction, and the z-axis direction is the direction vertical to the ground.
The laser radar coordinate system is thatThe center of the laser radar is used as an origin, and the vehicle coordinate system uses the center of the vehicle as the origin, so that the translational and rotational relation exists between the laser radar coordinate system and the vehicle coordinate system, and the translational relation [ x ] between the laser radar coordinate system and the vehicle coordinate system can be obtained through manual measurement iv ，y iv ，z iv ]And obtain the rotation relation between the laser radar coordinate system and the vehicle coordinate system
The coordinates of any point P in the vehicle coordinate system after translation and rotation can be obtained according to expression (4):
wherein R is determined according to expression (5), and t is determined according to expression (6):
optionally, after converting the point cloud data under the laser radar coordinate system into the point cloud data under the vehicle coordinate system, the point cloud data may be preprocessed first to obtain the point cloud data required by the user. For example, the point of the vehicle itself in the point cloud data can be filtered and removed according to the length and width of the vehicle, and the point cloud data farther from the vehicle can also be filtered and removed. And then, carrying out point cluster division on the filtered point cloud data.
S102, screening candidate ground grids from the fan-shaped annular grids according to the degree of the spread of each point in the point cluster in the direction vertical to the ground.
The degree of spread of each point in the point cluster in the direction vertical to the ground can represent the degree of concave-convex of the actual area topography of the fan-shaped annular grid corresponding to the point cluster, so that candidate ground grids with relatively flat actual area topography can be screened out from the fan-shaped annular grid according to the degree of spread.
Alternatively, the degree of spread of each point in the point cluster in the direction perpendicular to the ground may be represented by the curvature of the curved surface to which each point in the point cluster is fitted. After the point cloud data is divided into point clusters, the curvature and normal vector of a curved surface which is formed by fitting each point in the point clusters can be determined according to the three-dimensional coordinates of each point in the point clusters; candidate ground grids are then screened from the fanned annular grids based on curvature and normal vector.
The curvature is used for representing the spread degree of each point in the point cluster in the direction vertical to the ground; the normal vector is used for representing the proximity degree of the curved surface and the plane which are synthesized by each point in the point cluster.
Illustratively, in one possible implementation, a least square method may be used to fit the point cluster corresponding to the fan-ring grid to a curved surface M, and the specific curved surface M may be obtained based on the expression (7):
wherein n represents the normal vector of the curved surface M, k represents the total number of points in the point cluster corresponding to the fan-shaped annular grid, and P i Representing the three-dimensional coordinates of the ith point in the cluster of points corresponding to the fan-ring grid,
representing point P i Distance to the center point of the fan ring grid. P can be determined based on expression (8) i The corresponding covariance matrix C:
wherein P is 0 Representing the centroid of the cluster of points corresponding to the fan ring grid.
The covariance matrix C is subjected to eigenvalue decomposition to obtain eigenvalue lambda 0 ，λ 1 And lambda (lambda) 2 . The curvature δ=λ of the curved surface M 0 /(λ 0 +λ 1 +λ 2 )。
Alternatively, in one possible implementation manner, the point cluster with the smallest curvature may be determined as the target point cluster, and the fan-shaped annular grid corresponding to the target point cluster may be determined as the target grid; then, determining a normal angle difference according to the normal vector of the point cluster corresponding to other fan-ring grids in the fan-ring grid map and the normal vector of the target point cluster, and determining a second grid set from the fan-ring grids according to the normal angle difference; and then, selecting candidate ground grids from the second grid set according to the curvature of the point cluster corresponding to each fan-shaped annular grid in the second grid set.
The other fan-shaped grids are other grids except the target grid in the fan-shaped grid map.
Exemplary, if the normal vector of the point cluster corresponding to the other fan-shaped ring grid is n i Represented as n for normal vector of target point cluster j Expressed, the normal angle difference σ can be determined according to expression (9):
if the normal angle difference σ is less than or equal to the preset angle threshold, the corresponding fan-ring grid may be determined as a grid in the second grid set.
According to the embodiment of the application, the candidate ground grids with smaller curvature and smaller difference between the curvature and the normal angle of the target grid can be obtained. Because the curvature of the curved surface synthesized by each point in the point cluster of the target grid is very small, and the curvature of the curved surface synthesized by each point in the point cluster can represent the flatness of the actual area topography of the fan-shaped annular grid corresponding to the point cluster, the candidate ground grids which are relatively flat in actual area topography and close to the ground can be screened out through the embodiment of the application.
Optionally, before screening candidate ground grids from the fan-ring grids according to the degree of spread of each point in the point cluster in the direction perpendicular to the ground, the method for determining the drivable area provided in the embodiment of the present application may further include: determining the average height of each point in the point cluster in the direction vertical to the ground; and determining the fan-shaped annular grids corresponding to the point clusters with the average height smaller than or equal to the first preset height as grids in the first grid set. After the first grid set is obtained, candidate ground grids can be selected from the first grid set according to the spread degree of each point in the point cluster corresponding to each grid in the first grid set in the direction perpendicular to the ground.
In the embodiment of the application, before determining the candidate ground grids, fan-shaped ring grids corresponding to the point clusters with smaller average height can be screened out based on the average height of each point in the point clusters in the direction vertical to the ground. Therefore, a large number of grids which do not meet the requirements can be quickly screened out, and then the remaining fan-shaped annular grids are finely detected, so that the detection efficiency of the drivable area can be improved.
The first preset height may be a height determined by a person in advance.
For example, the average height z of each point in the point cluster in the direction perpendicular to the ground can be determined according to the expression (10) g ：
Where k represents the total number of points in the cluster of points, i represents the ith point in the k points, z i The height of the ith point in the direction perpendicular to the ground (corresponding to the z-axis coordinate in the vehicle coordinate system) is represented.
S103, screening the ground grids capable of running from the candidate ground grids according to the distance between the candidate ground grids and the center point of the fan-shaped grid map and the height value of each point in the point cluster corresponding to the candidate ground grids in the direction vertical to the ground.
In practical applications, the surface of some obstacles (such as a table) scanned by the lidar is also a relatively flat surface, and the grid of the area where the obstacles are located may be mistakenly determined as a candidate ground grid. Therefore, in the embodiment of the application, the candidate ground grids can be further screened to obtain the drivable ground grids.
Alternatively, in one possible implementation, the candidate ground grid may be further screened by: determining the local height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground according to the maximum height and the minimum height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground; determining the gradient of the point cluster corresponding to the candidate ground grid relative to the ground according to the average height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground and the distance between the center point of the candidate ground grid and the center point of the fan-shaped annular grid map; and determining the candidate ground grids with the gradient belonging to the preset gradient range and the local height smaller than the second preset height as the drivable ground grids.
The preset gradient range is a gradient range determined manually in advance, and the preset gradient range may include an upper gradient threshold and a lower gradient threshold, and the second preset height is a height determined manually in advance.
Exemplary, if the maximum height of each point in the point cluster corresponding to the ith grid in the candidate ground grids in the direction perpendicular to the ground
Representing the minimum height +.>
The local height of each point in the point cluster corresponding to the ith grid in the direction vertical to the ground can be +. >
The distance between the center point of the ith grid in the candidate ground grids and the center point of the fan-shaped annular grid map can be d i D is represented by i ＝(radius local ) D. Wherein radius is local The method is characterized in that the method is used for indicating the annular partition to which the ith grid belongs, and d is used for indicating the preset partition distance. If the point corresponding to the ith grid in the candidate ground gridsThe average height of the points in the cluster in the direction perpendicular to the ground is +.>
The gradient +.of the cluster corresponding to the candidate ground grid with respect to the ground can be determined based on expression (11)>
If it is
Is smaller than the upper gradient threshold and larger than the lower gradient threshold, and +.>
If the height is smaller than the second preset height, the ith grid can be determined as a travelable ground grid. Therefore, through gradient and height screening, some obstacles with relatively flat surfaces can be screened out, so that the ground grid can be accurately determined, and the robustness of the algorithm can be improved.
S104, determining a travelable area according to the travelable ground grid.
Optionally, in one possible implementation manner, if the third grid is determined to be a drivable ground grid according to at least two clusters of point cloud data, determining an area corresponding to the third grid as a drivable sub-area; and then, overlapping the drivable subareas to obtain the drivable area.
The third grid is any grid in the fan-shaped annular grid map.
Because of the contingency of one detection, in order to further improve the robustness of the detection method of the drivable ground grid, in the embodiment of the present application, continuous point cloud data collected by the laser radar device can be detected, and if the third grid is determined to be a drivable sub-area in continuous multiple detections, it can be determined that the area actually corresponding to the grid is a vehicle drivable area.
In the technical scheme provided by the embodiment of the application, the acquired point cloud data can be divided into a plurality of point clusters, and each point cluster corresponds to one fan-shaped annular grid in the fan-shaped annular grid map respectively. Then, candidate ground grids can be screened out according to the spread degree of each point in the point cluster in the direction vertical to the ground. The uneven degree of the land features of the actual area of the fan-shaped annular grid corresponding to the point cluster can be represented by the uneven degree of each point in the point cluster in the direction perpendicular to the ground, so that candidate ground grids with relatively flat land features of the actual area can be screened out from the fan-shaped annular grid according to the uneven degree. And then, according to the distance between the candidate ground grids and the central point of the fan-shaped annular grid map and the height value of each point in the point cluster corresponding to the candidate ground grids in the direction vertical to the ground, selecting the drivable ground grids with smaller relative ground height values from the candidate ground grids. It can be seen that through multi-step screening, the embodiment of the application can obtain the land form of the actual area to be relatively flat, and the ground grid capable of running with relatively small ground height value, so that the technical scheme provided by the embodiment of the application can be suitable for detecting the area capable of running on complex road conditions such as uneven road surfaces, large fluctuation and the like. Therefore, the method for determining the drivable region can improve the robustness of the method for determining the drivable region. In addition, in the embodiment of the application, the fan-shaped annular grid map is divided into the fan-shaped annular grids with higher precision, so that higher-precision analysis processing can be performed on the point clusters corresponding to each fan-shaped annular grid, and the accuracy of the determination result of the drivable area can be improved.
In view of the above description, as shown in fig. 3, the embodiment of the present application further provides a method for determining a drivable area, including S301-S3011:
s301, dividing point clusters into point cloud data, wherein the division result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map.
S302, determining the average height of each point in the point cluster in the direction vertical to the ground.
S303, determining fan-shaped annular grids corresponding to the point clusters with the average height smaller than or equal to the first preset height as grids in the first grid set.
S304, determining the curvature and normal vector of the curved surface which is formed by fitting each point in the point cluster according to the three-dimensional coordinates of each point in the point cluster corresponding to each grid in the first grid set.
S305, determining the point cluster with the smallest curvature as a target point cluster, and determining a fan-shaped annular grid corresponding to the target point cluster as a target grid.
S306, determining a normal angle difference according to normal vectors of point clusters corresponding to other fan-ring grids in the fan-ring grid map and normal vectors of target point clusters, and determining a second grid set from the fan-ring grids according to the normal angle difference.
S307, screening candidate ground grids from the second grid set according to the curvature of the point cluster corresponding to each fan-shaped annular grid in the second grid set.
S308, determining the local height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground according to the maximum height and the minimum height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground.
S309, determining the gradient of the point cluster corresponding to the candidate ground grid relative to the ground according to the average height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground and the distance between the center point of the candidate ground grid and the center point of the fan-shaped annular grid map.
S3010, determining the candidate ground grids with the gradients belonging to the preset gradient range and the local heights smaller than the second preset height as the drivable ground grids.
S3011, if the third grid is determined to be a drivable ground grid according to at least two clusters of point cloud data, determining an area corresponding to the third grid as a drivable sub-area, and superposing the drivable sub-areas to obtain the drivable area.
As shown in fig. 4, the embodiment of the present application further provides a device for determining a drivable area, where the device for determining a drivable area may include: the system comprises a dividing module 11, a screening module 12 and a determining module 13.
Wherein the dividing module 11 executes S101 in the above method embodiment, the screening module 12 executes S102 and S103 in the above method embodiment, and the determining module 13 executes S104 in the above method embodiment.
Specifically, the division module 11 is configured to divide the point cloud data into point clusters, where a division result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map;
a screening module 12, configured to screen candidate ground grids from the fan-shaped ring grids according to the degree of spread of each point in the point cluster divided by the dividing module 11 in the direction perpendicular to the ground;
the screening module 12 is further configured to screen a ground grid that can run from the candidate ground grids according to a distance between the candidate ground grids and a center point of the fan-shaped grid map and a height value of each point in a point cluster corresponding to the candidate ground grids in a direction perpendicular to the ground;
and the determining module 13 is used for determining the drivable area according to the drivable ground grids screened by the screening module 12.
Optionally, in one possible design, the determining module 13 is further configured to: before the screening module 12 screens candidate ground grids from the fan-shaped ring grids according to the degree of spread of each point in the point cluster in the direction vertical to the ground, determining the average height of each point in the point cluster in the direction vertical to the ground; determining fan-shaped annular grids corresponding to the point clusters with the average height smaller than or equal to the first preset height as grids in the first grid set;
The screening module 12 is specifically configured to: and screening candidate ground grids from the first grid set according to the degree of spread of each point in the point cluster corresponding to each grid in the first grid set in the direction vertical to the ground.
Alternatively, in another possible design, the screening module 12 is specifically configured to:
determining curvature and normal vector of a curved surface which is synthesized by each point in the point cluster according to the three-dimensional coordinates of each point in the point cluster; the curvature is used for representing the spread degree of each point in the point cluster in the direction vertical to the ground; the normal vector is used for representing the proximity degree of the curved surface and the plane which are synthesized by each point in the point cluster;
candidate ground grids are screened from the fanned annular grids according to the curvature and the normal vector.
Alternatively, in another possible design, the screening module 12 is specifically configured to:
determining a point cluster with the minimum curvature as a target point cluster, and determining a fan-shaped annular grid corresponding to the target point cluster as a target grid;
determining a normal angle difference according to normal vectors of point clusters corresponding to other fan-ring grids in the fan-ring grid map and normal vectors of target point clusters, and determining a second grid set from the fan-ring grids according to the normal angle difference;
and screening candidate ground grids from the second grid set according to the curvature of the point cluster corresponding to each fan-shaped annular grid in the second grid set.
Alternatively, in another possible design, the screening module 12 is specifically configured to:
determining the local height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground according to the maximum height and the minimum height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground;
determining the gradient of the point cluster corresponding to the candidate ground grid relative to the ground according to the average height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground and the distance between the center point of the candidate ground grid and the center point of the fan-shaped annular grid map;
and determining the candidate ground grids with the gradient belonging to the preset gradient range and the local height smaller than the second preset height as the drivable ground grids.
Alternatively, in another possible design, the dividing module 11 is specifically configured to:
determining a sector partition and an annular partition of each point in the point cloud data in a sector annular grid map based on coordinates of each point in the point cloud data in a first preset direction and a second preset direction; the first preset direction and the second preset direction are mutually perpendicular, and are parallel to the ground;
And determining a sector ring grid to which each point in the point cloud data belongs in the sector ring grid map according to the sector partition and the ring partition, and determining the points belonging to the same sector ring grid as the points in the same point cluster.
Alternatively, in another possible design, the determining module 13 is specifically configured to:
if the third grid is determined to be a drivable ground grid according to at least two clusters of point cloud data, determining an area corresponding to the third grid as a drivable sub-area; the third grid is any grid in the fan-shaped annular grid map;
and superposing the drivable subareas to obtain the drivable area.
Optionally, the determination device of the drivable area may further include a storage module for storing a program code or the like of the determination device of the drivable area.
As shown in fig. 5, the embodiment of the present application further provides a determination device of a drivable area, including a memory 41, a processor 42 (42-1 and 42-2), a bus 43, and a communication interface 44; the memory 41 is used for storing computer-executable instructions, and the processor 42 is connected with the memory 41 through the bus 43; when the determination means for a travelable region is operated, the processor 42 executes computer-executable instructions stored in the memory 41 to cause the determination means for a travelable region to execute the determination method for a travelable region as provided in the above-described embodiment.
In a particular implementation, the processor 42 may include, as one embodiment, one or more central processing units (central processing unit, CPU), such as CPU0 and CPU1 shown in FIG. 5. And as one example, the determination means of the drivable area may include a plurality of processors 42, such as the processor 42-1 and the processor 42-2 shown in fig. 5. Each of these processors 42 may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor 42 herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).
The memory 41 may be, but is not limited to, a read-only memory 41 (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), a compact disc read-only memory (compact disc read-only memory) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory 41 may be stand alone and be coupled to the processor 42 via a bus 43. Memory 41 may also be integrated with processor 42.
In a specific implementation, the memory 41 is used for storing data in the application and computer-executable instructions corresponding to executing a software program of the application. The processor 42 may determine various functions of the drivable area determination means by running or executing a software program stored in the memory 41 and calling data stored in the memory 41.
The communication interface 44 uses any transceiver-like device for communicating with other devices or communication networks, such as a control system, a radio access network (radio access network, RAN), a wireless local area network (wireless local area networks, WLAN), etc. The communication interface 44 may include a receiving unit to implement a receiving function and a transmitting unit to implement a transmitting function.
As an example, in connection with fig. 4, the screening module in the determination device of the drivable area performs the same function as the processor in fig. 5, and the storage module in the determination device of the drivable area performs the same function as the memory in fig. 5.
The explanation of the related content in this embodiment may refer to the above method embodiment, and will not be repeated here.
From the foregoing description of the embodiments, it will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of functional modules is illustrated, and in practical application, the above-described functional allocation may be implemented by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to implement all or part of the functions described above. The specific working processes of the above-described systems, devices and units may refer to the corresponding processes in the foregoing method embodiments, which are not described herein.
The present embodiment also provides a computer-readable storage medium having instructions stored therein, which when executed by a computer, cause the computer to perform the method for determining a travelable region provided by the above embodiments.
The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (erasable programmable read only memory, EPROM), a register, a hard disk, an optical fiber, a CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing, or any other form of computer readable storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (application specific integrated circuit, ASIC). In the context of the present application, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The foregoing is merely a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method of determining a drivable region, comprising:
dividing the point cloud data into point clusters, wherein the division result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map;
screening candidate ground grids from the fan-shaped annular grids according to the spread degree of each point in the point cluster in the direction vertical to the ground;
screening out a ground grid which can run from the candidate ground grids according to the distance between the candidate ground grids and the central point of the fan-shaped annular grid map and the height value of each point in the point cluster corresponding to the candidate ground grids in the direction vertical to the ground;
and determining a travelable area according to the travelable ground grid.
2. The method for determining a travelable region according to claim 1, wherein before the candidate ground grid is selected from the fan-shaped ring grid according to the degree of spread of each point in the point cluster in a direction perpendicular to the ground, the method further comprises:
Determining the average height of each point in the point cluster in the direction vertical to the ground;
determining fan-shaped annular grids corresponding to the point clusters with the average height smaller than or equal to a first preset height as grids in a first grid set;
the step of screening candidate ground grids from the fan-shaped ring grids according to the spread degree of each point in the point cluster in the direction vertical to the ground comprises the following steps: and screening the candidate ground grids from the first grid set according to the spread degree of each point in the point cluster corresponding to each grid in the first grid set in the direction vertical to the ground.
3. The method of claim 1, wherein said screening candidate ground grids from said fanned annular grids based on the degree of spread of each point in said cluster of points in a direction perpendicular to the ground, comprises:
determining the curvature and normal vector of a curved surface which is formed by fitting each point in the point cluster according to the three-dimensional coordinates of each point in the point cluster; the curvature is used for representing the spread degree of each point in the point cluster in the direction vertical to the ground; the normal vector is used for representing the proximity degree of a curved surface and a plane which are synthesized by each point in the point cluster;
And screening the candidate ground grids from the fan-shaped annular grids according to the curvature and the normal vector.
4. A method of determining a travelable region as claimed in claim 3, wherein the screening the candidate ground grid from the sector-ring grid based on the curvature and the normal vector comprises:
determining the point cluster with the minimum curvature as a target point cluster, and determining a fan-shaped annular grid corresponding to the target point cluster as a target grid;
determining a normal angle difference according to the normal vector of the point cluster corresponding to other fan-ring grids in the fan-ring grid map and the normal vector of the target point cluster, and determining a second grid set from the fan-ring grids according to the normal angle difference;
and screening the candidate ground grids from the second grid set according to the curvature of the point cluster corresponding to each fan-shaped annular grid in the second grid set.
5. The method according to claim 1, wherein the step of screening the drivable ground grid from the candidate ground grids based on a distance between the candidate ground grid and a center point of the fan-shaped grid map and a height value of each point in a point cluster corresponding to the candidate ground grid in a direction perpendicular to the ground comprises:
Determining the local height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground according to the maximum height and the minimum height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground;
determining the gradient of the point cluster corresponding to the candidate ground grid relative to the ground according to the average height of each point in the point cluster corresponding to the candidate ground grid in the direction vertical to the ground and the distance between the center point of the candidate ground grid and the center point of the fan-shaped annular grid map;
and determining the candidate ground grids with the gradient belonging to a preset gradient range and the local height smaller than a second preset height as the drivable ground grids.
6. The method for determining a travelable area according to claim 1, wherein the partitioning of the point cloud data into point clusters is performed, and the partitioning result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map, and the method comprises:
determining a sector partition and an annular partition of each point in the point cloud data in the sector annular grid map based on coordinates of each point in the point cloud data in a first preset direction and a second preset direction; the first preset direction and the second preset direction are perpendicular to each other, and the first preset direction and the second preset direction are parallel to the ground;
And determining the fan-shaped annular grid to which each point in the point cloud data belongs in the fan-shaped annular grid map according to the fan-shaped partition and the annular partition, and determining the points belonging to the same fan-shaped annular grid as a point cluster.
7. The method of determining a travelable region according to claim 1, characterized in that the determining a travelable region from the travelable ground grid comprises:
if the third grid is determined to be the drivable ground grid according to at least two clusters of point cloud data, determining a region corresponding to the third grid as a drivable sub-region; the third grid is any grid in the fan-shaped annular grid map;
and superposing the drivable subareas to obtain the drivable area.
8. A determination device of a drivable area, characterized by comprising:
the division module is used for dividing the point cloud data into point clusters, and the division result is that each point cluster corresponds to one fan-ring grid in the fan-ring grid map;
the screening module is used for screening candidate ground grids from the fan-shaped ring grids according to the spread degree of each point in the point cluster divided by the dividing module in the direction vertical to the ground;
The screening module is further used for screening the ground grids capable of running from the candidate ground grids according to the distance between the candidate ground grids and the central point of the fan-shaped annular grid map and the height value of each point in the point cluster corresponding to the candidate ground grids in the direction vertical to the ground;
and the determining module is used for determining a drivable area according to the drivable ground grids screened by the screening module.
9. A device for determining a travelable region, comprising a memory, a processor, a bus and a communication interface; the memory is used for storing computer execution instructions, and the processor is connected with the memory through the bus;
when the determination means for a travelable region is operated, the processor executes the computer-executable instructions stored in the memory to cause the determination means for a travelable region to perform the determination method for a travelable region as claimed in any one of claims 1-7.
10. A computer-readable storage medium having instructions stored therein, which when executed by a computer, cause the computer to perform the method of determining a travelable region as claimed in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111360333.1A CN116136599A (en) | 2021-11-17 | 2021-11-17 | Determination method and device for drivable area and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111360333.1A CN116136599A (en) | 2021-11-17 | 2021-11-17 | Determination method and device for drivable area and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116136599A true CN116136599A (en) | 2023-05-19 |
Family
ID=86332550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111360333.1A Pending CN116136599A (en) | 2021-11-17 | 2021-11-17 | Determination method and device for drivable area and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116136599A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116520353A (en) * | 2023-06-29 | 2023-08-01 | 广汽埃安新能源汽车股份有限公司 | Ground detection method, device, storage medium and equipment based on laser point cloud |
-
2021
- 2021-11-17 CN CN202111360333.1A patent/CN116136599A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116520353A (en) * | 2023-06-29 | 2023-08-01 | 广汽埃安新能源汽车股份有限公司 | Ground detection method, device, storage medium and equipment based on laser point cloud |
| CN116520353B (en) * | 2023-06-29 | 2023-09-26 | 广汽埃安新能源汽车股份有限公司 | Ground detection method, device, storage medium and equipment based on laser point cloud |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7305884B2 (en) | LASER RADAR-BASED DETECTION METHOD, APPARATUS AND COMPUTER-READABLE STORAGE MEDIUM | |
| US9842417B2 (en) | Computing device and method for simplifying point cloud of object | |
| CN116129376A (en) | Road edge detection method and device | |
| CN109143207A (en) | Laser radar internal reference precision test method, apparatus, equipment and medium | |
| CN112907722A (en) | Building information model generation method, system, device and storage medium | |
| JP6381137B2 (en) | Label detection apparatus, method, and program | |
| CN105844631A (en) | Method and device for positioning object | |
| CN112862890B (en) | Road gradient prediction method, device and storage medium | |
| CN112070870B (en) | Point cloud map evaluation method and device, computer equipment and storage medium | |
| US11250175B2 (en) | Spatial-information generation apparatus, spatial-information generation method, and non-transitory computer readable medium | |
| CN112348836A (en) | Method and device for automatically extracting building outline | |
| CN114047487B (en) | Radar and vehicle body external parameter calibration method and device, electronic equipment and storage medium | |
| CN116136599A (en) | Determination method and device for drivable area and storage medium | |
| CN111553946A (en) | Method and device for removing ground point cloud and obstacle detection method and device | |
| CN110530375B (en) | Robot adaptive positioning method, positioning device, robot and storage medium | |
| WO2021056339A1 (en) | Positioning method and system, and movable platform | |
| CN113220018B (en) | Unmanned aerial vehicle path planning method and device, storage medium and electronic equipment | |
| CN113192174B (en) | Picture construction method and device and computer storage medium | |
| CN112418316B (en) | Robot repositioning method and device, laser robot and readable storage medium | |
| JP6874987B2 (en) | Feature shape extraction device, feature shape extraction method, and program | |
| CN115164880A (en) | Method, device, controller and movable equipment for identifying obstacle | |
| CN111982152B (en) | Point cloud map quantification method and device, computer equipment and storage medium | |
| EP3612979A1 (en) | Hardware accelerator for histogram of oriented gradients computation | |
| CN113436336A (en) | Ground point cloud segmentation method and device and automatic driving vehicle | |
| CN112258566A (en) | Pavement collection point identification method and device and server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |