Cargo information identification method and device, computer device and storage medium

Abstract

The application relates to a cargo information recognition method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a point cloud data set, the point cloud data set being obtained by collecting a target region by a collection device; determining a cross-section parameter of a target cargo in the target region according to the point cloud data set, the target cargo being cylindrical, and the cross-section parameter comprising a cross-sectional dimension of the cross section of the target cargo; determining pose information of the target cargo based on the cross-section parameter and a forklift arm parameter of each forklift arm, the pose information being used for representing a position of the target cargo and an attitude of the target cargo. The method can determine the position and the attitude of the cylindrical target cargo.

Description

Technical Field

[0001] This application relates to the field of forklift technology, and in particular to a method, apparatus, computer equipment, and storage medium for cargo information identification. Background Technology

[0002] With the development of forklift technology, forklift sensing technology has emerged. Forklift sensing technology refers to the use of sensors at the fork ends of forklifts to identify the pose of non-cylindrical objects such as pallets, cages, and single stacks of goods in industrial application scenarios (such as factories and industrial parks).

[0003] However, traditional forklift sensing technology can only identify the pose of non-cylindrical goods such as pallets, cages, and single stacks of goods, and cannot identify the pose of cylindrical goods. Summary of the Invention

[0004] Therefore, it is necessary to provide a cargo information identification method, apparatus, computer equipment, computer-readable storage medium, and computer program product capable of identifying the pose of cylindrical cargo in order to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for identifying cargo information. Applied to a forklift, the forklift including at least two forklift arms, the method includes:

[0006] Obtain a point cloud dataset, which is obtained by collecting data from the target area;

[0007] The cross-sectional parameters of the target cargo within the target area are determined based on the point cloud dataset. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo.

[0008] The pose information of the target cargo is determined based on the cross-sectional parameters and the forklift arm parameters of each forklift arm. The pose information is used to represent the location and orientation of the target cargo.

[0009] In one embodiment, determining the cross-sectional parameters of the target cargo within the target area based on the point cloud dataset includes:

[0010] Extract the target point cloud dataset corresponding to the target cargo from the point cloud dataset;

[0011] The target point cloud dataset is fitted to obtain the point cloud shape of the target cargo;

[0012] The cross-sectional parameters of the target cargo are determined based on the point cloud shape of the target cargo.

[0013] In one embodiment, extracting the target point cloud dataset corresponding to the target cargo from the point cloud dataset includes:

[0014] Clustering algorithms are used to cluster point cloud datasets to obtain at least one candidate point cloud dataset.

[0015] The candidate point cloud dataset with the highest density is used as the target point cloud dataset.

[0016] In one embodiment, the cross-sectional dimension includes the radius of the cross-sectional circle corresponding to the cross-section. At least two forklift arms include a first forklift arm and a rotatable second forklift arm. Forklift arm parameters include the position of the contact point of the first forklift arm, the position of the root point of the second forklift arm, and the rotation radius of the second forklift arm. The contact point is the end of the first forklift arm closest to the cargo, and the root point is the end of the second forklift arm furthest from the cargo. The pose information of the target cargo is determined based on the cross-sectional parameters and the forklift arm parameters of each forklift arm, including:

[0017] Using a perception algorithm, the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation are calculated to obtain the pose information of the target cargo.

[0018] In one embodiment, the perception algorithm includes a first perception algorithm and a second perception algorithm. Using the perception algorithms, the radius of the cross-sectional circle, the position of the contact point, the position of the root point, and the radius of rotation are calculated to obtain the pose information of the target cargo, including:

[0019] Using the first sensing algorithm, the target position of the target cargo is obtained by calculating the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation.

[0020] The orientation of the target cargo is calculated using the second sensing algorithm and the target location.

[0021] In one embodiment, the target location includes a first location parameter and a second location parameter, the location of the contact point includes a first contact point location parameter and a second contact point location parameter, the location of the root point includes a first root point location parameter and a second root point location parameter, and the first sensing algorithm includes:

[0022] (x-x0) 2 +(y-y0) 2 =(2r) 2 ;

[0023] (x-x1) 2 +(y-y1) 2 =r1 2 ;

[0024] Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, x1 is the first root point position parameter, y1 is the second root point position parameter, r is the radius of the cross-sectional circle, and r1 is the radius of rotation.

[0025] In one embodiment, the target location includes a first location parameter and a second location parameter, the location of the contact point includes a first contact point location parameter and a second contact point location parameter, the location of the root point includes a first root point location parameter and a second root point location parameter, and the second sensing algorithm includes:

[0026] th=π / 2-arctan(∣y-y0∣ / ∣x-x0∣);

[0027] dx = r·sin(th);

[0028] dy=-(r·cos(th)-∣y0∣);

[0029] Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, th is the orientation of the target cargo, dx is the horizontal coordinate offset of the rotated second forklift arm relative to the forklift, and dy is the vertical coordinate offset of the rotated second forklift arm relative to the forklift.

[0030] Secondly, this application also provides a cargo information identification device. The device includes:

[0031] The data acquisition module is used to acquire point cloud datasets, which are obtained by collecting data from the target area.

[0032] The parameter determination module is used to determine the cross-sectional parameters of the target cargo within the target area based on the point cloud dataset. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo.

[0033] The information recognition module is used to determine the pose information of the target cargo based on the cross-sectional parameters and the forklift arm parameters of each forklift arm. The pose information is used to represent the location and posture of the target cargo.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the cargo information identification method of the first aspect.

[0035] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the cargo information identification method of the first aspect.

[0036] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the cargo information identification method of the first aspect.

[0037] The aforementioned cargo information identification method, apparatus, computer equipment, computer-readable storage medium, and computer program product acquire a point cloud dataset, which is obtained by collecting data from a target area. Based on the point cloud dataset, they determine the cross-sectional parameters of the target cargo within the target area. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo. Based on the cross-sectional parameters and the forklift arm parameters of each forklift arm, they determine the pose information of the target cargo, which represents the location and orientation of the target cargo. By determining the cross-sectional parameters of the target cargo using the point cloud dataset, the location and orientation of the cylindrical target cargo can be accurately identified. Attached Figure Description

[0038] Figure 1 This is an application environment diagram of the cargo information identification method in one embodiment;

[0039] Figure 2 This is a flowchart illustrating a cargo information identification method in one embodiment;

[0040] Figure 3 This is a schematic diagram of the forklift structure in one embodiment;

[0041] Figure 4 This is a flowchart illustrating the cargo information identification method in another embodiment;

[0042] Figure 5 This is a structural block diagram of a cargo information identification device in one embodiment;

[0043] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0045] The cargo information identification method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, the forklift 101 includes at least two forklift arms. The forklift 101 identifies the target cargo 102 within the target area and determines the location and orientation of the target cargo 102 by performing pose recognition on it, i.e., determining the pose information of the target cargo 102. It can be understood that pose information refers to the pose of the target cargo 102 relative to the forklift.

[0046] For example, forklift 101 acquires a point cloud dataset; the point cloud dataset is obtained by collecting data from the target area. Forklift 101 determines the cross-sectional parameters of the target cargo 102 within the target area based on the point cloud dataset; the target cargo 102 is cylindrical; the cross-sectional parameters include the cross-sectional dimensions of the target cargo 102. Forklift 101 determines the pose information of the target cargo 102 based on the cross-sectional parameters and the forklift arm parameters of each forklift arm; the pose information is used to represent the location and orientation of the target cargo 102.

[0047] In some embodiments, at least two forklift arms include a first forklift arm and a second forklift arm. It is understood that at least two forklift arms are configured to cooperate with each other to clamp and secure the target goods. For example, the target goods are clamped and secured by at least two forklift arms forming a grip.

[0048] In some embodiments, the forklift includes two forklift arms. The shorter forklift arm is called the first forklift arm, and the longer forklift arm is called the second forklift arm. The first forklift arm is shorter than the second forklift arm. It can be understood that having two forklift arms of different lengths can meet the needs of the forklift to pick up target goods of different sizes.

[0049] In one embodiment, such as Figure 2 As shown, a method for identifying cargo information is provided, which can be applied to... Figure 1 Taking forklift 101 as an example, the explanation includes the following steps:

[0050] Step 202: Obtain the point cloud dataset, which is obtained by collecting data from the target area.

[0051] Point cloud data refers to a set of vectors in a three-dimensional coordinate system. A point cloud dataset refers to a collection of point cloud data within a target area. For example, a point cloud dataset is obtained by acquiring data from a target area using a data acquisition device. A data acquisition device is a device capable of acquiring point cloud data from a target area, including but not limited to 2D laser sensors.

[0052] In some embodiments, the point cloud dataset, i.e., the point cloud data within the target area, includes: three-dimensional point cloud data of the target area and three-dimensional point cloud data of each object within the target area.

[0053] In some embodiments, objects within the target area include at least one of non-cylindrical goods such as pallets, cages, and single stacks of goods, cylindrical goods, and shelves for storing goods.

[0054] The target area refers to the designated area for forklifts to pick up or drop off goods.

[0055] For example, the acquisition device is installed on a forklift. When the forklift arrives at the target area, the acquisition device acquires the point cloud dataset of the target area. Then the forklift obtains the point cloud dataset acquired by the acquisition device in the designated area for the forklift to pick up or put down goods.

[0056] Step 204: Determine the cross-sectional parameters of the target cargo within the target area based on the point cloud dataset. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo.

[0057] Among them, cylindrical refers to the target cargo having a cylindrical shape.

[0058] Cross-sectional parameters refer to the cross-sectional dimensions of the target cargo. For example, if the target cargo is a cylinder, the cross-sectional parameters can be the cross-sectional dimensions of the cylinder. It can be understood that the cross-section of a cylinder is circular, therefore the cross-sectional dimensions of the target cargo include the diameter of the circle. The cross-sectional parameters of the target cargo are determined by analyzing the point cloud data of the target cargo using a point cloud dataset.

[0059] For example, the forklift clusters the point cloud dataset according to a clustering algorithm, determines the point cloud data of the target cargo from the clustered point cloud dataset, determines the point cloud shape of the target cargo based on the point cloud data of the target cargo, and determines the cross-sectional dimensions of the cylindrical target cargo within the target area based on the point cloud shape.

[0060] Step 206: Determine the pose information of the target cargo based on the cross-sectional parameters and the forklift arm parameters of each forklift arm. The pose information is used to represent the location and orientation of the target cargo.

[0061] Optionally, forklift arm parameters include forklift arm position parameters and forklift arm size parameters.

[0062] For example, the forklift determines the location and orientation of the target cargo based on the cross-sectional parameters, the position parameters of the forklift arm, and the size parameters of the forklift arm.

[0063] It can be understood that the orientation of the target cargo refers to its facing direction, that is, its angle relative to the forklift. Once the forklift determines the position and orientation of the target cargo, it can accurately pick it up.

[0064] In the above-described cargo information identification method, a point cloud dataset is acquired, which is obtained by the acquisition device by collecting data from the target area. Based on the point cloud dataset, the cross-sectional parameters of the target cargo within the target area are determined. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo. Based on the cross-sectional parameters and the forklift arm parameters of each forklift arm, the pose information of the target cargo is determined. This pose information represents the location and orientation of the target cargo. By determining the cross-sectional parameters of the target cargo using the point cloud dataset, the location and orientation of the cylindrical target cargo can be accurately identified.

[0065] In one embodiment, determining the cross-sectional parameters of a target cargo within a target area based on a point cloud dataset includes: extracting a target point cloud dataset corresponding to the target cargo from the point cloud dataset; performing fitting processing on the target point cloud dataset to obtain the point cloud shape of the target cargo; and determining the cross-sectional parameters of the target cargo based on the point cloud shape of the target cargo.

[0066] One approach is to fit the target point cloud dataset using the least squares method. The least squares method is a technique that finds the optimal matching function for the point cloud data in the target dataset by minimizing the sum of squared errors, ensuring that the distance from all target point cloud data points to the fitting plane is minimized during its application.

[0067] For example, the forklift extracts the point cloud dataset corresponding to the target cargo from the point cloud dataset, i.e., the target point cloud dataset. It then uses the least squares method to perform circle fitting on the target point cloud dataset to obtain the point cloud shape of the target cargo, i.e., the point cloud shape of the target cargo is cylindrical. Based on the point cloud shape of the target cargo, the cross-sectional dimensions of the target cargo are then obtained. It can be understood that in the process of using the least squares method to fit the cylindrical point cloud corresponding to the target cargo, the center coordinates and radii of each cross-section are first determined, and then the cylinder is obtained by fitting the center coordinates and radii. Therefore, after using the least squares method to perform circle fitting on the target point cloud dataset to obtain the cylindrical point cloud corresponding to the target cargo, the cross-sectional dimensions of the target cargo can be obtained by arbitrarily selecting one cross-section of the cylindrical point cloud.

[0068] In this embodiment, the point cloud shape of the target cargo is obtained through a point cloud dataset, and then the cross-sectional dimensions of the target cargo are determined based on the point cloud shape, providing computational parameters for calculating the pose of the target cargo. Furthermore, by extracting the target point cloud dataset corresponding to the target cargo from the point cloud dataset, and then performing fitting processing on the target point cloud dataset corresponding to the target cargo to determine the point cloud shape, the computational power required to determine the point cloud shape is relatively small. Therefore, this method embodiment has low hardware resource requirements and can save hardware resources.

[0069] In one embodiment, extracting the target point cloud dataset corresponding to the target cargo from the point cloud dataset includes: clustering the point cloud dataset using a clustering algorithm to obtain at least one candidate point cloud dataset in the point cloud dataset; and using the candidate point cloud dataset with the highest density as the target point cloud dataset.

[0070] Clustering refers to dividing a point cloud dataset into different classes or clusters according to a specific criterion, maximizing the similarity of point cloud datasets within the same cluster and maximizing the differences between point cloud datasets in different clusters. For example, clustering point cloud data according to density yields candidate point cloud datasets.

[0071] For example, the forklift uses a density clustering algorithm to segment the point cloud dataset into different candidate point cloud datasets, and selects the candidate point cloud dataset with the highest density as the target point cloud dataset.

[0072] In this embodiment, the target point cloud dataset is obtained through density clustering algorithm, which can accurately determine the target point cloud dataset.

[0073] In one embodiment, the forklift includes at least two forklift arms, and at least one forklift arm is rotatable. It is understood that having at least one rotatable forklift arm allows for flexible clamping and fixing of target goods in different placement positions.

[0074] In one embodiment, the target cargo is cylindrical, and its different placement positions include standing and lying down. Standing means the bottom surface of the cylindrical target cargo is on the ground, i.e., the round surface is on the ground. Lying down means the side surface of the cylindrical target cargo is on the ground, i.e., the curved surface is on the ground. It can be understood that, for target objects in different placement positions, the forklift arm can be rotated to clamp and fix the target object in different placement positions.

[0075] In some embodiments, the forklift includes two forklift arms. The shorter forklift arm is called the first forklift arm, and the longer forklift arm is called the second forklift arm. The first forklift arm is shorter than the second forklift arm, and the second forklift arm is rotatable. It is understood that having two forklift arms of different lengths can meet the needs of the forklift to grip target goods of different sizes. In one embodiment, the cross-sectional dimension includes the radius of the cross-sectional circle corresponding to the cross-section. At least two forklift arms include a first forklift arm and a rotatable second forklift arm. Forklift arm parameters include the position of the contact point of the first forklift arm, the position of the root point of the second forklift arm, and the rotation radius of the second forklift arm. The contact point is the end of the first forklift arm closest to the goods, and the root point is the end of the second forklift arm furthest from the goods. Figure 3 This is a schematic diagram of a forklift structure in one embodiment. Figure 3It is known that the forklift includes a forklift body, a first forklift arm 301, and a second forklift arm 302. The forklift body refers to the parts of the forklift excluding the forklift arms. The pose information of the target cargo is determined based on cross-sectional parameters and the forklift arm parameters of each forklift arm. This includes using a perception algorithm to calculate the radius of the cross-sectional circle, the position of the contact point 303 of the first forklift arm 301, the position of the root point 304 of the rotatable second forklift arm 302, and the rotation radius of the rotatable second forklift arm 302, thereby obtaining the pose information of the target cargo.

[0076] Among them, the perception algorithm is an algorithm for detecting goods in a 3D scene, and the pose refers to the position and orientation of the target goods.

[0077] For example, the forklift uses a sensing algorithm to calculate the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation to obtain the position and orientation of the target cargo.

[0078] In this embodiment, the pose of the target cargo can be accurately determined through a perception algorithm.

[0079] In one embodiment, the perception algorithm includes a first perception algorithm and a second perception algorithm. Using the perception algorithm, the radius of the cross-section circle, the position of the contact point, the position of the root point, and the rotation radius are calculated to obtain the pose information of the target cargo. This includes: using the first perception algorithm to calculate the radius of the cross-section circle, the position of the contact point, the position of the root point, and the rotation radius to obtain the target position of the target cargo; and using the second perception algorithm and the target position to calculate the pose of the target cargo.

[0080] For example, the forklift uses a first sensing algorithm to calculate the radius of the cross-section circle, the position parameters of the first contact point, the position parameters of the second contact point, the position parameters of the first root point, the position parameters of the second root point, and the rotation radius to obtain the first position parameters and the second position parameters of the target cargo. Then, it uses a second sensing algorithm to calculate the posture of the target cargo based on the first position parameters and the second position parameters of the target cargo.

[0081] In this embodiment, the position of the target cargo is calculated by the first perception algorithm, and the posture of the target cargo is calculated by the second perception algorithm, which can accurately determine the posture of the target cargo.

[0082] In one embodiment, the target location includes a first location parameter and a second location parameter, the location of the contact point includes a first contact point location parameter and a second contact point location parameter, the location of the root point includes a first root point location parameter and a second root point location parameter, and the first sensing algorithm includes: (x-x0) 2 +(y-y0) 2 =(2r) 2 (x-x1) 2+(y-y1) 2 =r1 2 Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, x1 is the first root point position parameter, y1 is the second root point position parameter, r is the radius of the cross-sectional circle, and r1 is the rotation radius.

[0083] In one embodiment, the target position includes a first position parameter and a second position parameter, the position of the contact point includes a first contact point position parameter and a second contact point position parameter, the position of the root point includes a first root point position parameter and a second root point position parameter, and the second sensing algorithm includes: th = π / 2 - atan(∣y - y0∣ / ∣x - x0∣); dx = r·sin(th); dy = -(r·cos(th) -∣y0∣); where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, and y0 is the second contact point position parameter.

[0084] This application provides a cargo information identification method applied to forklifts. A detailed embodiment is described below. Figure 4 As shown, the specific steps for identifying cargo information are described: the forklift includes at least two forklift arms, the at least two forklift arms include a first forklift arm and a second forklift arm, the first forklift arm is shorter than the second forklift arm, the first forklift arm is defined as the forklift short arm, and the second forklift arm is defined as the forklift long arm.

[0085] Step 401: Install a 2D laser sensor at the midpoint of the lower end of the two forklift arms, and calibrate the external parameters of the installed 2D laser sensor. The main parameters calibrated for the 2D laser sensor are laser_x, laser_y, and laser_th, where laser_th represents the angle of the laser relative to the forklift, laser_y represents the position of the laser relative to the forklift in the y-direction, and laser_x represents the position of the laser relative to the forklift in the x-direction.

[0086] Step 402: The forklift acquires a point cloud dataset collected by the 2D laser sensor in the designated area for the forklift to pick up or place goods.

[0087] Step 403: The forklift uses the DBSCAN clustering algorithm to cluster the collected point cloud dataset to obtain candidate point cloud datasets. Then, the point cloud data corresponding to the dataset with the highest density is used as the point cloud data corresponding to the target goods (e.g., the target paper roll).

[0088] Step 404: The forklift uses the least squares method to fit the point cloud data corresponding to the target paper roll to obtain the point cloud shape of the target paper roll.

[0089] Step 405: The forklift obtains the radius of the cross-sectional circle of the target paper roll based on the point cloud shape of the target paper roll.

[0090] Step 406: The forklift uses the first perception algorithm to calculate the position (x, y) of the target paper roll by the coordinates of the contact point (x0, y0) of the forklift short arm, the coordinates of the root of the forklift long arm (x1, y1), the radius r of the target paper roll cross-section circle, and the rotation radius r1 of the forklift long arm.

[0091] Among them, the first perception algorithm:

[0092] (x-x0) 2 +(y-y0) 2 =(2r) 2

[0093] (x-x1) 2 +(y-y1) 2 =r1 2

[0094] Step 407: The forklift uses the second sensing algorithm to calculate the position (x, y) of the target paper roll to obtain the orientation of the target paper roll.

[0095] Among them, the second perception algorithm:

[0096] th=π / 2-arctan(∣y-y0∣ / ∣x-x0∣)

[0097] dx=r·sin(th);dy=-(r·cos(th)-∣y0∣)

[0098] dy=-(r·cos(th)-∣y0∣)

[0099] In the aforementioned cargo information recognition method, a point cloud dataset is acquired, which is obtained by collecting data from the target area using a data acquisition device. Based on the point cloud dataset, the cross-sectional parameters of the target cargo within the target area are determined. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the cargo. Based on the cross-sectional parameters and the forklift arm parameters of each forklift arm, the pose information of the target cargo is determined. This pose information represents the location and orientation of the target cargo. By determining the cross-sectional parameters of the target cargo using the point cloud dataset, the location and orientation of the cylindrical target cargo can be accurately identified.

[0100] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0101] Based on the same inventive concept, this application also provides a cargo information identification device for implementing the cargo information identification method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more cargo information identification device embodiments provided below can be found in the limitations of the cargo information identification method described above, and will not be repeated here.

[0102] In one embodiment, such as Figure 5 As shown, a cargo information identification device is provided, comprising: a data acquisition module 510, a parameter determination module 520, and an information identification module 530, wherein:

[0103] The data acquisition module 510 is used to acquire point cloud datasets, which are collected from the target area.

[0104] The parameter determination module 520 is used to determine the cross-sectional parameters of the target cargo within the target area based on the point cloud dataset. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo.

[0105] The information recognition module 530 is used to determine the pose information of the target cargo based on the cross-sectional parameters and the forklift arm parameters of each forklift arm. The pose information is used to represent the location and posture of the target cargo.

[0106] In one embodiment, the parameter determination module 520 further includes an extraction unit and a fitting unit. The extraction unit is used to extract the target point cloud dataset corresponding to the target cargo from the point cloud dataset; the fitting unit is used to perform fitting processing on the target point cloud dataset to obtain the point cloud shape of the target cargo; the parameter determination module 520 is used to determine the cross-sectional parameters of the target cargo based on the point cloud shape of the target cargo.

[0107] In one embodiment, the parameter determination module 520 further includes a clustering unit. The clustering unit is used to cluster the point cloud dataset using a clustering algorithm to obtain at least one candidate point cloud dataset; and to select the candidate point cloud dataset with the highest density as the target point cloud dataset.

[0108] In one embodiment, the information recognition module 530 further includes: a computing unit.

[0109] The computing unit is used to calculate the pose information of the target cargo by using a perception algorithm to calculate the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation.

[0110] In one embodiment, the information recognition module 530 is used to calculate the target position of the target cargo by using a first perception algorithm to calculate the radius of the cross-section circle, the position of the contact point, the position of the root point and the radius of rotation; and to calculate the posture of the target cargo by using a second perception algorithm and the target position.

[0111] In one embodiment, the target location includes a first location parameter and a second location parameter, the location of the contact point includes a first contact point location parameter and a second contact point location parameter, the location of the root point includes a first root point location parameter and a second root point location parameter, and the first sensing algorithm includes: (x-x0) 2 +(y-y0) 2 =(2r) 2 (x-x1) 2 +(y-y1) 2 =r1 2 Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, x1 is the first root point position parameter, y1 is the second root point position parameter, r is the radius of the cross-sectional circle, and r1 is the radius of rotation.

[0112] In one embodiment, the second sensing algorithm includes: h = π / 2 - atan(∣y-y0∣ / ∣x-x0∣); dx = r·sin(th); dy = -(r·cos(th) -∣y0∣); where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, th is the posture of the target cargo, dx is the horizontal coordinate offset of the rotated second forklift arm relative to the forklift, and dy is the vertical coordinate offset of the rotated second forklift arm relative to the forklift.

[0113] Each module in the aforementioned cargo information identification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0114] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores relevant data required for implementing a cargo information identification method. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a cargo information identification method.

[0115] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0116] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0117] Obtain a point cloud dataset, which is obtained by collecting data from the target area;

[0118] The cross-sectional parameters of the target cargo within the target area are determined based on the point cloud dataset. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo.

[0119] The pose information of the target cargo is determined based on the cross-sectional parameters and the forklift arm parameters of each forklift arm. The pose information is used to represent the location and orientation of the target cargo.

[0120] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0121] Extract the target point cloud dataset corresponding to the target cargo from the point cloud dataset;

[0122] The target point cloud dataset is fitted to obtain the point cloud shape of the target cargo;

[0123] The cross-sectional parameters of the target cargo are determined based on the point cloud shape of the target cargo.

[0124] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0125] Clustering algorithms are used to cluster point cloud datasets to obtain at least one candidate point cloud dataset.

[0126] The candidate point cloud dataset with the highest density is used as the target point cloud dataset.

[0127] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0128] Using a perception algorithm, the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation are calculated to obtain the pose information of the target cargo.

[0129] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0130] Using the first sensing algorithm, the target position of the target cargo is obtained by calculating the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation.

[0131] The orientation of the target cargo is calculated using the second sensing algorithm and the target location.

[0132] In one embodiment, the processor, when executing a computer program, also implements the following formula:

[0133] (x-x0) 2 +(y-y0) 2 =(2r) 2 ;

[0134] (x-x1) 2 +(y-y1) 2 =r1 2 ;

[0135] Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, x1 is the first root point position parameter, y1 is the second root point position parameter, r is the radius of the cross-sectional circle, and r1 is the radius of rotation.

[0136] In one embodiment, the processor, when executing a computer program, also implements the following formula:

[0137] th=π / 2-arctan(∣y-y0∣ / ∣x-x0∣);

[0138] dx = r·sin(th);

[0139] dy=-(r·cos(th)-∣y0∣);

[0140] Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, th is the orientation of the target cargo, dx is the horizontal coordinate offset of the rotated second forklift arm relative to the forklift, and dy is the vertical coordinate offset of the rotated second forklift arm relative to the forklift.

[0141] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0142] Obtain a point cloud dataset, which is obtained by collecting data from the target area;

[0143] The cross-sectional parameters of the target cargo within the target area are determined based on the point cloud dataset. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo.

[0144] The pose information of the target cargo is determined based on the cross-sectional parameters and the forklift arm parameters of each forklift arm. The pose information is used to represent the location and orientation of the target cargo.

[0145] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0146] Extract the target point cloud dataset corresponding to the target cargo from the point cloud dataset;

[0147] The target point cloud dataset is fitted to obtain the point cloud shape of the target cargo;

[0148] The cross-sectional parameters of the target cargo are determined based on the point cloud shape of the target cargo.

[0149] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0150] Clustering algorithms are used to cluster point cloud datasets to obtain at least one candidate point cloud dataset.

[0151] The candidate point cloud dataset with the highest density is used as the target point cloud dataset.

[0152] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0153] Using a perception algorithm, the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation are calculated to obtain the pose information of the target cargo.

[0154] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0155] Using the first sensing algorithm, the target position of the target cargo is obtained by calculating the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation.

[0156] The orientation of the target cargo is calculated using the second sensing algorithm and the target location.

[0157] In one embodiment, when the computer program is executed by a processor, it also implements the following formula:

[0158] (x-x0) 2 +(y-y0) 2 =(2r) 2 ;

[0159] (x-x1) 2 +(y-y1) 2 =r1 2 ;

[0160] Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, x1 is the first root point position parameter, y1 is the second root point position parameter, r is the radius of the cross-sectional circle, and r1 is the radius of rotation.

[0161] In one embodiment, when the computer program is executed by a processor, it also implements the following formula:

[0162] th=π / 2-arctan(∣y-y0∣ / ∣x-x0∣);

[0163] dx = r·sin(th);

[0164] dy=-(r·cos(th)-∣y0∣);

[0165] Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, th is the orientation of the target cargo, dx is the horizontal coordinate offset of the rotated second forklift arm relative to the forklift, and dy is the vertical coordinate offset of the rotated second forklift arm relative to the forklift.

[0166] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0167] Obtain a point cloud dataset, which is obtained by collecting data from the target area;

[0168] The cross-sectional parameters of the target cargo within the target area are determined based on the point cloud dataset. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo.

[0169] The pose information of the target cargo is determined based on the cross-sectional parameters and the forklift arm parameters of each forklift arm. The pose information is used to represent the location and orientation of the target cargo.

[0170] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0171] Extract the target point cloud dataset corresponding to the target cargo from the point cloud dataset;

[0172] The target point cloud dataset is fitted to obtain the point cloud shape of the target cargo;

[0173] The cross-sectional parameters of the target cargo are determined based on the point cloud shape of the target cargo.

[0174] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0175] Clustering algorithms are used to cluster point cloud datasets to obtain at least one candidate point cloud dataset.

[0176] The candidate point cloud dataset with the highest density is used as the target point cloud dataset.

[0177] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0178] Using a perception algorithm, the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation are calculated to obtain the pose information of the target cargo.

[0179] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0180] Using the first sensing algorithm, the target position of the target cargo is obtained by calculating the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation.

[0181] The orientation of the target cargo is calculated using the second sensing algorithm and the target location.

[0182] In one embodiment, when the computer program is executed by a processor, it also implements the following formula:

[0183] (x-x0) 2 +(y-y0) 2 =(2r)2 ;

[0184] (x-x1) 2 +(y-y1) 2 =r1 2 ;

[0185] Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, x1 is the first root point position parameter, y1 is the second root point position parameter, r is the radius of the cross-sectional circle, and r1 is the radius of rotation.

[0186] In one embodiment, when the computer program is executed by a processor, it also implements the following formula:

[0187] th=π / 2-arctan(∣y-y0∣ / ∣x-x0∣);

[0188] dx = r·sin(th);

[0189] dy=-(r·cos(th)-∣y0∣);

[0190] Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, th is the orientation of the target cargo, dx is the horizontal coordinate offset of the rotated second forklift arm relative to the forklift, and dy is the vertical coordinate offset of the rotated second forklift arm relative to the forklift.

[0191] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0192] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0193] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0194] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for identifying cargo information, characterized in that, Applied to a forklift, the forklift including at least two forklift arms, the method includes: Obtain a point cloud dataset, which is obtained by collecting data from the target area; The cross-sectional parameters of the target cargo within the target area are determined based on the point cloud dataset. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo. The pose information of the target cargo is determined based on the cross-sectional parameters and the forklift arm parameters of each forklift arm. The pose information is used to represent the location and posture of the target cargo. The cross-sectional dimension includes the radius of the cross-sectional circle corresponding to the cross-section. At least two forklift arms include a first forklift arm and a rotatable second forklift arm. The forklift arm parameters include the position of the contact point of the first forklift arm, the position of the root point of the second forklift arm, and the rotation radius of the second forklift arm. The contact point is the end of the first forklift arm closest to the cargo, and the root point is the end of the second forklift arm furthest from the cargo. Determining the pose information of the target cargo based on the cross-sectional parameters and the forklift arm parameters of each forklift arm includes: Using a perception algorithm, the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation are calculated to obtain the pose information of the target cargo.

2. The method according to claim 1, characterized in that, Determining the cross-sectional parameters of the target cargo within the target area based on the point cloud dataset includes: Extract the target point cloud dataset corresponding to the target cargo from the point cloud dataset; The target point cloud dataset is fitted to obtain the point cloud shape of the target cargo; The cross-sectional parameters of the target cargo are determined based on the point cloud shape of the target cargo.

3. The method according to claim 2, characterized in that, The step of extracting the target point cloud dataset corresponding to the target cargo from the point cloud dataset includes: Clustering algorithms are used to cluster point cloud datasets to obtain at least one candidate point cloud dataset. The candidate point cloud dataset with the highest density is used as the target point cloud dataset.

4. The method according to claim 1, characterized in that, The perception algorithm includes a first perception algorithm and a second perception algorithm. The perception algorithm is used to calculate the radius of the cross-section circle, the position of the contact point, the position of the root point, and the rotation radius to obtain the pose information of the target cargo, including: Using the first perception algorithm, the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation are calculated to obtain the target position of the target cargo; The orientation of the target cargo is calculated using the second perception algorithm and the target location.

5. The method according to claim 4, characterized in that, The target location includes a first location parameter and a second location parameter; the location of the contact point includes a first contact point location parameter and a second contact point location parameter; the location of the root point includes a first root point location parameter and a second root point location parameter; the first sensing algorithm includes: (x-x0) 2 +(y-y0) 2 =(2r) 2 ; (x-x1) 2 +(y-y1) 2 =r1 2 ; Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, x1 is the first root point position parameter, y1 is the second root point position parameter, r is the radius of the cross-sectional circle, and r1 is the radius of rotation.

6. The method according to claim 4, characterized in that, The target location includes a first location parameter and a second location parameter; the location of the contact point includes a first contact point location parameter and a second contact point location parameter; the location of the root point includes a first root point location parameter and a second root point location parameter; the second sensing algorithm includes: th=π / 2-arctan(∣y-y0∣ / ∣x-x0∣); dx = r·sin(th); dy=-( r·cos(th)-∣y0∣); Where x is the first position parameter, y is the second position parameter, x0 is the first contact point position parameter, y0 is the second contact point position parameter, th is the posture of the target cargo, dx is the lateral coordinate offset of the rotated second forklift arm relative to the forklift, dy is the ordinate coordinate offset of the rotated second forklift arm relative to the forklift, and r is the radius of the cross-sectional circle.

7. A cargo information identification device, characterized in that, The device includes: The data acquisition module is used to acquire a point cloud dataset, which is obtained by collecting data from the target area. The parameter determination module is used to determine the cross-sectional parameters of the target cargo within the target area based on the point cloud dataset. The target cargo is cylindrical, and the cross-sectional parameters include the cross-sectional dimensions of the target cargo. An information recognition module is used to determine the pose information of the target cargo based on the cross-sectional parameters and the forklift arm parameters of each forklift arm. The pose information is used to represent the location and posture of the target cargo. The cross-sectional dimension includes the radius of the cross-sectional circle corresponding to the cross-section. At least two forklift arms include a first forklift arm and a rotatable second forklift arm. The forklift arm parameters include the position of the contact point of the first forklift arm, the position of the root point of the second forklift arm, and the rotation radius of the second forklift arm. The contact point is the end of the first forklift arm closest to the cargo, and the root point is the end of the second forklift arm furthest from the cargo. Determining the pose information of the target cargo based on the cross-sectional parameters and the forklift arm parameters of each forklift arm includes: Using a perception algorithm, the radius of the cross-section circle, the position of the contact point, the position of the root point, and the radius of rotation are calculated to obtain the pose information of the target cargo.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images