Full-automatic stacking method and system based on machine vision and path planning

Abstract

The invention relates to the technical field of logistics automation, in particular to a full-automatic stacking method and system based on machine vision and path planning, and the method comprises the following steps: based on three-dimensional point cloud data of goods, extracting point cloud coordinates, normal vectors and curvature values of the surface of the goods, calculating the geometric segmentation range of point cloud edge features, and calculating the geometric segmentation range of the point cloud edge features; and calculating a fitting relationship between the boundary size and curvature distribution. According to the method, the surface point cloud coordinates, the normal vector and the curvature value are extracted based on the three-dimensional point cloud data, the accuracy of geometric feature description of the complex cargo surface is enhanced, the geometric center and the variance range are reasonably determined through spatial distribution analysis and feature set classification, the accuracy and stability of shape classification are improved, and the accuracy and stability of shape classification are improved through gravity center and size deviation calculation. The position and pressure distribution of the contact point are optimized, the space priority analysis of the grabbing point and the obstacle point is combined, the path planning and obstacle point elimination strategy is optimized, the path conflict is reduced, and the flexibility and efficiency of logistics operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics automation, and in particular to a full-automatic palletizing method and system based on machine vision and path planning. Background Art

[0002] The field of logistics automation technology includes related methods and systems for automated management of logistics activities based on computers and intelligent technologies. Its core content is to use information technology, artificial intelligence, mechanical automation and other means to optimize and control logistics transportation, warehousing management, cargo sorting and distribution, so as to improve logistics efficiency. This technical field systematically covers the whole process automation from cargo storage, sorting, loading and unloading to transportation, mainly including key technical modules such as path planning, robot arm operation, visual recognition, dynamic scheduling, etc., and realizes precise control of logistics operations by combining multiple sensor data collection and real-time feedback technology.

[0003] Among them, the fully automatic palletizing method refers to an operation method that realizes automatic identification, classification, grabbing and neat stacking of goods by combining machine vision technology and path planning technology. The subject of this patent is aimed at the needs of palletizing operations in logistics or industrial production processes. By using machine vision technology to identify the shape, size and position of goods, combining the path planning algorithm to determine the optimal motion trajectory of the robot arm, and using the robot arm or other actuators to complete the grabbing and placement of goods, a stable and regular stack is finally formed.

[0004] Existing technologies are not sophisticated enough in the geometric description of complex cargo boundaries and surface features, making it difficult to accurately extract the boundary characteristics of complex-shaped cargo. The analysis of cargo center of gravity offset and dimensional deviation lacks dynamic adjustment capabilities, resulting in poor stability of stacked cargo. Insufficient analysis of the spatial impact range of obstacles makes it difficult for path planning to effectively avoid low-priority obstacles, increasing handling time and complexity. Insufficient real-time data processing response capabilities make it difficult to achieve precise control of path optimization and operation processes in a dynamic environment, affecting logistics operation efficiency and reliability. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a fully automatic palletizing method and system based on machine vision and path planning.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a fully automatic palletizing method based on machine vision and path planning, comprising the following steps: S1: Based on the three-dimensional point cloud data of the cargo, the point cloud coordinates, normal vector and curvature value of the cargo surface are extracted, the geometric segmentation range of the point cloud edge features is calculated, the fitting relationship between the boundary size and the curvature distribution is calculated, and the multinomial distribution of the relationship between the boundary size and the curvature is used for verification to generate the cargo geometric feature description value; S2: Based on the cargo geometric feature description value, extract the cargo curvature distribution and boundary feature position, calculate the feature point spatial range of the Euclidean distance, determine the geometric center position and distribution variance range, classify and process the feature set that meets the center distance and variance range, and generate the cargo shape classification coefficient; S3: Based on the cargo shape classification coefficient, the cargo center of gravity coordinates and three-dimensional size range are extracted, the relationship between the cargo center of gravity coordinate offset and the size deviation is calculated, the distribution area of ​​the stacking center of gravity offset and the force balance state are determined, the contact point position and the pressure value range are adjusted, and the cargo stacking force distribution is generated; S4: based on the cargo stacking force distribution, extract the contact point pressure value and the center of gravity offset range, calculate the center of gravity offset adjustment parameter and the contact point stacking matrix, accumulate all the energy relationship values ​​after stacking, establish the stacking energy optimization matrix relationship of all the cargoes, and generate the cargo stacking energy optimization value; S5: Based on the cargo stacking energy optimization value, the three-dimensional position relationship between the grabbing point and the placement point is extracted, the spatial priority values ​​of the grabbing point and the obstacle point are calculated, the spatial influence range of the lowest priority obstacle point is determined, the obstacle point exclusion parameters in the grabbing path are optimized, and a cargo path planning parameter table is generated.

[0007] As a further solution of the present invention, the cargo geometric feature description values ​​include cargo surface point cloud coordinates, normal vector, curvature value, boundary size, and curvature distribution fitting relationship; the cargo shape classification coefficient includes curvature distribution, boundary feature position, feature point spatial range, geometric center position, and distribution variance range; the cargo stacking force distribution includes contact point pressure value, center of gravity offset range, force balance state, contact point position, and pressure value range; the cargo stacking energy optimization value includes center of gravity offset adjustment parameter, contact point stacking matrix, energy relationship value after stacking, and stacking energy optimization matrix relationship; the cargo path planning parameter table includes grabbing point position, placement point position, grabbing point spatial priority value, obstacle point spatial priority value, lowest priority obstacle point spatial influence range, and obstacle point exclusion parameter.

[0008] As a further solution of the present invention, the steps for obtaining the cargo geometric feature description value are specifically as follows: S111: extracting the three-dimensional coordinates of each point in the cargo surface point cloud data, performing vector processing on the point cloud normal vector, calculating the curvature value of each point, analyzing the change trend of the curvature value in the point cloud point by point, removing abnormal points with excessive curvature changes, extracting a set of points with continuous distribution and smooth curvature in the point cloud, and generating cargo surface point cloud coordinates, normal vectors and curvature values; S112: Based on the point cloud coordinates and normal vector of the cargo surface, calculate the geometric angle difference between each point in the point cloud and the surrounding points, determine whether the geometric angle difference exceeds a set threshold, mark the points that meet the conditions as edge points, remove the points that do not meet the geometric conditions, re-analyze the boundary range of the remaining edge points, and generate a geometric segmentation range of the point cloud edge features; S113: Based on the boundary points in the geometric segmentation range of the point cloud edge features, the size distribution of the boundary points is calculated and the curvature value relationship is fitted, using the formula: ; Calculate the fitting relationship between the boundary size and the curvature value, and generate a multinomial distribution of the relationship between the boundary size and the curvature; in, Representative The curvature value of the boundary point, Representative The size value of the boundary point, represents the number of points in the curvature distribution range, represents the weight factor for each point in the curvature distribution, represents the smoothing parameter, The fitting function representing the boundary size and curvature value; S114: Calculate the deviation value of the curvature distribution according to the multinomial distribution of the relationship between the boundary size and the curvature, filter out abnormal data whose deviation value exceeds the fitting range, smooth the curvature distribution deviation value, re-verify the geometric consistency, and generate the cargo geometric feature description value.

[0009] As a further solution of the present invention, the steps for obtaining the cargo shape classification coefficient are specifically as follows: S211: extracting the curvature distribution and boundary feature positions of the cargo based on the cargo geometric feature description values, screening and extracting key points defining the cargo shape boundary by analyzing the change trend of the cargo surface curvature values ​​and combining the geometric distribution information of the boundary feature points, and generating a curvature distribution and boundary feature set; S212: using the curvature distribution and the boundary feature set, calculating the Euclidean distance from each feature point in the set to the geometric center of the cargo, constructing a geometric space model, analyzing the spatial concentration trend and outlier positions of the feature point distribution, and calibrating the spatial range of the feature points that meet the geometric conditions; S213: According to the spatial range of the feature points, determine whether each feature point is within a reasonable geometric center position and distribution variance range, using the formula: ; Calculate the geometric distance from the point to the center and evaluate the distribution deviation, classify and process the set of feature points that meet the conditions, and obtain the classified set of feature points; in, represents the Euclidean distance from the point to the geometric center, Represents the coordinates of the feature points, Represents the geometric center position of the feature point set, Represents the variance range of the feature point distribution, Represents the total number of feature point sets; S214: Analyze the statistical distribution characteristics according to the classified feature point set, combine with the geometric distribution model, calculate the spatial distribution parameters of the feature point set class by class, establish the classification standard of the cargo shape, and generate the cargo shape classification coefficient.

[0010] As a further solution of the present invention, the step of obtaining the cargo stacking force distribution is specifically as follows: S311: extracting the center of gravity coordinates and three-dimensional size range of the cargo based on the cargo shape classification coefficient, calculating the geometric center position and the corresponding volume range by analyzing the shape characteristics of the cargo unit item by item, eliminating the abnormally offset shape characteristic data, and obtaining the center of gravity coordinates and size data set; S312: Calculate the center of gravity coordinate offset and size deviation of the cargo unit according to the center of gravity coordinate and size data set, compare the offset data with the standard distribution of its corresponding geometric center, select the offset characteristic points that match the center position, remove the data with deviation values ​​exceeding a reasonable range, and generate center of gravity coordinate offset and size deviation relationship data; S313: According to the data on the relationship between the center of gravity coordinate offset and the size deviation, the distribution area of ​​the center of gravity offset of the goods in the stacked state is evaluated using the formula: ; Calculate the offset of the cargo unit under the state of force balance, determine the balance stability of the stack through the offset characteristic points, and adjust the contact point position and pressure value range; in, Represents the offset measurement under the force equilibrium state, Respectively represent The coordinates of the center of gravity of each cargo unit on the x, y, and z axes, represents the mean coordinates of the center of gravity of all cargo units, Respectively represent the standard deviation of the x, y, and z coordinates, which are used to describe the degree of discreteness of the coordinate distribution. is the total number of cargo units involved in the calculation; S314: In combination with the contact point position and the pressure value range, the force position of the contact point and the contact area ratio are adjusted by measuring the pressure distribution multiple times, the adjusted stacking stability is evaluated, and finally a force distribution model of the cargo stacking is determined to generate the cargo stacking force distribution.

[0011] As a further solution of the present invention, the step of obtaining the cargo stacking energy optimization value is specifically as follows: S411: Based on the force distribution of the cargo stack, the contact point pressure value and the center of gravity offset range are extracted, and the distribution characteristics of the pressure value in the spatial coordinates and its offset trend are calculated by analyzing the correlation between the contact point pressure data and the offset value, so as to generate the contact point pressure and center of gravity offset data; S412: calculating the center of gravity offset adjustment parameter according to the contact point pressure and center of gravity offset data, calculating the relationship between the pressure variation range and the offset value of each contact point based on the adjustment parameter, and establishing a contact point stacking matrix in combination with the geometric correlation between the contact points; S413: combining the contact point stacking matrix, accumulating the stacking energy relationship value of each contact point, calculating the sum of the stacking energies through iterative optimization based on the energy relationship values ​​of each contact point, integrating the energy accumulation relationship and performing matrix optimization operations to generate a stacking energy optimization matrix relationship; S414: According to the stacking energy optimization matrix relationship, by analyzing the optimized value distribution of all contact points in the stacking energy matrix, accumulating the optimized energy results, using the formula: ; Calculate the total stacking energy value of all goods and generate the optimized value of goods stacking energy; in, Represents the final optimized energy value of the cargo stack, Representative The initial energy value of each contact point, Representative The center of gravity offset value of each contact point, is the mean of the center of gravity offsets of all contact points, is the weight of adjusting the intensity parameter to affect the offset on energy optimization, is the total number of all contact points.

[0012] As a further solution of the present invention, the steps of obtaining the cargo path planning parameter table are specifically as follows: S511: Based on the cargo stacking energy optimization value, extract the three-dimensional positional relationship between the grabbing point and the placement point, analyze the spatial coordinates of the cargo unit item by item, calculate the distance and angle from the grabbing point to the placement point, select the coordinate characteristic points that affect the spatial connection, and generate the positional relationship data between the grabbing point and the placement point; S512: using the positional relationship data between the grabbing point and the placement point, calculating the spatial priority value between the grabbing point and the obstacle point, analyzing the spatial distribution of each obstacle point, screening the key obstacle points according to the geometric characteristics of the obstacle point's impact on the path, eliminating the non-key obstacle points with low impact, and generating a spatial priority ranking of the obstacle points; S513: According to the spatial priority ranking of the obstacle points, the spatial influence range of the lowest priority obstacle point is determined, and an improved formula is used: ; Calculate the impact of each obstacle point on the path and generate optimized obstacle point exclusion parameters for the grasping path; in, Represents the impact value of the obstacle point in the path, Indicates The importance of each obstacle point is determined by assigning differentiated weight values ​​to the importance of the path. is the distance between the obstacle point and the path, which is used to reflect the direct spatial impact of the obstacle point on the path. is a constant parameter used to avoid the situation where the denominator is zero when the obstacle point coincides with the path. It represents the indirect impact adjustment coefficient of the secondary obstacle point on the path, which is used to measure the superimposed impact intensity of the associated obstacle points. For the The main obstacle and The spatial distance between the secondary obstacle points is used to evaluate the indirect spatial effects of the relevant obstacle points. is the total number of all major obstacle points in the path, indicating the range of the number of major obstacle points. is the sum of the number of secondary obstacle points; S514: In combination with the optimized obstacle elimination parameters of the grasping path, the position arrangement of the obstacle points in the grasping path is adjusted, the connection path characteristics between the grasping points and the placement points are calculated, and a cargo path planning parameter table is generated by summarizing.

[0013] A fully automatic palletizing system based on machine vision and path planning, wherein the fully automatic palletizing system based on machine vision and path planning is used to execute the above-mentioned fully automatic palletizing method based on machine vision and path planning, and the system comprises: The cargo feature extraction module extracts the cargo surface point cloud coordinates based on the cargo 3D point cloud data, calculates the normal vector and curvature value of the point cloud coordinates, determines the geometric segmentation range of the edge features, analyzes the fitting relationship between the boundary size and the curvature distribution, and generates the cargo geometric feature description value; The cargo shape classification module extracts the curvature distribution and boundary feature position based on the cargo geometric feature description value, calculates the Euclidean distance space range of the feature point, determines the geometric center position, analyzes the distribution variance range, classifies the feature set that meets the center distance and variance range, and generates the cargo shape classification coefficient; The stacking force analysis module extracts the coordinates of the center of gravity and the three-dimensional size range of the cargo based on the cargo shape classification coefficient, calculates the relationship between the center of gravity offset value and the size deviation, determines the distribution area of ​​the center of gravity offset and the force balance state, adjusts the position and pressure value range of the contact point, analyzes the mechanical distribution range of the contact point, and generates the cargo stacking force distribution; The stacking energy optimization module extracts the pressure value of the contact point and the center of gravity offset range based on the cargo stacking force distribution, calculates the center of gravity offset adjustment parameter and the contact point stacking matrix, accumulates the energy relationship value after stacking, establishes the stacking energy optimization matrix relationship, and generates the cargo stacking energy optimization value; The path planning module extracts the three-dimensional position relationship between the grabbing point and the placement point based on the cargo stacking energy optimization value, calculates the spatial priority value of the grabbing point and the obstacle point, analyzes the spatial influence range of the lowest priority obstacle point, optimizes the obstacle point exclusion parameters in the grabbing path, and generates a cargo path planning parameter table.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, the surface point cloud coordinates, normal vectors and curvature values ​​are extracted based on the three-dimensional point cloud data, and the edge feature segmentation and boundary size fitting analysis are refined to enhance the accuracy of the description of the geometric features of the complex cargo surface. Through spatial distribution analysis and feature set classification, the geometric center and variance range are reasonably determined to improve the accuracy and stability of shape classification. Through the calculation of the center of gravity and dimensional deviation, the contact point position and pressure distribution are optimized to ensure stacking stability and force balance. Combined with the contact point stacking matrix and the energy optimization matrix, the stacking operation efficiency and resource utilization are improved. Combined with the spatial priority analysis of the grasping point and the obstacle point, the path planning and obstacle point elimination strategy are optimized to reduce path conflicts and improve the flexibility and efficiency of logistics operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 This is a flow chart of the steps for obtaining the description value of the geometric characteristics of the goods of the present invention; Figure 3 Flow chart of the steps for obtaining the cargo shape classification coefficient of the present invention; Figure 4 A flow chart of the steps for obtaining the force distribution of cargo stacking according to the present invention; Figure 5A flow chart of the steps for obtaining the optimal value of cargo stacking energy according to the present invention; Figure 6 This is a flow chart of the steps for obtaining the cargo path planning parameter table of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] Embodiment 1 See also Figure 1 The present invention provides a technical solution: a fully automatic palletizing method based on machine vision and path planning, comprising the following steps: S1: Based on the three-dimensional point cloud data of the cargo, the point cloud coordinates, normal vector and curvature value of the cargo surface are extracted, the geometric segmentation range of the point cloud edge features is calculated, the fitting relationship between the boundary size and the curvature distribution is calculated, and the multinomial distribution of the relationship between the boundary size and the curvature is used for verification to generate the cargo geometric feature description value; S2: Based on the cargo geometric feature description value, extract the cargo curvature distribution and boundary feature position, calculate the spatial range of the feature points of the Euclidean distance, determine the geometric center position and distribution variance range, classify and process the feature set that meets the center distance and variance range, and generate the cargo shape classification coefficient; S3: Based on the cargo shape classification coefficient, the cargo center of gravity coordinates and three-dimensional size range are extracted, the relationship between the cargo center of gravity coordinate offset and the size deviation is calculated, the distribution area of ​​the stacking center of gravity offset and the force balance state are determined, the contact point position and the pressure value range are adjusted, and the cargo stacking force distribution is generated; S4: Based on the force distribution of cargo stacking, the contact point pressure value and the center of gravity offset range are extracted, the center of gravity offset adjustment parameter and the contact point stacking matrix are calculated, the energy relationship values ​​of all stacked goods are accumulated, the stacking energy optimization matrix relationship of all goods is established, and the cargo stacking energy optimization value is generated; S5: Based on the cargo stacking energy optimization value, the three-dimensional position relationship between the grabbing point and the placement point is extracted, the spatial priority values ​​of the grabbing point and the obstacle point are calculated, the spatial influence range of the lowest priority obstacle point is determined, the obstacle point exclusion parameters in the grabbing path are optimized, and the cargo path planning parameter table is generated.

[0019] The cargo geometric feature description values ​​include the cargo surface point cloud coordinates, normal vector, curvature value, boundary size, and curvature distribution fitting relationship. The cargo shape classification coefficient includes curvature distribution, boundary feature position, feature point spatial range, geometric center position, and distribution variance range. The cargo stacking force distribution includes contact point pressure value, center of gravity offset range, force balance state, contact point position, and pressure value range. The cargo stacking energy optimization value includes center of gravity offset adjustment parameter, contact point stacking matrix, energy relationship value after stacking, and stacking energy optimization matrix relationship. The cargo path planning parameter table includes grabbing point position, placement point position, grabbing point spatial priority value, obstacle point spatial priority value, lowest priority obstacle point spatial influence range, and obstacle point exclusion parameter.

[0020] See also Figure 2 , the specific steps for obtaining the cargo geometric feature description value are as follows: S111: extracting the three-dimensional coordinates of each point in the cargo surface point cloud data, performing vector processing on the point cloud normal vector, calculating the curvature value of each point, analyzing the change trend of the curvature value in the point cloud point by point, removing abnormal points with excessive curvature changes, extracting a set of points with continuous distribution and smooth curvature in the point cloud, and generating cargo surface point cloud coordinates, normal vectors and curvature values; Extract the three-dimensional coordinates of each point in the point cloud data of the cargo surface and perform vector processing on the point cloud normal vector. First, it is necessary to obtain the original point cloud data set of the cargo through a scanner or a three-dimensional acquisition device, including the three-dimensional coordinates and normal vector information of the cargo surface. The data is cleaned by the point cloud preprocessing method to remove abnormal points caused by noise or environmental interference. Then, the normal vector is used to calculate the normal direction of each point in the point cloud and the curvature value of each point. The curvature value can be calculated through the geometric relationship between the neighborhood points around the point. Specifically, a set of neighborhood points within a fixed radius is selected and the normal vector is used to calculate the curvature value of each point. The surface equation of the points in the neighborhood is fitted using the least squares method, and the curvature value is calculated based on the second-order derivative of the surface equation. The calculated curvature values ​​are stored point by point in the curvature distribution data set, and the distribution characteristics of the curvature values ​​are analyzed and points with abnormal curvature changes are eliminated. For example, when the curvature value of a point deviates from the curvature value of the neighborhood point by more than the set threshold, the point can be considered as an abnormal point and eliminated. The remaining curvature values ​​are re-analyzed to ensure the continuity and smoothness of their distribution. Finally, a set of points with continuous distribution and smooth curvature in the point cloud is extracted to generate the point cloud coordinates, normal vector and curvature value of the cargo surface.

[0021] S112: Based on the point cloud coordinates and normal vector of the cargo surface, the geometric angle difference between each point in the point cloud and the surrounding points is calculated, and it is determined whether the geometric angle difference exceeds a set threshold, and the points that meet the conditions are marked as edge points, and the points that do not meet the geometric conditions are removed. The boundary range of the remaining edge points is reorganized and analyzed again to generate the geometric segmentation range of the point cloud edge features; Based on the point cloud coordinates and normal vectors of the cargo surface, the geometric angle difference between each point in the point cloud and the surrounding points is calculated. First, the normal angle difference between each point and the surrounding points is calculated using the normal vector data of the point cloud. The normal angle difference can be calculated using the dot product formula of the point normal vector. When the normal angle difference is greater than the set threshold, the point is marked as an edge point. In order to screen the geometric distribution range of the edge points, it is necessary to eliminate points that do not meet the geometric conditions. For example, the geometric relationship between the edge point and its neighboring points is calculated, including the distance and curvature difference. When the distance from the point to the neighboring point exceeds a certain set range or the curvature difference exceeds the set range, the point is not considered to be a valid edge point and is eliminated. Among the retained edge points, the boundary range reorganization process is further analyzed. By performing cluster analysis or regional division on the distribution of the edge points, the densely distributed edge points are classified into the same area to obtain a clearer geometric segmentation range, and finally generate the geometric segmentation range of the point cloud edge feature.

[0022] S113: Based on the boundary points in the geometric segmentation range of the point cloud edge features, the size distribution of the boundary points is calculated and the curvature value relationship is fitted, using the formula: ; Calculate the fitting relationship between the boundary size and the curvature value, and generate a multinomial distribution of the relationship between the boundary size and the curvature; in, Representative The curvature value of the boundary point, Representative The size value of the boundary point, represents the number of points in the curvature distribution range, represents the weight factor for each point in the curvature distribution, represents the smoothing parameter, The fitting function representing the boundary size and curvature value; formula: ; The benefit of the formula is that by introducing the weight parameter and smoothing parameters , the fitting relationship between boundary size and curvature distribution is optimized, and the stability and accuracy of curvature calculation in boundary areas are improved.

[0023] Detailed explanation of the formula and the process of formula calculation and derivation: Extract the curvature value of the boundary point , size value , the number of neighboring points , calculated by aggregating neighborhood points based on point cloud data , using the surface fitting method to obtain , calculated using Euclidean distance or density clustering methods , weight parameter The smoothing parameter is set according to the importance of the region to which the boundary point belongs. Used to adjust the stability of boundary points.

[0024] Example of data input: Assume there are five boundary points and the curvature value , the size value is , the number of neighboring points is , the weight parameter is , smoothing parameter .

[0025] Step by step calculation: First calculation: .

[0026] The second calculation: .

[0027] The third calculation: .

[0028] Fourth point calculation: .

[0029] Fifth calculation: .

[0030] Sum the fitted values: ; The results show that the fitted curvature distribution value is , indicating that the distribution relationship between curvature and boundary size tends to be smooth and reasonable, which can be used for the subsequent generation and verification calculation of multiple distributions.

[0031] S114: Calculate the deviation value of the curvature distribution according to the multinomial distribution of the relationship between the boundary size and the curvature, filter out abnormal data whose deviation value exceeds the fitting range, smooth the curvature distribution deviation value, re-verify the geometric consistency, and generate the cargo geometric feature description value.

[0032] According to the multinomial distribution of the relationship between boundary size and curvature, the deviation value of the curvature distribution is calculated. First, the curvature value data is extracted from the boundary point set, and its deviation value is calculated by combining the multinomial distribution. The deviation value can be calculated by summing and normalizing the absolute deviation between the fitted curvature value and the actual curvature value. Specifically, the formula After calculation, filter out abnormal data whose deviation values ​​exceed the fitting range. The screening condition for abnormal data is that the deviation value is greater than the set threshold or a fixed ratio value. Then smooth the curvature distribution deviation value. For example, use the sliding average method to smooth the deviation value sequence, and use the mean value in the sliding window as the adjustment value of the deviation value sequence. When re-verifying the geometric consistency, reconstruct the curvature distribution data of the geometric boundary and compare it point by point with the original curvature distribution to ensure that the geometric boundary consistency meets the fitting accuracy requirements, and finally generate the cargo geometric feature description value.

[0033] See also Figure 3 , the steps for obtaining the cargo shape classification coefficient are as follows: S211: extracting the curvature distribution and boundary feature positions of the cargo based on the cargo geometric feature description values, screening and extracting key points defining the cargo shape boundary by analyzing the change trend of the cargo surface curvature values ​​and combining the geometric distribution information of the boundary feature points, and generating a curvature distribution and boundary feature set; Based on the description value of the cargo geometric features, the curvature distribution of the cargo is analyzed. By discretizing the collection of curvature values, the curvature values ​​of continuous points are discretized into curvature amplitude intervals. Then, the curvature segment with the smallest change in the amplitude interval is extracted and matched with the geometric position of the boundary feature point. By comparing the normal vector of the boundary feature point with the gradient direction of the curvature segment, the boundary feature point set that conforms to the curvature gradient change direction is screened. Finally, combined with the spatial distribution pattern of the geometric position, the key points used to define the shape boundary of the cargo are extracted to generate the curvature distribution and boundary feature set; S212: Using the curvature distribution and the boundary feature set, the Euclidean distance from each feature point in the set to the geometric center of the cargo is calculated. By constructing a geometric space model, the spatial concentration trend and outlier positions of the feature point distribution are analyzed, and the spatial range of the feature points that meet the geometric conditions is calibrated; Using the curvature distribution and boundary feature set, we first calculate the Euclidean distance from each feature point in the curvature distribution to the geometric center through the initial selection of the geometric center, and then use the formula The calculation is performed to generate a preliminary spatial distribution model of all feature points. Then, the point set with distance values ​​above the tertile is counted to determine whether these points constitute outliers. The geometric center coordinates of the entire point set are then recalculated and the initial point set is adjusted. The spatial influence weight of the outliers is gradually reduced by introducing a center offset correction factor. The set is corrected according to the adjusted distribution weight, the range of feature points that meet the geometric conditions is calibrated, and the spatial range of feature points is generated. S213: According to the spatial range of the feature points, determine whether each feature point is within a reasonable geometric center position and distribution variance range, using the formula: ; Calculate the geometric distance from the point to the center and evaluate the distribution deviation, classify and process the set of feature points that meet the conditions, and obtain the classified set of feature points; in, represents the Euclidean distance from the point to the geometric center, Represents the coordinates of the feature points, Represents the geometric center position of the feature point set, Represents the variance range of the feature point distribution, Represents the total number of feature point sets; formula: ; The benefit of the formula is that, by combining the geometric center and the distribution variance parameter, it can not only analyze the spatial offset of the feature points, but also comprehensively evaluate the dispersion of the feature points in the set by introducing the distribution variance parameter, thus avoiding the misjudgment of the offset caused by the simple Euclidean distance; Detailed explanation of the formula and the process of formula calculation and derivation: Determine the geometric center coordinates of the feature point set based on the spatial range of the feature points , calculate the distance value from each point to the center, for example, assuming The coordinates of the feature point sets are , the geometric center coordinates are , then enter the formula to calculate: ; Expand calculation: ; ; ; ; The results show that the average offset value of the feature point set to the center is 2.02. By introducing the distribution variance parameter, the geometric distribution state of the feature points can be analyzed more accurately, providing a basis for classification processing; S214: Analyze the statistical distribution characteristics according to the classified feature point set, combine with the geometric distribution model, calculate the spatial distribution parameters of the feature point set class by class, establish the classification standard of the cargo shape, and generate the cargo shape classification coefficient.

[0034] According to the classified feature point set, by analyzing the spatial distribution pattern of each type of feature point in the set, the point set is spatially enveloped by using the minimum envelope volume method. For the distribution center of gravity in the set, the core points that affect the distribution shape are separated through the weight allocation strategy. The geometric arrangement of the core points is spatially analyzed. By comparing the analysis results with the curvature range standard, the classification standards for different cargo shapes are determined, and finally the cargo shape classification coefficient is generated.

[0035] See also Figure 4 , the specific steps for obtaining the cargo stacking force distribution are: S311: Based on the cargo shape classification coefficient, the center of gravity coordinates and three-dimensional size range of the cargo are extracted, the shape characteristics of the cargo unit are analyzed item by item, the geometric center position and the corresponding volume range are calculated, and the shape characteristic data with abnormal deviation is eliminated to obtain the center of gravity coordinates and size data set; Based on the cargo shape classification coefficient, the center of gravity coordinates and three-dimensional size range of the cargo are extracted. By analyzing the shape characteristics of the cargo units item by item, the cargo as a whole is divided into multiple structural units. The external contour points of each unit are extracted to determine the boundary coordinates. The maximum and minimum values ​​of the three-dimensional range of the cargo are calculated by the boundary coordinate data to obtain the cargo size range. Combined with the geometric center calculation formula of the boundary coordinate points, the center of gravity coordinates of each cargo unit are obtained by taking the average coordinate value. The deviation of each geometric point in each unit is judged based on the center of gravity coordinate data, and the abnormal data with an offset exceeding three times the standard deviation is eliminated. Finally, the center of gravity coordinates and size range of each unit are integrated into a set to obtain the center of gravity coordinate and size data set.

[0036] S312: Calculate the center of gravity coordinate offset and size deviation of the cargo unit based on the center of gravity coordinate and size data set, compare the offset data with the standard distribution of its corresponding geometric center, select the offset characteristic points that match the center position, remove the data with deviation values ​​exceeding the reasonable range, and generate the center of gravity coordinate offset and size deviation relationship data; According to the center of gravity coordinates and size data set, the center of gravity coordinate offset and size deviation of the cargo unit are calculated. The position offset of each unit of the cargo relative to the overall geometric center is calculated using the offset formula The three-dimensional offset of each unit is calculated, and the actual size is compared with the ideal size range to analyze the dimensional errors that may occur in the assembly or stacking process of each cargo unit. All offset values ​​are mapped to relative proportional values ​​to standardize the data. Based on the calculation results, units with dimensional deviation values ​​exceeding twice the standard deviation are screened and eliminated. The offset and dimensional data of the remaining units are integrated to form a complete offset and dimensional deviation distribution, and finally the relationship data of the center of gravity coordinate offset and dimensional deviation is generated.

[0037] S313: Based on the data on the relationship between the center of gravity coordinate offset and the dimensional deviation, the distribution area of ​​the center of gravity offset of the goods in the stacked state is evaluated using the formula: ; Calculate the offset of the cargo unit under the state of force balance, determine the balance stability of the stack through the offset characteristic points, and adjust the contact point position and pressure value range; in, Represents the offset measurement under the force equilibrium state, Respectively represent The coordinates of the center of gravity of each cargo unit on the x, y, and z axes, represents the mean coordinates of the center of gravity of all cargo units, Respectively represent the standard deviation of the x, y, and z coordinates, which are used to describe the degree of discreteness of the coordinate distribution. is the total number of cargo units involved in the calculation; formula: ; The benefit of the formula is that, by comprehensively calculating the three-dimensional offset of the cargo unit and the normalized value of its distribution variance, it can effectively analyze the cargo stacking stability and force balance state, so as to guide the adjustment of the contact point position and the optimization of the pressure range; Detailed explanation of the formula and the process of formula calculation and derivation: Assume there are 5 cargo units, The coordinate values ​​are as follows: unit 1 (10, 20, 30), unit 2 (12, 18, 29), unit 3 (11, 19, 31), unit 4 (13, 22, 28), unit 5 (9, 21, 30); first calculate the mean of each dimension : ; ; ; Then calculate the standard deviation of each dimension: ; ; ; Then substitute the formula to calculate the normalized offset of each cargo unit: ; For Unit 1: ; Calculate units 2 to 5 in sequence, and finally get ; The results show that the overall offset of the cargo unit meets the requirements of stacking stability, the offset distribution is small, and it is suitable for contact point adjustment and pressure distribution optimization.

[0038] S314: Combining the contact point position and the pressure value range, measuring the pressure distribution multiple times, adjusting the force position of the contact point and the contact area ratio, evaluating the adjusted stacking stability, and finally determining the force distribution model of the cargo stacking to generate the cargo stacking force distribution.

[0039] Combined with the contact point position and pressure value range, the contact point position of the cargo unit is adjusted successively to minimize the distance between the contact point and the bottom support point to ensure stability. The pressure distribution is calculated for the adjusted contact point position to solve the reasonable range of pressure values. The pressure formula is used to calculate the pressure distribution. Analyze the force of each contact point and calculate the support force based on the actual contact area of ​​the cargo unit It also verifies whether the pressure range is within the safe range, makes adjustments by comparing the contact points where the pressure values ​​are out of range, and finally re-evaluates the force distribution of the cargo stacking state to generate the cargo stacking force distribution.

[0040] See also Figure 5 , the specific steps for obtaining the optimized value of cargo stacking energy are as follows: S411: based on the force distribution of cargo stacking, extract the contact point pressure value and the center of gravity offset range, calculate the distribution characteristics of the pressure value in the spatial coordinates and its offset trend by analyzing the correlation between the contact point pressure data and the offset value, and generate the contact point pressure and center of gravity offset data; Based on the stress distribution of cargo stacking, it is first necessary to obtain the pressure value data of each contact point of the cargo during the stacking process. This can be done by monitoring the pressure distribution of the contact point through a stress sensor, using equipment to collect the force variation range of the contact point, and performing data cleaning and statistics through software tools. The center of gravity offset range is obtained by setting a three-dimensional coordinate system and combining measuring instruments to obtain the offset position range of the center of gravity of the cargo in the horizontal and vertical directions. These offset data are input into the statistical model for analysis through a calculation program, and the pressure value of the contact point and the cargo offset value are associated. The relationship model between the two is obtained through data fitting analysis. For example, the multivariate linear regression formula can be used. (in For the shift trend, is the contact point pressure value, The pressure is then reconstructed and the pressure distribution is analyzed. The pressure distribution is then analyzed and the pressure is reconstructed. The pressure distribution is then analyzed and the pressure is reconstructed. The pressure distribution is then analyzed and the pressure is reconstructed. The pressure distribution is then analyzed and the pressure distribution is analyzed. The pressure distribution is then analyzed and the pressure distribution is analyzed.

[0041] S412: calculating the center of gravity offset adjustment parameter according to the contact point pressure and center of gravity offset data, calculating the relationship between the pressure variation range and the offset value of each contact point based on the adjustment parameter, and establishing the contact point stacking matrix in combination with the geometric correlation between the contact points; According to the contact point pressure and center of gravity offset data, the center of gravity offset adjustment parameters need to be calculated first. The center of gravity offset adjustment parameters can be calculated by analyzing the offset degree of the goods between each stacking layer. In this process, the geometric position relationship of the contact points can be extracted using matrix analysis tools and the displacement between the contact points can be calculated. The offset trend can be further analyzed in combination with the pressure change range. For example, the offset change range of each contact point can be calculated by the formula (in are the coordinate values ​​of the two contact points), establish a correlation matrix between the offset value of each contact point and the pressure variation range, analyze the geometric correlation between the contact points through software, and optimize the geometric correlation matrix into a contact point stacking matrix that can be used for stacking relationship. The stacking matrix reflects the interaction force and displacement trend of each contact point, providing basic data for the next step of optimizing the stacking energy.

[0042] S413: combining the contact point stacking matrix, accumulating the stacking energy relationship value of each contact point, calculating the sum of the stacking energy through iterative optimization based on the energy relationship value of each contact point, integrating the energy accumulation relationship and performing matrix optimization operation to generate a stacking energy optimization matrix relationship; In combination with the contact point stacking matrix, it is necessary to perform cumulative analysis on the stacking energy relationship value of each contact point. First, according to the mechanical parameters in the contact point stacking matrix, the iterative calculation method is used to optimize the sum of the stacking energy. The stacking energy is calculated by analyzing the stress state of each contact point through the mechanical model formula, and the matrix accumulation method is used to integrate the energy relationship value of each contact point into a stacking energy optimization matrix relationship. The optimization operation of the matrix is ​​completed through a matrix sparse optimization algorithm. For example, the sparse algorithm can optimize the energy value distribution through the L1 regularization constraint term. The matrix relationship can reflect the overall trend of the stacking force between the contact points, and the stacking energy is further accumulated to obtain the optimization result.

[0043] S414: According to the stacking energy optimization matrix relationship, by analyzing the optimized value distribution of all contact points in the stacking energy matrix, accumulating the optimized energy results, using the formula: ; Calculate the total stacking energy value of all goods and generate the optimized value of goods stacking energy; in, Represents the final optimized energy value of the cargo stack, Representative The initial energy value of each contact point, Representative The center of gravity offset value of each contact point, is the mean of the center of gravity offsets of all contact points, is the weight of adjusting the intensity parameter to affect the offset on energy optimization, is the total number of all contact points.

[0044] formula: ; The benefit of the formula is that, by introducing the distribution characteristics of the center of gravity offset value and the weight influence of the offset mean, the optimization effect of the offset trend on the stacking energy can be effectively adjusted, thereby achieving a more reasonable energy distribution calculation.

[0045] Detailed explanation of the formula and the process of formula calculation and derivation: Parameter Description: Represents the total value of the optimized stacking energy, Representative The initial energy value of each contact point is collected by the sensor and calculated using the mechanical formula. Representative The center of gravity offset value of each contact point comes from the offset measuring instrument. Represents the mean value of the center of gravity offset of all contact points, which can be calculated by the formula Calculated, Represents the adjustment strength parameter, which is used to reflect the weighted impact of the offset value on the optimization energy. represents the total number of contact points, determined by the dimension of the stacking matrix, Represents the base of natural logarithms.

[0046] Parameter acquisition: :Acquire data through contact point pressure distribution monitoring and combine with mechanical formula (in For strength, is calculated as displacement).

[0047] : The center of gravity offset value of each contact point is directly measured through the three-dimensional coordinate system.

[0048] : Obtain the average value by counting the offset values ​​of each contact point.

[0049] :It is determined by the adjustment requirements of actual cargo stacking, and a reasonable range can be evaluated through adjustment simulation experiments, for example, between 0.5 and 2.0.

[0050] : Determined directly from the number of contact points of the stacking matrix.

[0051] Actual example: Assuming that the cargo stack contains 4 contact points, the initial energy value , offset value , adjustment coefficient .

[0052] Compute the shifted mean: ; Substitute the formula and calculate item by item: ; ; ; ; The total energy value after optimization: ; The results show that the optimized stacking energy value calculated by the optimization formula is 42.41. Compared with the initial energy value sum (45), it is more balanced after the weight adjustment, the energy distribution tends to be reasonable, and the stacking stability is improved.

[0053] See also Figure 6 , the specific steps for obtaining the cargo path planning parameter table are: S511: based on the cargo stacking energy optimization value, extract the three-dimensional positional relationship between the grabbing point and the placement point, calculate the distance and angle from the grabbing point to the placement point by analyzing the spatial coordinates of the cargo unit item by item, select the coordinate characteristic points that affect the spatial connection, and generate the positional relationship data between the grabbing point and the placement point; Based on the cargo stacking energy optimization value, the three-dimensional position relationship between the grabbing point and the placement point is extracted. By analyzing the spatial coordinates of the cargo units item by item, the three-dimensional coordinates of each cargo unit are split into the grabbing point coordinates ( ) and the placement point coordinates ( ), combined with the offset of the cargo center of gravity, the Euclidean distance between the grabbing point and the placement point is calculated using the following formula: , where each parameter is collected by the cargo unit positioning system. For example, the coordinates of the grabbing point of a cargo unit are (1.5, 2.0, 1.0), and the coordinates of the placement point are (3.0, 5.0, 2.5). Substituting them into the formula, we can get By calculating the relative spatial angle of the cargo unit and combining the center of gravity adjustment parameters (such as the angle offset of the stacked cargo), the cargo units that do not meet the stable grasping conditions are further screened out. For example, when the coordinates of the grasping point deviate from the geometric center of the cargo by more than a certain threshold (such as a 3° deviation range), the data marks that do not meet the conditions are removed, and the coordinates of the grasping points and placement points that meet the requirements are screened to generate the position relationship data of the grasping points and placement points; S512: using the positional relationship data between the grabbing point and the placement point, calculating the spatial priority value between the grabbing point and the obstacle point, analyzing the spatial distribution of each obstacle point, screening the key obstacle points according to the geometric characteristics of the obstacle point's impact on the path, eliminating the non-key obstacle points with low impact, and generating a spatial priority ranking of the obstacle points; Using the positional relationship data between the grabbing point and the placement point, the spatial priority value between the grabbing point and the obstacle point is calculated, and the three-dimensional coordinates of the obstacle point are marked as By analyzing the spatial distance between each obstacle point and the grasping path and combining the geometric characteristics of the obstacle point's impact on the path, the minimum distance to the grasping path is calculated. The formula is: ,in is the plane equation parameter of the grasping path. For example, the plane equation of the grasping path is , the coordinates of the obstacle point are (1,1,1), then ,Through the priority sorting of the minimum distance values ​​of all obstacle points, the obstacle points with larger distance values ​​are defined as lower priority points, and the points with smaller distance values ​​and densely distributed are defined as higher priority points.,Through the gradual screening of the degree of the impact of the obstacle points on the path, the obstacle points with lower priority and less impact are eliminated, and the spatial priority sorting of the obstacle points is generated; S513: According to the spatial priority ranking of the obstacle points, the spatial influence range of the lowest priority obstacle point is determined, and the improved formula is used: ; Calculate the impact of each obstacle point on the path and generate optimized obstacle point exclusion parameters for the grasping path; in, Represents the impact value of the obstacle point in the path, Indicates The importance of each obstacle point is determined by assigning differentiated weight values ​​to the importance of the path. is the distance between the obstacle point and the path, which is used to reflect the direct spatial impact of the obstacle point on the path. is a constant parameter used to avoid the situation where the denominator is zero when the obstacle point coincides with the path. It represents the indirect impact adjustment coefficient of the secondary obstacle point on the path, which is used to measure the superimposed impact intensity of the associated obstacle points. For the The main obstacle and The spatial distance between the secondary obstacle points is used to evaluate the indirect spatial effects of the relevant obstacle points. is the total number of all major obstacle points in the path, indicating the range of the number of major obstacle points. is the sum of the number of secondary obstacle points, indicating the complexity of the network associated with the primary obstacle points and the secondary obstacle points; formula: ; The benefit of the formula is that by introducing the influencing parameters of the main and secondary obstacles and combining the nonlinear calculation relationship between the weight value and the distance value, the direct and indirect impact of the obstacle on the path is comprehensively evaluated, which helps to more accurately optimize the obstacle elimination strategy in path planning; Detailed explanation of the formula and the process of formula calculation and derivation: Select the data of the obstacle point And grab the path plane data, and calculate the distance from each obstacle point to the path according to the minimum distance value in the previous formula , for example, the minimum distance to the main obstacle point is , weight value is the importance parameter of the path impact, which is obtained by evaluating the spatial distribution characteristics of the obstacle point and the path. The influence coefficient of the secondary obstacle point It is calculated by the superposition characteristics of the impact of secondary obstacles on the path. The specific value is determined by monitoring the interaction parameters between obstacles, such as the weight value of the main obstacle. , secondary obstacle point influence coefficient , the distance from the secondary obstacle point to the primary obstacle point , smoothing parameter , substituting into the formula we get: ; The result shows that the impact value of the obstacle point on the path is 1.226, which belongs to the range of high impact, so it is necessary to further optimize the obstacle point exclusion parameters to reduce its obstruction to the grasping path; S514: Based on the optimized obstacle elimination parameters of the grasping path, the position arrangement of the obstacle points in the grasping path is adjusted, the connection path characteristics between the grasping points and the placement points are calculated, and a cargo path planning parameter table is generated.

[0054] Combined with the optimized obstacle elimination parameters of the grasping path, the position arrangement of the obstacle points in the grasping path is adjusted, and the optimal angle connecting the distribution coordinates of the obstacle points and the path is calculated through the optimization model. By calculating the connection angle between the projection point of the obstacle point on the path and the grasping point to the placement point, the formula is: ,in is the vector between the grab point and the projection point, is the vector of the grab point and the placement point. For example, the grab point is (0,0,0), the obstacle point projection is (2,2,2), and the placement point is (4,4,4), then , , substitute into the formula , by adjusting the position of the projection point so that the angle value approaches the optimal angle range (such as within 5°), and finally generating a cargo path planning parameter table.

[0055] The fully automatic palletizing system based on machine vision and path planning is used to execute the above-mentioned fully automatic palletizing method based on machine vision and path planning. The system includes: The cargo feature extraction module extracts the cargo surface point cloud coordinates based on the cargo 3D point cloud data, calculates the normal vector and curvature value of the point cloud coordinates, determines the geometric segmentation range of the edge features, analyzes the fitting relationship between the boundary size and the curvature distribution, and generates the cargo geometric feature description value; The cargo shape classification module extracts the curvature distribution and boundary feature position based on the cargo geometric feature description value, calculates the Euclidean distance space range of the feature point, determines the geometric center position, analyzes the distribution variance range, classifies the feature set that meets the center distance and variance range, and generates the cargo shape classification coefficient; The stacking force analysis module extracts the coordinates of the center of gravity and the three-dimensional size range of the cargo based on the cargo shape classification coefficient, calculates the relationship between the center of gravity offset value and the size deviation, determines the distribution area of ​​the center of gravity offset and the force balance state, adjusts the position and pressure value range of the contact point, analyzes the mechanical distribution range of the contact point, and generates the cargo stacking force distribution; The stacking energy optimization module extracts the pressure value of the contact point and the center of gravity offset range based on the force distribution of the cargo stacking, calculates the center of gravity offset adjustment parameters and the contact point stacking matrix, accumulates the energy relationship value after stacking, establishes the stacking energy optimization matrix relationship, and generates the cargo stacking energy optimization value; The path planning module extracts the three-dimensional position relationship between the grabbing point and the placement point based on the cargo stacking energy optimization value, calculates the spatial priority value of the grabbing point and the obstacle point, analyzes the spatial influence range of the lowest priority obstacle point, optimizes the obstacle point exclusion parameters in the grabbing path, and generates a cargo path planning parameter table.

[0056] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A fully automatic palletizing method based on machine vision and path planning, characterized in that: The following steps are involved: S1: Based on the three-dimensional point cloud data of the cargo, the point cloud coordinates, normal vector and curvature value of the cargo surface are extracted, the geometric segmentation range of the point cloud edge features is calculated, the fitting relationship between the boundary size and the curvature distribution is calculated, and the multinomial distribution of the relationship between the boundary size and the curvature is used for verification to generate the cargo geometric feature description value; S2: Based on the cargo geometric feature description value, extract the cargo curvature distribution and boundary feature position, calculate the feature point spatial range of the Euclidean distance, determine the geometric center position and distribution variance range, classify and process the feature set that meets the center distance and variance range, and generate the cargo shape classification coefficient; S3: Based on the cargo shape classification coefficient, the cargo center of gravity coordinates and three-dimensional size range are extracted, the relationship between the cargo center of gravity coordinate offset and the size deviation is calculated, the distribution area of ​​the stacking center of gravity offset and the force balance state are determined, the contact point position and the pressure value range are adjusted, and the cargo stacking force distribution is generated; S4: based on the cargo stacking force distribution, extract the contact point pressure value and the center of gravity offset range, calculate the center of gravity offset adjustment parameter and the contact point stacking matrix, accumulate all the energy relationship values ​​after stacking, establish the stacking energy optimization matrix relationship of all the cargoes, and generate the cargo stacking energy optimization value; S5: Based on the cargo stacking energy optimization value, the three-dimensional position relationship between the grabbing point and the placement point is extracted, the spatial priority values ​​of the grabbing point and the obstacle point are calculated, the spatial influence range of the lowest priority obstacle point is determined, the obstacle point exclusion parameters in the grabbing path are optimized, and a cargo path planning parameter table is generated.

2. The fully automatic palletizing method based on machine vision and path planning according to claim 1 is characterized in that: The cargo geometric feature description value includes the cargo surface point cloud coordinates, normal vector, curvature value, boundary size, and curvature distribution fitting relationship; the cargo shape classification coefficient includes curvature distribution, boundary feature position, feature point spatial range, geometric center position, and distribution variance range; the cargo stacking force distribution includes contact point pressure value, center of gravity offset range, force balance state, contact point position, and pressure value range; the cargo stacking energy optimization value includes center of gravity offset adjustment parameter, contact point stacking matrix, energy relationship value after stacking, and stacking energy optimization matrix relationship; the cargo path planning parameter table includes grabbing point position, placement point position, grabbing point spatial priority value, obstacle point spatial priority value, lowest priority obstacle point spatial influence range, and obstacle point exclusion parameter.

3. The fully automatic palletizing method based on machine vision and path planning according to claim 2 is characterized in that: The steps for obtaining the cargo geometric feature description value are specifically as follows: S111: extracting the three-dimensional coordinates of each point in the cargo surface point cloud data, performing vector processing on the point cloud normal vector, calculating the curvature value of each point, analyzing the change trend of the curvature value in the point cloud point by point, removing abnormal points with excessive curvature changes, extracting a set of points with continuous distribution and smooth curvature in the point cloud, and generating cargo surface point cloud coordinates, normal vectors and curvature values; S112: Based on the point cloud coordinates and normal vector of the cargo surface, calculate the geometric angle difference between each point in the point cloud and the surrounding points, determine whether the geometric angle difference exceeds a set threshold, mark the points that meet the conditions as edge points, remove the points that do not meet the geometric conditions, re-analyze the boundary range of the remaining edge points, and generate a geometric segmentation range of the point cloud edge features; S113: Based on the boundary points in the geometric segmentation range of the edge features of the point cloud, the size distribution of the boundary points is calculated and the curvature value relationship is fitted, using the formula: ； Calculate the fitting relationship between the boundary size and the curvature value, and generate a multinomial distribution of the relationship between the boundary size and the curvature; in, Representative The curvature value of the boundary point, Representative The size value of the boundary point, represents the number of points in the curvature distribution range, represents the weight factor for each point in the curvature distribution, represents the smoothing parameter, The fitting function representing the boundary size and curvature value; S114: Calculate the deviation value of the curvature distribution according to the multinomial distribution of the relationship between the boundary size and the curvature, filter out abnormal data whose deviation value exceeds the fitting range, smooth the curvature distribution deviation value, re-verify the geometric consistency, and generate the cargo geometric feature description value.

4. The fully automatic palletizing method based on machine vision and path planning according to claim 3 is characterized in that: The steps for obtaining the cargo shape classification coefficient are specifically as follows: S211: extracting the curvature distribution and boundary feature positions of the cargo based on the cargo geometric feature description values, screening and extracting key points defining the cargo shape boundary by analyzing the change trend of the cargo surface curvature values ​​and combining the geometric distribution information of the boundary feature points, and generating a curvature distribution and boundary feature set; S212: using the curvature distribution and the boundary feature set, calculating the Euclidean distance from each feature point in the set to the geometric center of the cargo, constructing a geometric space model, analyzing the spatial concentration trend and outlier positions of the feature point distribution, and calibrating the spatial range of the feature points that meet the geometric conditions; S213: According to the spatial range of the feature points, determine whether each feature point is within a reasonable geometric center position and distribution variance range, using the formula: ； Calculate the geometric distance from the point to the center and evaluate the distribution deviation, classify and process the set of feature points that meet the conditions, and obtain the classified set of feature points; in, represents the Euclidean distance from the point to the geometric center, Represents the coordinates of the feature points, Represents the geometric center position of the feature point set, Represents the variance range of the feature point distribution, Represents the total number of feature point sets; S214: Analyze the statistical distribution characteristics according to the classified feature point set, combine with the geometric distribution model, calculate the spatial distribution parameters of the feature point set class by class, establish the classification standard of the cargo shape, and generate the cargo shape classification coefficient.

5. The fully automatic palletizing method based on machine vision and path planning according to claim 4 is characterized in that: The steps for obtaining the cargo stacking force distribution are specifically as follows: S311: extracting the center of gravity coordinates and three-dimensional size range of the cargo based on the cargo shape classification coefficient, calculating the geometric center position and the corresponding volume range by analyzing the shape characteristics of the cargo unit item by item, eliminating the abnormally offset shape characteristic data, and obtaining the center of gravity coordinates and size data set; S312: Calculate the center of gravity coordinate offset and size deviation of the cargo unit according to the center of gravity coordinate and size data set, compare the offset data with the standard distribution of its corresponding geometric center, select the offset characteristic points that match the center position, remove the data with deviation values ​​exceeding a reasonable range, and generate center of gravity coordinate offset and size deviation relationship data; S313: According to the data on the relationship between the center of gravity coordinate offset and the size deviation, the distribution area of ​​the center of gravity offset of the goods in the stacked state is evaluated using the formula: ； Calculate the offset of the cargo unit under the state of force balance, determine the balance stability of the stack through the offset characteristic points, and adjust the contact point position and pressure value range; in, Represents the offset measurement under the force equilibrium state, Respectively represent The coordinates of the center of gravity of each cargo unit on the x, y, and z axes, represents the mean coordinates of the center of gravity of all cargo units, Respectively represent the standard deviation of the x, y, and z coordinates, which are used to describe the degree of discreteness of the coordinate distribution. is the total number of cargo units involved in the calculation; S314: In combination with the contact point position and the pressure value range, the force position of the contact point and the contact area ratio are adjusted by measuring the pressure distribution multiple times, the adjusted stacking stability is evaluated, and finally a force distribution model of the cargo stacking is determined to generate the cargo stacking force distribution.

6. The fully automatic palletizing method based on machine vision and path planning according to claim 5 is characterized in that: The steps for obtaining the cargo stacking energy optimization value are specifically as follows: S411: Based on the force distribution of the cargo stack, the contact point pressure value and the center of gravity offset range are extracted, and the distribution characteristics of the pressure value in the spatial coordinates and its offset trend are calculated by analyzing the correlation between the contact point pressure data and the offset value, so as to generate the contact point pressure and center of gravity offset data; S412: calculating the center of gravity offset adjustment parameter according to the contact point pressure and center of gravity offset data, calculating the relationship between the pressure variation range and the offset value of each contact point based on the adjustment parameter, and establishing a contact point stacking matrix in combination with the geometric correlation between the contact points; S413: combining the contact point stacking matrix, accumulating the stacking energy relationship value of each contact point, calculating the sum of the stacking energies through iterative optimization based on the energy relationship values ​​of each contact point, integrating the energy accumulation relationship and performing matrix optimization operations to generate a stacking energy optimization matrix relationship; S414: According to the stacking energy optimization matrix relationship, by analyzing the optimized value distribution of all contact points in the stacking energy matrix, accumulating the optimized energy results, using the formula: ； Calculate the total stacking energy value of all goods and generate the optimized value of goods stacking energy; in, Represents the final optimized energy value of the cargo stack, Representative The initial energy value of each contact point, Representative The center of gravity offset value of each contact point, is the mean of the center of gravity offsets of all contact points, is the weight of adjusting the intensity parameter to affect the offset on energy optimization, is the total number of all contact points.

7. The fully automatic palletizing method based on machine vision and path planning according to claim 6 is characterized in that: The steps for obtaining the cargo path planning parameter table are specifically as follows: S511: Based on the cargo stacking energy optimization value, extract the three-dimensional positional relationship between the grabbing point and the placement point, analyze the spatial coordinates of the cargo unit item by item, calculate the distance and angle from the grabbing point to the placement point, select the coordinate characteristic points that affect the spatial connection, and generate the positional relationship data between the grabbing point and the placement point; S512: using the positional relationship data between the grabbing point and the placement point, calculating the spatial priority value between the grabbing point and the obstacle point, analyzing the spatial distribution of each obstacle point, screening the key obstacle points according to the geometric characteristics of the obstacle point's impact on the path, eliminating the non-key obstacle points with low impact, and generating a spatial priority ranking of the obstacle points; S513: According to the spatial priority ranking of the obstacle points, the spatial influence range of the lowest priority obstacle point is determined, and an improved formula is used: ； Calculate the impact of each obstacle point on the path and generate optimized obstacle point exclusion parameters for the grasping path; in, Represents the impact value of the obstacle point in the path, Indicates The importance of each obstacle point is determined by assigning differentiated weight values ​​to the importance of the path. is the distance between the obstacle point and the path, which is used to reflect the direct spatial impact of the obstacle point on the path. is a constant parameter used to avoid the situation where the denominator is zero when the obstacle point coincides with the path. It represents the indirect impact adjustment coefficient of the secondary obstacle point on the path, which is used to measure the superimposed impact intensity of the associated obstacle points. For the The main obstacle and The spatial distance between the secondary obstacle points is used to evaluate the indirect spatial effects of the relevant obstacle points. is the total number of all major obstacle points in the path, indicating the range of the number of major obstacle points. is the sum of the number of secondary obstacle points; S514: In combination with the optimized obstacle elimination parameters of the grasping path, the position arrangement of the obstacle points in the grasping path is adjusted, the connection path characteristics between the grasping points and the placement points are calculated, and a cargo path planning parameter table is generated by summarizing.

8. The fully automatic palletizing system based on machine vision and path planning is characterized by: According to any one of claims 1 to 7, the fully automatic palletizing method based on machine vision and path planning comprises: The cargo feature extraction module extracts the cargo surface point cloud coordinates based on the cargo 3D point cloud data, calculates the normal vector and curvature value of the point cloud coordinates, determines the geometric segmentation range of the edge features, analyzes the fitting relationship between the boundary size and the curvature distribution, and generates the cargo geometric feature description value; The cargo shape classification module extracts the curvature distribution and boundary feature position based on the cargo geometric feature description value, calculates the Euclidean distance space range of the feature point, determines the geometric center position, analyzes the distribution variance range, classifies the feature set that meets the center distance and variance range, and generates the cargo shape classification coefficient; The stacking force analysis module extracts the coordinates of the center of gravity and the three-dimensional size range of the cargo based on the cargo shape classification coefficient, calculates the relationship between the center of gravity offset value and the size deviation, determines the distribution area of ​​the center of gravity offset and the force balance state, adjusts the position and pressure value range of the contact point, analyzes the mechanical distribution range of the contact point, and generates the cargo stacking force distribution; The stacking energy optimization module extracts the pressure value of the contact point and the center of gravity offset range based on the cargo stacking force distribution, calculates the center of gravity offset adjustment parameter and the contact point stacking matrix, accumulates the energy relationship value after stacking, establishes the stacking energy optimization matrix relationship, and generates the cargo stacking energy optimization value; The path planning module extracts the three-dimensional position relationship between the grabbing point and the placement point based on the cargo stacking energy optimization value, calculates the spatial priority value of the grabbing point and the obstacle point, analyzes the spatial influence range of the lowest priority obstacle point, optimizes the obstacle point exclusion parameters in the grabbing path, and generates a cargo path planning parameter table.

Images