CN118038027B - Point of interest detection method for flat transport vehicle - Google Patents

Abstract

The application provides a method for detecting interest points of a flat transport vehicle. The method comprises the following steps: and in the point cloud of the flat-bed transport vehicle, calculating the normal vector of each point to form a point cloud A with normal vector information. Based on these normal vectors, point cloud a is further divided into planar point cloud Plane and non-planar point cloud NPlane. The number of planes in the loading plate is determined by the Plane point cloud Plane. If the number of planes is one, in the point cloud a, a point cloud Edge1 at the Edge of the loading plate is identified and projected to the XY plane of the world coordinate system to form a point cloud ProjEdge1. And performing linear fitting on the point cloud ProjEdge1 according to the boundary line of the preset parking area to obtain a linear equation corresponding to the edges of the two sides and the tail end of the loading plate. In the non-planar point cloud NPlane, the straight line equation corresponding to the front end baffle of the load plate is identified. And finally, calculating the intersection points of the linear equations to obtain the interest point positions of the flat-bed transport vehicle. The method realizes the detection of the key point positions on the flat transport vehicle.

Description

Point of interest detection method for flat transport vehicle

Technical Field

The application relates to the technical field of flat transport vehicles. In particular, the application relates to a point of interest detection method for a flat transport vehicle.

Background

A flat-bed transport vehicle is a vehicle specially used for transporting goods, the body of which has no fence or enclosure, and only one flat bed is used for loading various goods with large size, irregular shape or ultra-long, such as long steel pipes, wood, construction materials, heavy machinery, etc.

When the robot carries the goods to the loading platform of the flat transport vehicle for loading operation, the robot needs to know the specific position where the goods are placed so as to ensure that the goods are placed at the correct position. The position where the cargo is placed can be determined by considering basic properties such as the size and shape of the cargo, and the position of the key points (e.g., corner points) of the flat transporter.

Therefore, how to detect and determine the key points on the flat transport vehicle is a technical problem to be solved urgently by those skilled in the art.

Disclosure of Invention

Based on the above, it is necessary to provide a method for detecting points of interest of a flat-panel transport vehicle.

In a first aspect, the present application provides a method for detecting points of interest of a flatbed transporter. The method comprises the following steps:

in the point cloud of the flat-plate transport vehicle, calculating the normal vector of each point to obtain a point cloud A with the normal vector;

screening Ping Miandian cloud Plane and non-planar point cloud NPlane from the point cloud A according to the normal vector of each point in the point cloud A;

Determining the number of planes in a loading plate of the flat-bed transport vehicle according to the Plane point cloud Plane;

If the number of planes in the loading plate is one, identifying a point cloud Edge1 at the Edge of the loading plate in the point cloud A;

Projecting the point cloud Edge1 to an XY plane of a world coordinate system to obtain a point cloud ProjEdge1; performing linear fitting on the point cloud ProjEdge1 according to a boundary line of a preset parking area to obtain a linear equation corresponding to the edges of the two sides of the loading plate and a linear equation corresponding to the edge of the tail end;

identifying a linear equation corresponding to a front end baffle of the loading plate in the non-planar point cloud NPlane;

And calculating the intersection point of the linear equation corresponding to the two side edges, the linear equation corresponding to the front end baffle and the linear equation corresponding to the tail end edge to obtain the interest point position of the flat-bed transport vehicle.

In one embodiment, the method further comprises:

If the number of planes in the loading plate is two, identifying a point cloud Edge1 at the Edge of the loading plate and a point cloud Edge2 at the high plane Edge of the loading plate in the point cloud A;

Projecting the point cloud Edge1 and the point cloud Edge2 to an XY plane of a world coordinate system to obtain a point cloud ProjEdge; performing linear fitting on the point cloud ProjEdge according to a boundary line of a preset parking area to obtain a linear equation corresponding to the edges of the two sides of the loading plate and a linear equation corresponding to the edge of the tail end;

identifying a linear equation corresponding to a front end baffle plate and a linear equation corresponding to a middle baffle plate of the loading plate in the non-planar point cloud NPlane; the front end baffle is positioned at the front end of the high plane of the loading flat plate, and the middle baffle is a baffle between the high plane and the low plane of the loading flat plate;

And calculating the intersection points of the linear equations of the two side edges, the linear equation corresponding to the front end baffle, the linear equation corresponding to the middle baffle and the linear equation corresponding to the tail end edge to obtain the interest point position of the flat-bed transport vehicle.

In one embodiment, determining the number of planes in the loading plate of the plate carrier vehicle according to the Plane point cloud Plane includes:

In the Plane point cloud Plane, calculating the distance from each point to the rear edge boundary line of the preset parking area on an XY Plane in a world coordinate system; based on the distance, ordering the points in the Plane point cloud Plane according to the order from small to large to obtain a point cloud B;

Selecting a preset percentage of points positioned in the front in the point cloud B to obtain a point cloud C; performing plane fitting on the point cloud C to obtain a plane equation F1;

In the point cloud a, calculating a distance absolute value L1 and a distance L2 between each point and the plane equation F1; screening points with the absolute value L1 of the distance smaller than a preset distance threshold value from the point cloud A to obtain a Plane point cloud Plane1; projecting the Ping Miandian cloud Plane1 to an XY Plane of a world coordinate system to obtain a point cloud ProjCloud1;

Calculating a concave polygon of the point cloud ProjCloud1, and determining points in the concave polygon as a point cloud Convex; clustering the point cloud Convex, and determining a point Cluster Cluster1 with the largest number of points; calculating the area S1 of the Cluster Cluster1;

In the Plane point cloud Plane, calculating a distance L3 between each point and the Plane equation F1; screening points with the distance L3 larger than the preset distance threshold value from the Plane point Cloud Plane to obtain a Plane point Cloud2;

Performing plane fitting on the plane point Cloud2 to obtain a plane equation F2; screening points meeting the Plane equation F2 from the Plane point Cloud Cloud2 to obtain Ping Miandian Cloud Plane2; projecting the Ping Miandian cloud Plane2 to an XY Plane of a world coordinate system to obtain a point cloud ProjCloud;

Calculating a concave polygon of the point cloud ProjCloud2, and determining points in the concave polygon as a point cloud Convex; clustering the point cloud Convex to determine a point Cluster Cluster2 with the largest number of points; calculating the area S2 of the Cluster Cluster2;

If the ratio of the area S2 to the area S1 is smaller than or equal to the preset ratio threshold, the number of planes in the loading plate is one; if the ratio of the area S2 to the area S1 is greater than a preset ratio threshold, the number of planes in the loading plate is two; wherein the two planes in the loading plate are a high plane and a low plane.

In one embodiment, identifying, in the point cloud a, a point cloud Edge1 at the loading plate Edge includes:

Screening points with the distance L2 being greater than the preset distance threshold and the distance L2 being smaller than 2 times of the preset distance threshold in the point cloud A to obtain a point cloud Edge1 at the Edge of the loading plate;

in the point cloud a, identifying a point cloud Edge2 at a high plane Edge of the loading plate, comprising:

In the point cloud a, calculating a distance absolute value LTop1 between each point and the plane equation F2;

And screening points of which the distance absolute value LTop is larger than the preset distance threshold and the distance absolute value LTop is smaller than 2 times of the preset distance threshold in the point cloud A, and obtaining a point cloud Edge2 at the high plane Edge of the loading plate.

In one embodiment, according to a boundary line of a preset parking area, performing straight line fitting on the point cloud ProjEdge to obtain a straight line equation corresponding to two side edges of the loading plate and a straight line equation corresponding to a tail end edge, where the straight line equation includes:

According to the boundary line of the preset parking area, calculating a directed bounding box of the point cloud ProjEdge; determining a reference vector V1 and a reference vector V2 according to the directed bounding box;

Performing linear fitting on the point cloud ProjEdge according to a preset first linear fitting condition to obtain a linear equation BaseLine and a linear equation BaseLine2; calculating a distance from a left end point of a rear boundary line of the preset parking area to the linear equation BaseLine and the linear equation BaseLine2; based on the distance, the linear equation BaseLine and the linear equation BaseLine2 are arranged in order from small to large to obtain a new linear equation BaseLine and a new linear equation BaseLine; the first linear fitting condition is that an included angle between a linear equation obtained by fitting and the reference vector V1 is smaller than a preset threshold value;

Determining the new linear equation BaseLine and the new linear equation BaseLine as linear equations corresponding to two side edges of the loading plate;

Performing linear fitting on the point cloud ProjEdge according to a preset second linear fitting condition to obtain a linear equation VLine1, a linear equation VLine2 and a linear equation VLine3; calculating the distance from the left end point of the rear boundary line of the preset parking area to the linear equation VLine1, the linear equation VLine2 and the linear equation VLine3; based on the distance, arranging the linear equation VLine1, the linear equation VLine2 and the linear equation VLine3 in order from small to large to obtain a new linear equation VLine1, a new linear equation VLine2 and a new linear equation VLine3; the second straight line fitting condition is that an included angle between a straight line equation obtained by fitting and the reference vector V2 is smaller than a preset threshold value;

and determining the new linear equation VLine3 as a linear equation corresponding to the tail end edge of the loading plate.

In one embodiment, in the non-planar point cloud NPlane, identifying a straight line equation corresponding to the front end baffle and a straight line equation corresponding to the middle baffle of the loading plate includes:

screening points higher than the Plane point cloud Plane2 in the non-Plane point cloud NPlane, wherein the distance between the points and the new linear equation VLine3 is smaller than a preset distance threshold value, and the included angle between the normal vector of the points and the reference vector V2 is smaller than a preset angle threshold value, so as to obtain a point cloud Baffle1 of the front end baffle of the loading plate;

Projecting the point cloud Baffle to an XY plane of a world coordinate system and performing linear fitting to obtain a linear equation corresponding to a front end baffle of the loading plate;

Screening points which are higher than the Plane point cloud Plane1 and lower than the Ping Miandian cloud Plane2 and in which the included angle between the normal vector of the points and the direction vector of the new linear equation BaseLine1 is smaller than a preset angle threshold value in the non-Plane point cloud NPlane to obtain a point cloud Baffle of the middle baffle of the loading plate;

And projecting the point cloud Baffle to an XY plane of a world coordinate system and performing linear fitting to obtain a linear equation corresponding to the middle baffle of the loading plate.

In one embodiment, according to a boundary line of a preset parking area, performing straight line fitting on the point cloud ProjEdge to obtain a straight line equation corresponding to two side edges of the loading plate and a straight line equation corresponding to a tail end edge, where the straight line fitting includes:

According to the boundary line of the preset parking area, calculating a directed bounding box of the point cloud ProjEdge 1; determining a reference vector VC1 and a reference vector VC2 according to the directed bounding box;

Performing linear fitting on the point cloud ProjEdge1 according to a preset third linear fitting condition to obtain a linear equation FBase and a linear equation FBase; the third linear fitting condition is that an included angle between a linear equation obtained by fitting and the reference vector VC1 is smaller than a preset threshold value;

Determining the linear equation FBase and the linear equation FBase2 as linear equations corresponding to two side edges of the loading plate;

Performing linear fitting on the point cloud ProjEdge1 according to a preset fourth linear fitting condition to obtain a linear equation FV1; the fourth straight line fitting condition is that an included angle between a straight line equation obtained by fitting and the reference vector VC2 is smaller than a preset threshold value, and the distance between the left end point of the rear boundary line of the preset parking area and the straight line equation obtained by fitting is minimum;

and determining the linear equation FV1 as a linear equation corresponding to the tail edge of the loading plate.

In one embodiment, in the non-planar point cloud NPlane, identifying a straight line equation corresponding to the front end baffle of the loading plate includes:

In the non-planar point cloud NPlane, calculating the distance between each point and the planar point cloud Plane 1; in the non-Ping Miandian cloud NPlane, according to the distance, screening points higher than the Plane point cloud Plane1 and having an included angle between a normal vector of the points and the reference vector VC1 smaller than a preset angle threshold value to obtain a point cloud BaffleFront of a front end baffle of the loading plate;

And performing linear fitting on the point cloud BaffleFront to obtain a linear equation corresponding to the front end baffle of the loading plate.

In one embodiment, in the point cloud a, screening Ping Miandian a cloud Plane and a non-planar point cloud NPlane from the point cloud a according to a normal vector of each point includes:

in the point cloud A, calculating an included angle between each point and a Z axis of a world coordinate system according to a normal vector of each point;

Screening points with the included angle smaller than a preset included angle threshold value from the point cloud A to obtain Ping Miandian cloud planes;

And screening points with the included angle larger than or equal to the preset included angle threshold value from the point cloud A to obtain a non-planar point cloud NPlane.

In one embodiment, the method further comprises:

in the process that the robot carries cargoes to a loading plate of the plate transport vehicle, three-dimensional point clouds are collected through radars on the robot, and the poses of the robot at different moments are calculated through a synchronous positioning and mapping method;

According to the poses of the different moments, the three-dimensional point clouds acquired at the different moments are spliced to obtain an environment map;

and in the environment map, dividing the three-dimensional point cloud positioned in the preset parking area to obtain the point cloud of the flat-panel transport vehicle.

According to the interest point detection method of the flat-panel transport vehicle, the normal vector of each point is calculated in the point cloud of the flat-panel transport vehicle, so that the point cloud A with normal vector information is formed. Based on these normal vectors, point cloud a is further divided into planar point cloud Plane and non-planar point cloud NPlane. The number of planes in the loading plate is determined by the Plane point cloud Plane. If the number of planes is one, in the point cloud a, a point cloud Edge1 at the Edge of the loading plate is identified and projected to the XY plane of the world coordinate system to form a point cloud ProjEdge1. And performing linear fitting on the point cloud ProjEdge1 according to the boundary line of the preset parking area to obtain a linear equation corresponding to the edges of the two sides and the tail end of the loading plate. Meanwhile, in the non-planar point cloud NPlane, a straight line equation corresponding to the front end baffle of the loading plate is identified. And finally, calculating the intersection points of the linear equations to obtain the interest point positions of the flat-bed transport vehicle. It can be understood that the method realizes the detection and determination of the key point positions on the flat transport vehicle, and further determines the positions where the cargoes need to be placed through the detected key point position information and the basic properties (size and shape) of the cargoes, thereby finally completing the whole loading operation.

Drawings

FIG. 1 is a flow chart of a method for detecting points of interest of a flatbed transport vehicle in one embodiment;

FIG. 2 is a schematic view of 6 corner points of a flatbed transport vehicle in one embodiment;

FIG. 3 is a schematic diagram of a three-dimensional point cloud obtained using parking area segmentation after flatbed transport vehicle modeling in one embodiment;

FIG. 4 is a diagram showing the effect of actual recognition of a flatbed transporter in one embodiment;

Fig. 5 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

In one embodiment, a method of point of interest detection for a flatbed transporter is provided. As shown in fig. 1, the method includes the following steps S101 to S105:

Step S101, in the point cloud of the flat-bed transport vehicle, calculating the normal vector of each point to obtain a point cloud A with the normal vector.

Specifically, in step S101, the normal vector of the point may be realized in various ways. As an example, in a point cloud of a flatbed transporter, for each point, the K nearest neighbor of the point is searched, and a plane is fitted based on the k+1 points, and a line passing through the point and perpendicular to the plane is taken as a normal vector of the point. Each point in the point cloud a additionally contains normal vector information of the surface on which the point cloud a is located, so that the new point cloud data set a can describe the geometric features and orientation information of the surface of the flat-bed transport vehicle more fully.

In step S102, in the point cloud a, the Ping Miandian cloud Plane and the non-planar point cloud NPlane are screened from the point cloud a according to the normal vector of each point.

Specifically, step S102 may be specifically realized by the following steps S1021 to S1022:

S1021, in the point cloud A, calculating an included angle theta between each point and the Z axis of the world coordinate system according to the normal vector of each point.

And S1022, screening points with an included angle theta smaller than a preset included angle threshold TRESANGLE from the point cloud A to obtain Ping Miandian cloud Plane.

S1023, screening points with an included angle theta greater than or equal to a preset included angle threshold TRESANGLE from the point cloud A to obtain a non-planar point cloud NPlane.

And step S103, determining the number of planes in the loading plate of the flat-bed transport vehicle according to Ping Miandian cloud planes.

Specifically, step S103 can be specifically realized by the following steps S1031 to S1038:

Step S1031, in the Plane point cloud Plane, calculating the distance between each point and the rear edge boundary line (for example, the straight line formed by the vertices A2 and A3 in fig. 2) of the preset parking area (for example, the rectangular area formed by the vertices A1, A2, A3 and A4 in fig. 2) on the XY Plane in the world coordinate system; based on the distance, the points in the Plane point cloud Plane are ordered in order from small to large, and point cloud B is obtained.

Step S1032, selecting a point with a preset percentage (for example, the first 50%) in the front of the point cloud B to obtain a point cloud C; and performing plane fitting on the point cloud C to obtain a plane equation F1. Optionally, the point cloud C is plane fitted by a random sample consensus (Random sample consensus, RANSAC) algorithm to obtain a plane equation F1.

Step S1033, in the point cloud a, calculating a distance absolute value L1 and a distance L2 between each point and the plane equation F1; screening points with the absolute value L1 of the distance smaller than a preset distance threshold value Thres1 from the point cloud A to obtain Ping Miandian cloud Plane1; the planar point cloud Plane1 is projected onto the XY Plane of the world coordinate system, resulting in the point cloud ProjCloud1.

Step S1034, calculating a concave polygon of the point cloud ProjCloud, and determining points in the concave polygon as the point cloud Convex1; european clustering is carried out on the point cloud Convex, and a point Cluster Cluster1 with the largest point number is determined; the area S1 of the Cluster1 is calculated.

Step S1035, in the Plane point cloud Plane, calculating a distance L3 between each point and the Plane equation F1; and screening points with the distance L3 larger than a preset distance threshold value Thres1 from the Plane point Cloud Plane to obtain Ping Miandian Cloud2.

Step S1036, performing plane fitting on the plane point Cloud2 through a RANSAC algorithm to obtain a plane equation F2; screening points meeting a Plane equation F2 from the Plane point Cloud Cloud2 to obtain Ping Miandian Cloud Plane2; and projecting the planar point cloud Plane2 to an XY Plane of a world coordinate system to obtain a point cloud ProjCloud2.

Step S1037, calculating a concave polygon of the point cloud ProjCloud, and determining points in the concave polygon as the point cloud Convex; european clustering is carried out on the point cloud Convex, and a point Cluster Cluster2 with the largest point number is determined; the area S2 of the Cluster2 is calculated.

Step S1038, if the ratio S2/S1 of the area S2 to the area S1 is smaller than or equal to the preset ratio threshold THRESRATE, the number of planes in the loading plate of the flat-bed transport vehicle is one; if the ratio S2/S1 of the area S2 to the area S1 is greater than the preset ratio threshold THRESRATE, the number of planes in the loading plate of the flat-bed transport vehicle is two; wherein, two planes in the loading plate are a high plane and a low plane, namely, the plate carrier is a high-low plate carrier.

In step S104, if the number of planes in the loading plate is one, then in the point cloud a, the point cloud Edge1 at the Edge of the loading plate is identified.

Specifically, step S104 may be specifically implemented by the following step S1041:

In step S1041, in the point cloud a, the points with the distance L2 greater than the preset distance threshold Thres1 and the distance L2 less than 2 times the preset distance threshold (2×thres1) are screened to obtain a point cloud Edge1 at the Edge of the loading plate.

Step S105, projecting the point cloud Edge1 to the XY plane of the world coordinate system to obtain a point cloud ProjEdge1; and (3) performing straight line fitting on the point cloud ProjEdge1 according to the boundary line of the preset parking area (for example, the boundary line of the rectangular area formed by the vertexes A1, A2, A3 and A4 in FIG. 2), so as to obtain a straight line equation corresponding to the two side edges of the loading plate and a straight line equation corresponding to the tail end edge.

Specifically, in step S105, "fitting a straight line to the point cloud ProjEdge1 according to the boundary line of the preset parking area, to obtain a straight line equation corresponding to the two side edges of the loading plate and a straight line equation corresponding to the tail end edge", the method can be specifically implemented by the following steps S1051 to S1055:

Step S1051, calculating a directed bounding box (Oriented Bounding Box, OBB) of the point cloud ProjEdge1 according to the boundary line of the preset parking area; from the directional bounding box, a reference vector VC1 and a reference vector VC2 are determined.

Step S1052, performing straight line fitting on the point cloud ProjEdge1 by using a RANSAC algorithm according to a preset third straight line fitting condition to obtain a straight line equation FBase and a straight line equation FBase; the third linear fitting condition is that an included angle between a linear equation obtained by fitting and the reference vector VC1 is smaller than a preset threshold value.

In step S1053, the linear equation FBase and the linear equation FBase2 are determined as the linear equations corresponding to the two side edges of the loading plate.

Step S1054, performing straight line fitting on the point cloud ProjEdge by using a RANSAC algorithm according to a preset fourth straight line fitting condition to obtain a straight line equation FV1; the fourth linear fitting condition is that an included angle between the linear equation obtained by fitting and the reference vector VC2 is smaller than a preset threshold, and a distance between a left end point (e.g., a vertex A2 in fig. 2) of a rear boundary line of the preset parking area and the linear equation obtained by fitting is minimum.

In step S1055, the straight line equation FV1 is determined as the straight line equation corresponding to the trailing edge of the loading plate.

In step S106, in the non-planar point cloud NPlane, a straight line equation corresponding to the front end baffle of the loading plate is identified.

Specifically, step S106 can be specifically realized by the following steps S1061 to S1062:

step S1061, in the non-planar point cloud NPlane, calculating the distance between each point and the planar point cloud Plane 1; in the non-planar point cloud NPlane, according to the distance, the point cloud BaffleFront of the front end baffle of the loading plate is obtained by screening the point which is higher than the planar point cloud Plane1 and has an included angle between the normal vector of the point and the reference vector VC1 smaller than a preset angle threshold.

In step S1062, the point cloud BaffleFront is linearly fitted by the RANSAC algorithm to obtain a linear equation BaffFrontFunc corresponding to the front end baffle of the loading plate.

Step S107, calculating the intersection points of the straight line equations FBase, FBase2 corresponding to the edges on both sides, the straight line equation BaffFrontFunc corresponding to the front end baffle and the straight line equation FV1 corresponding to the tail end edge, to obtain the x and y coordinates of 4 interest points (such as the corner points 1, 3, 4 and 6 in FIG. 2) of the flat-panel transporter; and projecting the 4 interest points onto a Plane corresponding to the Plane point cloud Plane1 to obtain z coordinates of the 4 interest points.

In one embodiment, the method further comprises the following step S111-step S114:

in step S111, if the number of planes in the loading plate is two, in the point cloud a, the point cloud Edge1 at the Edge of the loading plate and the point cloud Edge2 at the Edge of the high plane of the loading plate are identified.

Specifically, "in the point cloud a, the point cloud Edge2 at the high plane Edge of the loading plate is identified" in step S111, specifically may be implemented by the following steps S1111 to S1112:

In step S1111, in the point cloud a, the absolute value LTop1 of the distance between each point and the plane equation F2 is calculated.

In step S1112, in the point cloud a, the points with the distance absolute value LTop1 greater than the preset distance threshold Thres1 and the distance absolute value LTop less than 2 times the preset distance threshold (2×thres1) are screened to obtain the point cloud Edge2 at the high plane Edge of the loading plate.

Step S112, projecting the point cloud Edge1 and the point cloud Edge2 to an XY plane of a world coordinate system to obtain a point cloud ProjEdge; and performing linear fitting on the point cloud ProjEdge according to the boundary line of the preset parking area to obtain a linear equation corresponding to the edges of the two sides of the loading plate and a linear equation corresponding to the edge of the tail end.

Specifically, in step S112, "fitting a straight line to the point cloud ProjEdge according to the boundary line of the preset parking area, to obtain a straight line equation corresponding to the two side edges of the loading plate and a straight line equation corresponding to the tail end edge", the method can be specifically implemented by the following steps S1121-S1125:

Step S1121, calculating a directed bounding box of the point cloud ProjEdge according to a boundary line of a preset parking area; from the directional bounding box, a reference vector V1 and a reference vector V2 are determined.

Step S1122, performing straight line fitting on the point cloud ProjEdge by using a RANSAC algorithm according to a preset first straight line fitting condition to obtain a straight line equation BaseLine and a straight line equation BaseLine; calculating a distance between a left end point (e.g., a vertex A2 in fig. 2) of a rear boundary line of the preset parking area to the linear equation BaseLine and the linear equation BaseLine; based on the distance, the linear equation BaseLine and the linear equation BaseLine2 are arranged in order from small to large to obtain a new linear equation BaseLine and a new linear equation BaseLine; the first linear fitting condition is that an included angle between a linear equation obtained by fitting and the reference vector V1 is smaller than a preset threshold value.

In step S1123, a new linear equation BaseLine and a new linear equation BaseLine are determined as linear equations corresponding to both side edges of the loading plate.

Step S1124, performing straight line fitting on the point cloud ProjEdge by using a RANSAC algorithm according to a preset second straight line fitting condition to obtain a straight line equation VLine1, a straight line equation VLine2 and a straight line equation VLine3; calculating the distance between the left end point (e.g., the vertex A2 in fig. 2) of the rear boundary line of the preset parking area to the straight line equation VLine1, the straight line equation VLine2 and the straight line equation VLine3; based on the distance, arranging the linear equation VLine1, the linear equation VLine2 and the linear equation VLine3 in order from small to large to obtain a new linear equation VLine1, a new linear equation VLine2 and a new linear equation VLine3; the second straight line fitting condition is that an included angle between a straight line equation obtained by fitting and the reference vector V2 is smaller than a preset threshold value.

In step S1125, a new linear equation VLine3 is determined as a linear equation corresponding to the trailing edge of the loading plate.

Step S113, in the non-planar point cloud NPlane, identifying a linear equation corresponding to a front end baffle plate of the loading plate and a linear equation corresponding to a middle baffle plate; the front end baffle is positioned at the front end of the high plane of the loading plate, and the middle baffle is a baffle between the high plane and the low plane of the loading plate.

Specifically, step S113 may be specifically implemented by the following steps S1131 to S1134:

In step S1131, in the non-planar point cloud NPlane, the point cloud Baffle of the front end baffle of the loading plate is obtained by screening the points higher than the planar point cloud Plane2, the distance between the point and the new linear equation VLine3 is smaller than the preset distance threshold, and the included angle between the normal vector of the point and the reference vector V2 is smaller than the preset angle threshold.

In step S1132, the point cloud Baffle is projected onto the XY plane of the world coordinate system and is fitted with a straight line, so as to obtain a straight line equation BaffleFunc corresponding to the front end baffle of the loading plate.

Step S1133, in the non-planar point cloud NPlane, screening the points higher than the planar point cloud Plane1 and lower than the planar point cloud Plane2, and the included angle between the normal vector of the point and the direction vector of the new linear equation BaseLine1 is smaller than the preset angle threshold value, to obtain a point cloud Baffle of the middle baffle plate of the loading plate;

In step S1134, the point cloud Baffle is projected onto the XY plane of the world coordinate system and is fitted with a straight line, so as to obtain a straight line equation BaffleFunc corresponding to the middle baffle of the loading plate.

Step S114, calculating the intersection points of the linear equations BaseLine, baseLine2 at the two side edges with the linear equation BaffleFunc corresponding to the front end baffle, the linear equation BaffleFunc corresponding to the middle baffle, and the linear equation VLine3 corresponding to the tail end edge, to obtain the x and y coordinates of 6 interest points (e.g., the corner points 1,2,3,4, 5, and 6 in fig. 2) of the flatbed transporter; and projecting the 6 interest points onto a Plane corresponding to the Plane point cloud Plane1 and a Plane corresponding to the Plane2 to obtain z coordinates of the 6 interest points.

According to the interest point detection method of the flat-panel transport vehicle, the normal vector of each point is calculated in the point cloud of the flat-panel transport vehicle, so that the point cloud A with normal vector information is formed. Based on these normal vectors, point cloud a is further divided into planar point cloud Plane and non-planar point cloud NPlane. The number of planes in the loading plate is determined by the Plane point cloud Plane. If the number of planes is one, in the point cloud a, a point cloud Edge1 at the Edge of the loading plate is identified and projected to the XY plane of the world coordinate system to form a point cloud ProjEdge1. And performing linear fitting on the point cloud ProjEdge1 according to the boundary line of the preset parking area to obtain a linear equation corresponding to the edges of the two sides and the tail end of the loading plate. Meanwhile, in the non-planar point cloud NPlane, a straight line equation corresponding to the front end baffle of the loading plate is identified. And finally, calculating the intersection points of the linear equations to obtain the interest point positions of the flat-bed transport vehicle. It can be understood that the method realizes the detection and determination of the key point positions on the flat transport vehicle, and further determines the positions where the cargoes need to be placed through the detected key point position information and the basic properties (size and shape) of the cargoes, thereby finally completing the whole loading operation.

In one embodiment, one implementation involves reconstruction of a point cloud of a flatbed transporter. On the basis of the above embodiment, the process includes the following steps S121 to S123:

Step S121, collecting three-dimensional point clouds through radars on the robot in the process that the robot carries cargoes onto a loading plate of a plate transport vehicle, and calculating the poses of the robot at different moments through a synchronous positioning and mapping method;

step S122, according to the poses of different moments, the three-dimensional point clouds acquired at different moments are spliced to obtain an environment map;

Step S123, in the environment map, dividing the three-dimensional point cloud positioned in the preset parking area to obtain the point cloud of the flat-panel transport vehicle.

Specifically, first, the robot navigates to the navigation point of the first task. Next, the current coordinates and gestures of the robot in the world coordinate system are assigned to a synchronous positioning and mapping (slam) module as modeling initial values. Next, the laser slam module is started to begin collecting radar data. And then, the robot runs to the navigation point of the next task, the pose in a world coordinate system is calculated when the robot is at each position at different moments through a slam technology, so that each frame point cloud at the corresponding moment is spliced, and the three-dimensional (3D) point cloud reconstruction of the robot to the environment is completed when the navigation point of the next task is reached. Finally, according to the fixed parking area, the point cloud data belonging to the flat-bed transport vehicle is segmented, and three-dimensional (3D) reconstruction of the flat-bed transport vehicle is completed, as shown in FIG. 3.

In this embodiment, the laser slam technology is utilized, and in the running process of the robot, the point cloud data of the robot at different positions are continuously accumulated and spliced, so as to complete the three-dimensional point cloud reconstruction of the flat-panel transport vehicle. Compared with a 3D reconstruction scheme formed by using structured light and a camera in a large scene, the embodiment does not need to build an expensive structured light reconstruction system, can save cost, and is suitable for being used in scenes with low precision requirements.

In one embodiment, another implementation process involves reconstruction of the point cloud of the flatbed transporter. On the basis of the above embodiment, the process includes the following steps S131 to S137:

step S131, the robot navigates to the navigation point of the first task.

Step S132, collecting data of the lidar is started.

Step S133, the robot runs to the navigation point of the second task.

Step S134, acquiring the pose T of the robot in the world coordinate system during running, and converting the laser radar point cloud of the current frame from the robot coordinate system to the world coordinate system.

Step S135, optimizing the pose T by comparing the current frame Lei Dadian cloud information with the historical radar point cloud information and using GICP, NDT, ICP equal point cloud registration algorithm.

And step S136, splicing data of radars of different frames in a world coordinate system by using the optimized pose, and completing three-dimensional point cloud mapping of the scene.

And step S137, dividing the point cloud by using the fixed parking area to obtain three-dimensional point cloud data of the flat-bed transport vehicle.

In the embodiment, by means of a high-precision positioning technology, positioning data of the robot under world coordinate systems of different positions are utilized in the running process of the robot, and point cloud data of each frame are spliced to achieve three-dimensional point cloud reconstruction of the flat transport vehicle. Compared with the traditional 3D reconstruction scheme based on the structured light and camera composition, the embodiment does not need to build an expensive structured light reconstruction system, so that the cost is remarkably reduced, and the method has the advantage of being more economical and efficient particularly when processing large scenes.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a point of interest detection device of the flat-panel transport vehicle for realizing the point of interest detection method of the flat-panel transport vehicle. The implementation scheme of the solution to the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitation in the embodiment of the interest point detection device of the flat-panel transport vehicle can be referred to the limitation of the interest point detection method of the flat-panel transport vehicle hereinabove, and the description thereof is omitted here.

It should be noted that, when the point of interest detection device of the flat transport vehicle realizes the corresponding functions, the function allocation can be completed by different functional modules according to the needs, that is, the internal structure of the device is divided into different functional modules so as to complete all or part of the functions. In addition, the point of interest detection device of the flat-panel transport vehicle provided in the above embodiment belongs to the same concept as the point of interest detection method embodiment of the flat-panel transport vehicle, and the specific implementation process is detailed in the method embodiment, and will not be described herein.

According to one aspect of the application, the embodiment of the application also provides a computer program product comprising a computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through a communication section. When the computer program is executed by the processor, the interest point detection method of the flat-panel transport vehicle provided by the embodiment of the application is executed.

In addition, the embodiment of the invention also provides a computer device, which comprises a processor and a memory, wherein the memory stores a computer program, the processor can execute the computer program stored in the memory, and when the computer program is executed by the processor, the method for detecting the interest point of the flat-panel transport vehicle provided by any embodiment can be realized.

For example, FIG. 5 illustrates a computer device provided by an embodiment of the invention, the device comprising a bus 1110, a processor 1120, a transceiver 1130, a bus interface 1140, a memory 1150, and a user interface 1160.

In an embodiment of the present invention, the apparatus further includes: computer programs stored on the memory 1150 and executable on the processor 1120, which when executed by the processor 1120, implement the various processes of the point of interest detection method embodiments of the flatbed transport vehicle described above.

A transceiver 1130 for receiving and transmitting data under the control of the processor 1120.

In an embodiment of the invention, represented by bus 1110, bus 1110 may include any number of interconnected buses and bridges, with bus 1110 connecting various circuits, including one or more processors, represented by processor 1120, and memory, represented by memory 1150.

Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and a memory controller, a peripheral bus, an accelerated graphics Port (ACCELERATE GRAPHICAL Port, AGP), a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such an architecture includes: industry standard architecture (Industry Standard Architecture, ISA) bus, micro channel architecture (Micro Channel Architecture, MCA) bus, enhanced ISA (ENHANCED ISA, EISA) bus, video electronics standards association (Video Electronics Standards Association, VESA), peripheral component interconnect (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus.

Processor 1120 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments may be implemented by instructions in the form of integrated logic circuits in hardware or software in a processor. The processor includes: general purpose processors, central processing units (Central Processing Unit, CPU), network processors (Network Processor, NP), digital signal processors (DIGITAL SIGNAL processors, DSP), application specific integrated circuits (Application SPECIFIC INTEGRATED circuits, ASIC), field programmable gate arrays (Field Programmable GATE ARRAY, FPGA), complex programmable logic devices (Complex Programmable Logic Device, CPLD), programmable logic arrays (Programmable Logic Array, PLA), micro control units (Microcontroller Unit, MCU) or other programmable logic devices, discrete gates, transistor logic devices, discrete hardware components. The methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. For example, the processor may be a single-core processor or a multi-core processor, and the processor may be integrated on a single chip or located on multiple different chips.

The processor 1120 may be a microprocessor or any conventional processor. The steps of the method disclosed in connection with the embodiments of the present invention may be performed directly by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules may be located in a random access Memory (Random Access Memory, RAM), flash Memory (Flash Memory), read-Only Memory (ROM), programmable ROM (PROM), erasable Programmable ROM (EPROM), registers, and so forth, as are known in the art. The readable storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

Bus 1110 may also connect together various other circuits such as peripheral devices, voltage regulators, or power management circuits, bus interface 1140 providing an interface between bus 1110 and transceiver 1130, all of which are well known in the art. Accordingly, the embodiments of the present invention will not be further described.

The transceiver 1130 may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. For example: the transceiver 1130 receives external data from other devices, and the transceiver 1130 is configured to transmit the data processed by the processor 1120 to the other devices. Depending on the nature of the computer system, a user interface 1160 may also be provided, for example: touch screen, physical keyboard, display, mouse, speaker, microphone, trackball, joystick, stylus.

It should be appreciated that in embodiments of the present invention, the memory 1150 may further comprise memory located remotely from the processor 1120, such remotely located memory being connectable to a server through a network. One or more portions of the above-described networks may be an ad hoc network (ad hoc network), an intranet, an extranet (extranet), a Virtual Private Network (VPN), a Local Area Network (LAN), a Wireless Local Area Network (WLAN), a Wide Area Network (WAN), a Wireless Wide Area Network (WWAN), a Metropolitan Area Network (MAN), the Internet (Internet), a Public Switched Telephone Network (PSTN), a plain old telephone service network (POTS), a cellular telephone network, a wireless fidelity (Wi-Fi) network, and a combination of two or more of the above-described networks. For example, the cellular telephone network and wireless network may be a global system for mobile communications (GSM) system, code Division Multiple Access (CDMA) system, worldwide Interoperability for Microwave Access (WiMAX) system, general Packet Radio Service (GPRS) system, wideband Code Division Multiple Access (WCDMA) system, long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, long term evolution-advanced (LTE-a) system, universal Mobile Telecommunications (UMTS) system, enhanced mobile broadband (Enhance Mobile Broadband, eMBB) system, mass machine class Communication (MASSIVE MACHINE TYPE of Communication, mMTC) system, ultra-reliable low latency Communication (Ultra Reliable Low Latency Communications, uRLLC) system, and the like.

It should be appreciated that the memory 1150 in embodiments of the present invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. Wherein the nonvolatile memory includes: read-Only Memory (ROM), programmable ROM (PROM), erasable Programmable EPROM (EPROM), electrically Erasable EPROM (EEPROM), or Flash Memory (Flash Memory).

The volatile memory includes: random access memory (Random Access Memory, RAM) that serves as an external cache. By way of example, and not limitation, many forms of RAM are available, such as: static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate Synchronous dynamic random access memory (Double DATA RATE SDRAM, DDRSDRAM), enhanced Synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM) and Direct memory bus random access memory (DRRAM). Memory 1150 described in embodiments of the present invention includes, but is not limited to, the above and any other suitable types of memory.

In an embodiment of the invention, memory 1150 stores the following elements of operating system 1151 and application programs 1152: an executable module, a data structure, or a subset thereof, or an extended set thereof.

Specifically, the operating system 1151 includes various system programs, such as: a framework layer, a core library layer, a driving layer and the like, which are used for realizing various basic services and processing tasks based on hardware. The applications 1152 include various applications such as: a media player (MEDIA PLAYER), a Browser (Browser) for implementing various application services. A program for implementing the method of the embodiment of the present invention may be included in the application 1152. The application 1152 includes: applets, objects, components, logic, data structures, and other computer system executable instructions that perform particular tasks or implement particular abstract data types.

In addition, the embodiment of the invention further provides a computer readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the processes of the embodiment of the method for detecting the interest point of the flat transport vehicle are realized, and the same technical effects can be achieved, so that repetition is avoided, and the description is omitted here.

The computer-readable storage medium includes: persistent and non-persistent, removable and non-removable media are tangible devices that may retain and store instructions for use by an instruction execution device. The computer-readable storage medium includes: electronic storage, magnetic storage, optical storage, electromagnetic storage, semiconductor storage, and any suitable combination of the foregoing. The computer-readable storage medium includes: phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), non-volatile random access memory (NVRAM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassette storage, magnetic tape disk storage or other magnetic storage devices, memory sticks, mechanical coding (e.g., punch cards or bump structures in grooves with instructions recorded thereon), or any other non-transmission medium that may be used to store information that may be accessed by a computing device. In accordance with the definition in the present embodiments, the computer-readable storage medium does not include a transitory signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a pulse of light passing through a fiber optic cable), or an electrical signal transmitted through a wire.

In the description of the embodiments of the present invention, those skilled in the art should appreciate that the embodiments of the present invention may be implemented as a method, an apparatus, a device, and a storage medium. Thus, embodiments of the present invention may be embodied in the following forms: complete hardware, complete software (including firmware, resident software, micro-code, etc.), a combination of hardware and software. Furthermore, in some embodiments, embodiments of the invention may also be implemented in the form of a computer program product in one or more computer-readable storage media having computer program code embodied therein.

Any combination of one or more computer-readable storage media may be employed by the computer-readable storage media described above. The computer-readable storage medium includes: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer readable storage medium include the following: portable computer diskette, hard disk, random Access Memory (RAM), read-only Memory (ROM), erasable programmable read-only Memory (EPROM), flash Memory (Flash Memory), optical fiber, compact disc read-only Memory (CD-ROM), optical storage device, magnetic storage device, or any combination thereof. In embodiments of the present invention, 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, device.

The computer program code embodied in the computer readable storage medium may be transmitted using any appropriate medium, including: wireless, wire, fiber optic cable, radio Frequency (RF), or any suitable combination thereof.

Computer program code for carrying out operations of embodiments of the present invention may be written in assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or in one or more programming languages, including an object oriented programming language such as: java, smalltalk, C ++, also include conventional procedural programming languages, such as: c language or similar programming language. The computer program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer and entirely on the remote computer or server. In the case of remote computers, the remote computers may be connected via any sort of network, including: a Local Area Network (LAN) or a Wide Area Network (WAN), which may be connected to the user's computer or to an external computer.

It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

These computer readable program instructions may also be stored in a computer readable storage medium that can cause a computer or other programmable data processing apparatus to function in a particular manner. Thus, instructions stored in a computer-readable storage medium produce an instruction means which implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

The foregoing is merely a specific implementation of the embodiment of the present invention, but the protection area of the embodiment of the present invention is not limited thereto, and any person skilled in the art can easily think of changes or substitutions within the technical area disclosed in the embodiment of the present invention, and the changes or substitutions are covered in the protection area of the embodiment of the present invention. Therefore, the protection area of the embodiments of the present invention shall be subject to the protection area of the claims.

Claims (10)

1. A method for detecting points of interest of a flatbed transporter, the method comprising:

in the point cloud of the flat-plate transport vehicle, calculating the normal vector of each point to obtain a point cloud A with the normal vector;

screening Ping Miandian cloud Plane and non-planar point cloud NPlane from the point cloud A according to the normal vector of each point in the point cloud A;

Determining the number of planes in a loading plate of the flat-bed transport vehicle according to the Plane point cloud Plane;

If the number of planes in the loading plate is one, identifying a point cloud Edge1 at the Edge of the loading plate in the point cloud A;

Projecting the point cloud Edge1 to an XY plane of a world coordinate system to obtain a point cloud ProjEdge1; performing linear fitting on the point cloud ProjEdge1 according to a boundary line of a preset parking area to obtain a linear equation corresponding to the edges of the two sides of the loading plate and a linear equation corresponding to the edge of the tail end;

identifying a linear equation corresponding to a front end baffle of the loading plate in the non-planar point cloud NPlane;

And calculating the intersection point of the linear equation corresponding to the two side edges, the linear equation corresponding to the front end baffle and the linear equation corresponding to the tail end edge to obtain the interest point position of the flat-bed transport vehicle.

2. The method according to claim 1, wherein the method further comprises:

If the number of planes in the loading plate is two, identifying a point cloud Edge1 at the Edge of the loading plate and a point cloud Edge2 at the high plane Edge of the loading plate in the point cloud A;

Projecting the point cloud Edge1 and the point cloud Edge2 to an XY plane of a world coordinate system to obtain a point cloud ProjEdge; performing linear fitting on the point cloud ProjEdge according to a boundary line of a preset parking area to obtain a linear equation corresponding to the edges of the two sides of the loading plate and a linear equation corresponding to the edge of the tail end;

identifying a linear equation corresponding to a front end baffle plate and a linear equation corresponding to a middle baffle plate of the loading plate in the non-planar point cloud NPlane; the front end baffle is positioned at the front end of the high plane of the loading flat plate, and the middle baffle is a baffle between the high plane and the low plane of the loading flat plate;

And calculating the intersection points of the linear equations of the two side edges, the linear equation corresponding to the front end baffle, the linear equation corresponding to the middle baffle and the linear equation corresponding to the tail end edge to obtain the interest point position of the flat-bed transport vehicle.

3. The method of claim 2, wherein determining the number of planes in the loading plate of the flatbed transporter from the planar point cloud Plane comprises:

In the Plane point cloud Plane, calculating the distance from each point to the rear edge boundary line of the preset parking area on an XY Plane in a world coordinate system; based on the distance, ordering the points in the Plane point cloud Plane according to the order from small to large to obtain a point cloud B;

Selecting a preset percentage of points positioned in the front in the point cloud B to obtain a point cloud C; performing plane fitting on the point cloud C to obtain a plane equation F1;

In the point cloud a, calculating a distance absolute value L1 and a distance L2 between each point and the plane equation F1; screening points with the absolute value L1 of the distance smaller than a preset distance threshold value from the point cloud A to obtain a Plane point cloud Plane1; projecting the Ping Miandian cloud Plane1 to an XY Plane of a world coordinate system to obtain a point cloud ProjCloud1;

Calculating a concave polygon of the point cloud ProjCloud1, and determining points in the concave polygon as a point cloud Convex; clustering the point cloud Convex, and determining a point Cluster Cluster1 with the largest number of points; calculating the area S1 of the Cluster Cluster1;

In the Plane point cloud Plane, calculating a distance L3 between each point and the Plane equation F1; screening points with the distance L3 larger than the preset distance threshold value from the Plane point Cloud Plane to obtain a Plane point Cloud2;

Performing plane fitting on the plane point Cloud2 to obtain a plane equation F2; screening points meeting the Plane equation F2 from the Plane point Cloud Cloud2 to obtain Ping Miandian Cloud Plane2; projecting the Ping Miandian cloud Plane2 to an XY Plane of a world coordinate system to obtain a point cloud ProjCloud;

Calculating a concave polygon of the point cloud ProjCloud2, and determining points in the concave polygon as a point cloud Convex; clustering the point cloud Convex to determine a point Cluster Cluster2 with the largest number of points; calculating the area S2 of the Cluster Cluster2;

If the ratio of the area S2 to the area S1 is smaller than or equal to a preset ratio threshold, the number of planes in the loading plate is one; if the ratio of the area S2 to the area S1 is greater than the preset ratio threshold, the number of planes in the loading plate is two; wherein the two planes in the loading plate are a high plane and a low plane.

4. The method of claim 3, wherein identifying, in the point cloud a, a point cloud Edge1 at the loading plate Edge comprises:

Screening points with the distance L2 being greater than the preset distance threshold and the distance L2 being smaller than 2 times of the preset distance threshold in the point cloud A to obtain a point cloud Edge1 at the Edge of the loading plate;

in the point cloud a, identifying a point cloud Edge2 at a high plane Edge of the loading plate, comprising:

In the point cloud a, calculating a distance absolute value LTop1 between each point and the plane equation F2;

And screening points of which the distance absolute value LTop is larger than the preset distance threshold and the distance absolute value LTop is smaller than 2 times of the preset distance threshold in the point cloud A, and obtaining a point cloud Edge2 at the high plane Edge of the loading plate.

5. The method of claim 4, wherein performing straight line fitting on the point cloud ProjEdge according to a boundary line of a preset parking area to obtain a straight line equation corresponding to two side edges and a straight line equation corresponding to a tail end edge of the loading plate, includes:

According to the boundary line of the preset parking area, calculating a directed bounding box of the point cloud ProjEdge; determining a reference vector V1 and a reference vector V2 according to the directed bounding box;

Performing linear fitting on the point cloud ProjEdge according to a preset first linear fitting condition to obtain a linear equation BaseLine and a linear equation BaseLine2; calculating a distance from a left end point of a rear boundary line of the preset parking area to the linear equation BaseLine and the linear equation BaseLine2; based on the distance, the linear equation BaseLine and the linear equation BaseLine2 are arranged in order from small to large to obtain a new linear equation BaseLine and a new linear equation BaseLine; the first linear fitting condition is that an included angle between a linear equation obtained by fitting and the reference vector V1 is smaller than a preset threshold value;

Determining the new linear equation BaseLine and the new linear equation BaseLine as linear equations corresponding to two side edges of the loading plate;

Performing linear fitting on the point cloud ProjEdge according to a preset second linear fitting condition to obtain a linear equation VLine1, a linear equation VLine2 and a linear equation VLine3; calculating the distance from the left end point of the rear boundary line of the preset parking area to the linear equation VLine1, the linear equation VLine2 and the linear equation VLine3; based on the distance, arranging the linear equation VLine1, the linear equation VLine2 and the linear equation VLine3 in order from small to large to obtain a new linear equation VLine1, a new linear equation VLine2 and a new linear equation VLine3; the second straight line fitting condition is that an included angle between a straight line equation obtained by fitting and the reference vector V2 is smaller than a preset threshold value;

and determining the new linear equation VLine3 as a linear equation corresponding to the tail end edge of the loading plate.

6. The method of claim 5, wherein identifying, in the non-planar point cloud NPlane, a straight line equation corresponding to a front end baffle and a straight line equation corresponding to a middle baffle of the load plate comprises:

screening points higher than the Plane point cloud Plane2 in the non-Plane point cloud NPlane, wherein the distance between the points and the new linear equation VLine3 is smaller than a preset distance threshold value, and the included angle between the normal vector of the points and the reference vector V2 is smaller than a preset angle threshold value, so as to obtain a point cloud Baffle1 of the front end baffle of the loading plate;

Projecting the point cloud Baffle to an XY plane of a world coordinate system and performing linear fitting to obtain a linear equation corresponding to a front end baffle of the loading plate;

Screening points which are higher than the Plane point cloud Plane1 and lower than the Ping Miandian cloud Plane2 and in which the included angle between the normal vector of the points and the direction vector of the new linear equation BaseLine1 is smaller than a preset angle threshold value in the non-Plane point cloud NPlane to obtain a point cloud Baffle of the middle baffle of the loading plate;

And projecting the point cloud Baffle to an XY plane of a world coordinate system and performing linear fitting to obtain a linear equation corresponding to the middle baffle of the loading plate.

7. The method according to claim 3, wherein performing straight line fitting on the point cloud ProjEdge according to a boundary line of a preset parking area to obtain a straight line equation corresponding to two side edges and a straight line equation corresponding to a tail end edge of the loading plate includes:

According to the boundary line of the preset parking area, calculating a directed bounding box of the point cloud ProjEdge 1; determining a reference vector VC1 and a reference vector VC2 according to the directed bounding box;

Performing linear fitting on the point cloud ProjEdge1 according to a preset third linear fitting condition to obtain a linear equation FBase and a linear equation FBase; the third linear fitting condition is that an included angle between a linear equation obtained by fitting and the reference vector VC1 is smaller than a preset threshold value;

Determining the linear equation FBase and the linear equation FBase2 as linear equations corresponding to two side edges of the loading plate;

Performing linear fitting on the point cloud ProjEdge1 according to a preset fourth linear fitting condition to obtain a linear equation FV1; the fourth straight line fitting condition is that an included angle between a straight line equation obtained by fitting and the reference vector VC2 is smaller than a preset threshold value, and the distance between the left end point of the rear boundary line of the preset parking area and the straight line equation obtained by fitting is minimum;

and determining the linear equation FV1 as a linear equation corresponding to the tail edge of the loading plate.

8. The method of claim 7, wherein identifying, in the non-planar point cloud NPlane, a straight line equation corresponding to a front end baffle of the load plate comprises:

In the non-planar point cloud NPlane, calculating the distance between each point and the planar point cloud Plane 1; in the non-Ping Miandian cloud NPlane, according to the distance, screening points higher than the Plane point cloud Plane1 and having an included angle between a normal vector of the points and the reference vector VC1 smaller than a preset angle threshold value to obtain a point cloud BaffleFront of a front end baffle of the loading plate;

And performing linear fitting on the point cloud BaffleFront to obtain a linear equation corresponding to the front end baffle of the loading plate.

9. The method of claim 1, wherein in the point cloud a, screening Ping Miandian a cloud Plane and a non-planar point cloud NPlane from the point cloud a according to a normal vector of each point, comprises:

in the point cloud A, calculating an included angle between each point and a Z axis of a world coordinate system according to a normal vector of each point;

Screening points with the included angle smaller than a preset included angle threshold value from the point cloud A to obtain Ping Miandian cloud planes;

And screening points with the included angle larger than or equal to the preset included angle threshold value from the point cloud A to obtain a non-planar point cloud NPlane.

10. The method according to claim 1, wherein the method further comprises:

in the process that the robot carries cargoes to a loading plate of the plate transport vehicle, three-dimensional point clouds are collected through radars on the robot, and the poses of the robot at different moments are calculated through a synchronous positioning and mapping method;

According to the poses of the different moments, the three-dimensional point clouds acquired at the different moments are spliced to obtain an environment map;

and in the environment map, dividing the three-dimensional point cloud positioned in the preset parking area to obtain the point cloud of the flat-panel transport vehicle.