Intelligent cutting path planning method based on sprout eye position information

Abstract

The application discloses an intelligent cutting path planning method based on bud eye position information, relates to the technical field of bud eye cutting planning, and is used for solving the problems of unreasonable cutting position, breeding success rate reduction and cutting resource waste. A laser radar scanner is used to obtain a three-dimensional image of crops and mark positions, attribute data is collected to calculate active weight, water content is detected to analyze a target cutting path and generate a driving signal, the cutting area is determined, the bud eye barycenter offset degree and the aggregation degree are calculated, and the cutting utilization rate is generated. After the driving signal is detected, the cutting operation is started, the movement and stress data of the cutting tool are collected in real time, the offset rate and the abnormal impedance value are calculated, and it is judged whether the path switching mechanism is enabled. If the path switching mechanism is enabled, the cutting speed is detected, the adjacent cutting points are judged in combination with the cutting utilization rate, and the path is adjusted. The cutting utilization rate is calculated by comprehensively considering the active weight, the water content, the bud eye offset degree and the aggregation degree, the integrity of crops is ensured, and the cutting efficiency is maximized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bud eye cutting planning, more particularly, the present application relates to an intelligent cutting path planning method based on bud eye position information. BACKGROUND

[0002] At present, in the planting and processing process of agricultural crops (such as potatoes, sugarcane, etc.), there is a demand for pre-cutting of tuber crops to improve breeding efficiency or speed up subsequent processing links. With the continuous development of agricultural intelligent equipment, some devices begin to introduce visual recognition, force control feedback, laser mapping and other technologies for crop identification and processing path planning.

[0003] The prior art has the following disadvantages:

[0004] At present, the structure characteristics of crops, especially the distribution characteristics of bud eyes, cannot be finely processed, active identification and quantitative evaluation of bud eye information are lacking, and the influence of crop moisture content, texture and biological properties on cutting behavior is ignored, resulting in unreasonable cutting position, reduced breeding success rate and waste of cutting resources. Therefore, an intelligent cutting path planning method based on bud eye position information is proposed.

[0005] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide an intelligent cutting path planning method based on bud eye position information, which solves the problems raised in the above-mentioned background technology by using three-dimensional image recognition, bud eye activity modeling, moisture content analysis and cutting feedback regulation and control fusion mechanism.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical scheme, an intelligent cutting path planning method based on bud eye position information, comprising the following steps:

[0008] Step S1: obtaining a three-dimensional image of the crop to be cut by a laser radar scanner, finding a bud eye point and marking the position after pre-processing the three-dimensional image, collecting attribute data of the marked position, calculating the activity weight of the marked position according to the attribute data, the attribute data including bud eye field point density and bud eye depth;

[0009] Step S2: detecting the moisture content of the marked position, analyzing the target cutting path of the crop to be cut in combination with the activity weight of the marked position and generating a driving signal, determining the cutting block area according to the target cutting path and calculating the bud eye center of gravity offset degree and aggregation degree of the cutting block area, and generating the cutting utilization rate of the cutting block area by comprehensively considering the bud eye center of gravity offset degree and aggregation degree;

[0010] Step S3: After detecting the driving signal, the cutting operation is performed, the motion data and force data of the cutting tool are collected in real time, the offset rate and abnormal impedance value are calculated respectively, and whether to pass through the path switching mechanism is judged by comprehensively considering the offset rate and abnormal impedance value;

[0011] Step S4: When passing through the path switching mechanism, the cutting rate of the cutting tool is detected, the cutting utilization rate of the cutting block area is combined to judge the adjacent cutting point, and the target cutting path is adjusted based on the adjacent cutting point.

[0012] In a preferred embodiment, in step S1, a three-dimensional image of the crop to be cut is obtained by a laser radar scanner, comprising:

[0013] The product of the transmission speed of the laser beam and the time interval from emission to reception of the laser beam is divided by 2 to obtain the distance between the laser beam emission point and the pixel point on the surface of the crop to be cut;

[0014] Based on the distance between the laser beam emission point and the pixel point on the surface of the crop to be cut, the three-dimensional coordinates of the pixel point on the surface of the crop to be cut are calculated by a trigonometric function;

[0015] The three-dimensional coordinates of the pixel point on the surface of the crop to be cut are processed by a Poisson reconstruction algorithm to obtain a three-dimensional image of the crop to be cut.

[0016] In a preferred embodiment, after the three-dimensional image is preprocessed in step S1, the bud eye point is found and the position is marked, comprising:

[0017] The three-dimensional image of the crop to be cut is preprocessed by an outlier rejection method;

[0018] Each pixel point of the preprocessed three-dimensional image of the crop to be cut is taken as a target point, a space field with a predetermined radius is constructed around the target point, and the Z-axis height mean value of all pixel points in the space field is calculated;

[0019] The difference between the Z-axis height mean value of the target point and the Z-axis height mean value of all pixel points in the space field is taken as the bud eye characteristic value;

[0020] If the bud eye characteristic value is greater than or equal to 0, it is determined that the target point is not a bud eye point;

[0021] If the bud eye characteristic value is less than 0 and the absolute value of the bud eye characteristic value is greater than the Z-axis height mean value of all pixel points in the space field, it is determined that the target point is a bud eye point and the position is marked.

[0022] In a preferred embodiment, in step S1, attribute data of the marked position is collected, and the activity weight of the marked position is calculated according to the attribute data, comprising:

[0023] Traverse all pixels on the 3D image of the crop to be cut after preprocessing, and calculate the Euclidean distance from each pixel to the bud position.

[0024] If the Euclidean distance is less than or equal to the preset radius and The absolute value of the axis coordinate is greater than the position of the bud. The absolute value of the axis coordinate is used to determine whether a pixel belongs to the eye region;

[0025] Conversely, if the pixel does not belong to the bud eye region, then it is determined that the pixel does not belong to the bud eye region.

[0026] The total number of pixels belonging to the bud eye region is counted as the number of bud eye region points, and the density of bud eye region points is calculated in combination with the preset radius;

[0027] The absolute value of the bud eye feature value at the marked location is taken as the bud eye depth;

[0028] The bud activity weights were calculated after normalizing the density and depth of bud neighborhoods using the Max-Min normalization method.

[0029] In a preferred embodiment, step S2 involves detecting the water content at the marked location and analyzing the target cutting path of the crop to be cut based on the activity weight of the marked location, including:

[0030] The water content at the marked location is obtained by detecting the marked location using a plant-compatible capacitive moisture sensor;

[0031] The target cutting path of the crop to be cut is obtained based on the A-Star algorithm combined with the target cutting path constraint condition; the target cutting path constraint condition is:

[0032] If the moisture content at the marked location is less than or equal to a preset moisture content threshold and the activity weight at the marked location is less than or equal to a preset activity weight threshold, then the marked location is determined to be an impassable area.

[0033] If the moisture content at the marked location is greater than a preset moisture content threshold and the activity weight at the marked location is greater than a preset activity weight threshold, then the marked location is determined to be a preferred selection area.

[0034] If the moisture content at the marked location is less than or equal to a preset moisture content threshold and the activity weight at the marked location is greater than a preset activity weight threshold, then the marked location is determined to be a pass-avoided area.

[0035] In a preferred embodiment, step S2 involves determining the cutting area based on the target cutting path and calculating the bud centroid offset and aggregation degree of the cutting area, including:

[0036] According to the target cutting path of the to-be-cut crop, combined with the cutting width and cutting depth of the cutting tool, the part of the to-be-cut crop cut by the cutting tool is taken as a cutting block region;

[0037] The geometric center three-dimensional coordinates of the cutting block region are obtained by averaging the three-dimensional coordinates of each pixel point in the cutting block region.

[0038] The three-dimensional coordinates of the eyelet barycenter of the cutting block region are calculated by integrating the three-dimensional coordinates of all eyelet positions in the cutting block region.

[0039] The eyelet barycenter offset degree of the cutting block region is calculated according to the geometric center three-dimensional coordinates of the cutting block region and the three-dimensional coordinates of the eyelet barycenter of the cutting block region.

[0040] The aggregation degree of the cutting block region is calculated by the distance between all eyelet positions in the cutting block region.

[0041] In a preferred embodiment, the motion data and force data of the cutting tool are collected in real time in step S3, and the offset rate and abnormal impedance value are calculated respectively, including:

[0042] The position change of the guide rail shaft is monitored in real time by the absolute encoder of the cutting tool, and the position change value is read and converted into the actual position of the cutting tool; the offset amount is calculated by integrating the actual position of the cutting tool and the ideal position of the cutting tool at the same time, and normalized to obtain the offset rate;

[0043] The real-time feeding speed of the cutting tool is obtained by the servo motor controller, the difference between the real-time feeding speeds of the cutting tool at adjacent two times and the ratio of the real-time feeding speed at the previous time are calculated, and the absolute value is taken to obtain the abnormal impedance value.

[0044] In a preferred embodiment, in step S3, the offset rate and the abnormal impedance value are integrated to determine whether to turn on the path switching mechanism, including:

[0045] The product of the offset rate and the abnormal impedance value is taken as the path switching characteristic value;

[0046] If the path switching characteristic value is greater than the preset path switching threshold, the path switching mechanism is turned on;

[0047] If the path switching characteristic value is less than or equal to the preset path switching threshold, the path switching mechanism is not turned on.

[0048] In a preferred embodiment, step S4 detects the cutting rate of the cutting tool, judges the adjacent cutting point combined with the cutting utilization rate of the cutting block region, and adjusts the target cutting path based on the adjacent cutting point, including:

[0049] The real-time feeding speed of the cutting tool is taken as the cutting rate of the cutting tool;

[0050] obtaining all adjacent cutting point positions within the preset radius with the current cutting tool position as the center point and calculating the distance between all adjacent cutting point positions within the preset radius and the current cutting tool position;

[0051] comparing the cutting rate of the cutting tool and the cutting utilization rate of the cutting block area with the preset cutting rate threshold and the preset cutting utilization rate threshold respectively, and selecting different adjacent cutting points as the next cutting point of the current path to adjust the target cutting path.

[0052] The technical effects and advantages of the present application are:

[0053] The present application obtains a three-dimensional image of crops through a laser radar scanner, finds a bud eye point after preprocessing and marks the position, collects attribute data to calculate an activity weight, detects water content and analyzes a target cutting path to generate a driving signal, determines a cutting block area according to the target path, calculates a bud eye gravity center offset degree and an aggregation degree, generates a cutting utilization rate, detects the driving signal, starts the cutting operation, collects motion data and force data of the cutting tool in real time, calculates an offset rate and an abnormal impedance value, judges whether to enable a path switching mechanism, detects the cutting rate if the path switching mechanism is started, judges adjacent cutting points in combination with the cutting utilization rate, adjusts the target path based on the adjacent cutting points; the cutting utilization rate is calculated by combining multiple factors such as the activity weight, the water content, the bud eye gravity center offset degree and the aggregation degree, which can maximize the cutting efficiency while ensuring the integrity of the crops, and improves the precision of the cutting operation and the crop utilization rate. BRIEF DESCRIPTION OF DRAWINGS

[0054] Fig. 1 The present application is based on the intelligent cutting path planning method based on bud eye position information.

[0055] Fig. 2 The present application is based on the intelligent cutting path planning method based on bud eye position information. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0057] The application obtains a three-dimensional image of crops by a laser radar scanner, marks positions after preprocessing, collects attribute data to calculate active weight, detects water content and analyzes target cutting path to generate driving signal, determines cutting block area according to target path, calculates bud eye barycenter offset degree and aggregation degree, generates cutting utilization rate, starts cutting operation after detecting driving signal, collects motion data and force data of cutting tool in real time, calculates offset rate and abnormal impedance value, judges whether to enable path switching mechanism, detects cutting rate if the path switching mechanism is started, judges adjacent cutting points combined with cutting utilization rate, and adjusts target path based on adjacent cutting points.

[0058] Embodiment 1, intelligent cutting path planning method based on bud eye position information, as shown in Figs. 1-2 , includes the following steps:

[0059] Step S1: obtain a three-dimensional image of crops to be cut by a laser radar scanner, find bud eye points and mark positions after preprocessing the three-dimensional image, collect attribute data of the marked positions, and calculate active weight of the marked positions according to the attribute data;

[0060] Step S2: detect the water content of the marked positions, analyze the target cutting path of the crops to be cut combined with the active weight of the marked positions and generate driving signal, determine the cutting block area according to the target cutting path and calculate the bud eye barycenter offset degree and aggregation degree of the cutting block area, and generate the cutting utilization rate of the cutting block area by integrating the bud eye barycenter offset degree and aggregation degree;

[0061] Step S3: after detecting the driving signal, perform cutting operation, collect motion data and force data of the cutting tool in real time and calculate offset rate and abnormal impedance value respectively, and judge whether to enable path switching mechanism by integrating the offset rate and abnormal impedance value;

[0062] Step S4: when the path switching mechanism is enabled, detect the cutting rate of the cutting tool, judge adjacent cutting points combined with the cutting utilization rate of the cutting block area, and adjust the target cutting path based on the adjacent cutting points.

[0063] The specific implementation is as follows:

[0064] In step S1, the laser radar scanner continuously emits laser beams to the crop to be cut by rotating scanning, the laser beams are reflected and returned to the receiving unit of the laser radar scanner after encountering the surface of the crop to be cut, the receiving unit records the time interval from emission to reception of the laser beams, and the distance between the laser beam emission point of the laser radar scanner and the pixel point on the surface of the crop to be cut is obtained by dividing the product of the transmission speed of the laser beams and the time interval by 2, and the three-dimensional coordinates of the pixel point on the surface of the crop to be cut are calculated according to the preset installation information of the laser radar scanner and the distance between the laser beam emission point of the laser radar scanner and the pixel point on the surface of the crop to be cut through trigonometric functions.

[0065] It should be explained that the laser radar scanner is a device for determining the position of an object by emitting a laser beam and measuring the time difference of laser reflection to obtain the three-dimensional coordinates of the surface of the crop to be cut; the rotating scanning method is a scanning method in the laser radar, which is commonly used to obtain the three-dimensional information of the environment in all directions; the receiving unit is the core component of the laser radar system, which is used to receive the laser signal reflected from the surface of the object, and the installation information of the preset laser radar scanner refers to the installation position, angle, direction and other installation-related parameters of the laser radar sensor in the system, which are set by professionals according to the site implementation; the trigonometric function is a very important function in mathematics, which is mainly used to describe the relationship between angle and right triangle, in the present application, the sine function is used to calculate the distance between the laser beam emission point of the laser radar scanner and the pixel point on the surface of the crop to be cut and the vertical scanning angle of the laser radar to obtain the z-axis coordinate of the pixel point, and the cosine function is used to calculate the distance between the laser beam emission point of the laser radar scanner and the pixel point on the surface of the crop to be cut, the vertical scanning angle of the laser radar and the horizontal scanning angle of the laser radar to obtain the x-axis and y-axis coordinates of the pixel point;

[0066] The three-dimensional coordinates of the pixel points on the surface of the crop to be cut are processed by the Poisson reconstruction algorithm to obtain a three-dimensional image of the crop to be cut;

[0067] The three-dimensional image of the crop to be cut is preprocessed by the statistical outlier rejection method;

[0068] Each pixel point of the preprocessed three-dimensional image of the crop to be cut is taken as a target point, a space field with a preset radius is constructed around the target point, and the Z-axis height mean of all pixel points in the space field is calculated;

[0069] The difference between the Z-axis height mean of the target point and the Z-axis height mean of all pixel points in the space field is taken as the bud eye feature value;

[0070] If the bud eye feature value is greater than or equal to 0, it is determined that the target point is not a bud eye point;

[0071] If the bud eye feature value is less than 0 and the absolute value of the bud eye feature value is greater than the average Z-axis height of all pixels in the spatial domain, then the target point is determined to be a bud eye point and its position is marked.

[0072] Collect attribute data of the marked locations, including the density of bud eye points and the depth of bud eyes;

[0073] Traverse all pixels on the preprocessed 3D image of the crop to be cut, and calculate the Euclidean distance from each pixel to the bud position. The specific calculation formula is as follows:

[0074] ;

[0075] in, , and The third image of the crop to be cut The three-dimensional coordinates of each pixel , and Let be the three-dimensional coordinates of the bud position. Euclidean distance;

[0076] Based on the Euclidean distance and the preset radius:

[0077] If the Euclidean distance is less than or equal to the preset radius and The absolute value of the axis coordinate is greater than the position of the bud. The absolute value of the axis coordinate is used to determine whether a pixel belongs to the eye region;

[0078] Conversely, if the pixel does not belong to the bud eye region, then it is determined that the pixel does not belong to the bud eye region.

[0079] The total number of pixels belonging to the bud eye region is counted as the number of bud eye region points, and the bud eye region point density is calculated by combining this with a preset radius. The specific calculation formula is as follows: ,in For the preset radius, Count the number of points in the bud eye area. Density of dots in the bud eye area;

[0080] The absolute value of the bud eye feature value at the marked location is taken as the bud eye depth;

[0081] The density and depth of bud eyes in the vicinity are normalized using the Max-Min normalization method, and the calculation formula is as follows:

[0082] , ;

[0083] in, For the density of dots in the bud eye area, and a maximum value and a minimum value of the point density in the sprout eye field, a maximum value and a minimum value of the sprout eye depth, and a maximum value and a minimum value of the sprout eye depth, a normalized value of the point density in the sprout eye field, a normalized value of the sprout eye depth;

[0084] The greater the point density in the sprout eye field, the smoother the position around the sprout eye, and the better the growth state of the crop to be cut; the greater the sprout eye depth, the farther the position of the sprout eye from the surface of the crop to be cut, and the worse the growth state of the crop to be cut; the activity weight of the sprout eye is calculated by comprehensively considering the point density in the sprout eye field and the sprout eye depth, and the calculation formula is: wherein, a normalized value of the point density in the sprout eye field, a normalized value of the sprout eye depth, an activity weight of the sprout eye;

[0085] It needs to be explained that the Poisson reconstruction algorithm is an algorithm for generating a three-dimensional surface from point cloud data, which is used to obtain a three-dimensional image of the crop to be cut; the statistical outlier rejection method is a common method for identifying and rejecting outliers from a data set based on statistical principles, which is used for preprocessing the three-dimensional image of the crop to be cut; the preset radius is used to construct a space field, which is set by professionals; the Max-Min normalization method is a common data preprocessing method, which is used to scale the data to a specific range in proportion.

[0086] In step S2, the moisture content of the marked position is obtained by detecting the marked position by a plant-applicable capacitive moisture sensor;

[0087] The target cutting path of the crop to be cut is obtained based on the A-star algorithm combined with the target cutting path constraint condition;

[0088] The target cutting path constraint condition is:

[0089] If the moisture content of the marked position is less than or equal to the preset moisture content threshold and the activity weight of the marked position is less than or equal to the preset activity weight threshold, it is determined that the marked position is an impassable area;

[0090] If the moisture content of the marked position is greater than the preset moisture content threshold and the activity weight of the marked position is greater than the preset activity weight threshold, it is determined that the marked position is a priority selection area;

[0091] If the moisture content of the marked position is less than or equal to the preset moisture content threshold and the activity weight of the marked position is greater than the preset activity weight threshold, it is determined that the marked position is an area to be avoided;

[0092] It needs to be explained that the plant suitable type capacitive moisture sensor is a sensor for monitoring the moisture content in the soil, which is used to obtain the water content of the marked position; A-star is a classic algorithm widely used in path planning and graph search problems, which is used to obtain the target cutting path of the crop to be cut; The preset water content threshold and the activity weight threshold are used to determine the type of the marked position, which is set by professionals; The non-passable area refers to an area that cannot be crossed or passed in the field of path planning; The priority selection area refers to the selection of some areas or paths for exploration according to certain standards or targets among multiple available areas or paths; The avoidable area refers to the area that should be avoided in path planning, i.e. the area that needs to be avoided when performing tasks;

[0093] The target cutting path of the crop to be cut is analyzed to obtain specific control instructions of the cutting tool, and the specific control instructions of the cutting tool are converted into driving signals through a signal converter;

[0094] It should be noted that the specific analysis process is as follows: the target cutting path of the crop to be cut is converted into the movement path of the cutting tool in the area of the crop to be cut through a coordinate conversion algorithm, the angle requirement of the cutting tool is obtained according to the geometric characteristics of the target cutting path of the crop to be cut such as turning, straight line segment, etc., and finally the specific control instructions of the cutting tool are generated by the control instruction generation unit according to the movement path of the cutting tool in the area of the crop to be cut and the angle of the cutting tool;

[0095] According to the target cutting path of the crop to be cut, the cutting width and cutting depth of the cutting tool, the part of the crop to be cut cut down by the cutting tool is taken as the cutting block area;

[0096] The three-dimensional coordinates of the geometric center of the cutting block area are obtained by averaging the three-dimensional coordinates of each pixel point in the cutting block area;

[0097] The three-dimensional coordinates of the eye center of the cutting block area are calculated by integrating the three-dimensional coordinates of all eye positions in the cutting block area, and the three-dimensional coordinates of the eye center of the cutting block area are: , , wherein, , and is the three-dimensional coordinates of the th eye position in the cutting block area, is the number of eyes in the cutting block area, , and are the three-dimensional coordinates of the eye center of the cutting block area;

[0098] The bud eye center offset of the cutting block region is calculated according to the three-dimensional coordinates of the geometric center of the cutting block region and the three-dimensional coordinates of the bud eye center of the cutting block region, and the calculation formula is:

[0099] ;

[0100] wherein, 、 and are the three-dimensional coordinates of the bud eye center of the cutting block region, 、 and are the three-dimensional coordinates of the geometric center of the cutting block region, 、 、 、 、 and are the corresponding maximum value and minimum value on the axis of the cutting block region , and , is the bud eye center offset of the cutting block region;

[0101] The aggregation degree of the cutting block region is calculated by the distance between all bud eye positions in the cutting block region, and the aggregation degree of the cutting block region is: wherein, is the Euclidean distance between the bud eye position with subscript and the bud eye position with subscript , is the number of bud eyes in the cutting block region, is the aggregation degree of the cutting block region;

[0102] The cutting utilization rate of the cutting block region is calculated by integrating the bud eye center offset of the cutting block region and the aggregation degree of the cutting block region, and the cutting utilization rate of the cutting block region is: wherein is the bud eye center offset of the cutting block region, is the aggregation degree of the cutting block region, and are preset weighting coefficients, is the cutting utilization rate of the cutting block region;

[0103] The greater the bud eye center offset of the cutting block region, the more uneven the distribution of bud eyes in the cutting block region, and the smaller the cutting utilization rate of the cutting block region;

[0104] The greater the aggregation degree of the cutting block region, the more concentrated the distribution of bud eyes and the closer the distance between adjacent bud eyes, and the higher the cutting utilization rate of the cutting block region;

[0105] It needs to be explained that the control instruction is the instruction set required to perform an operation, the command used to instruct the cutting tool to perform a specific task in the intelligent cutting system, and the control instruction of the cutting tool is obtained through the analysis of the target cutting path, the assessment of the crop characteristics and the performance matching of the cutting tool, combined with the real-time feedback data; the signal converter is an electronic device that converts one type of signal into another type, which is used to convert the control instruction into a driving signal; the Euclidean distance is a method to measure the straight-line distance between two points in space; the preset weighting coefficient is used to adjust the influence of the bud eye barycenter deviation of the cutting block area and the aggregation degree of the cutting block area on the cutting utilization rate of the cutting block area, which is set by professionals.

[0106] In step S3, the motion data of the cutting tool refers to the physical parameters used to characterize the spatial motion state of the tool during the cutting operation, including the actual position of the cutting tool;

[0107] The position change of the guide rail shaft is monitored in real time by the absolute encoder of the cutting tool, and the position change value is read and converted into the actual position of the cutting tool;

[0108] The offset is calculated by combining the actual position of the cutting tool and the ideal position of the cutting tool at the same time, and the offset is: wherein, , and are the coordinate values of the actual position of the cutting tool, , and are the coordinate values of the ideal position of the cutting tool, is the offset;

[0109] The offset is normalized as the offset rate, and the offset rate is: wherein, is the offset at the t-th moment, is the total number of collection moments, is the offset rate at the t-th moment;

[0110] The force data of the cutting tool refers to the values of various physical forces borne by the cutting tool during the cutting process, including the real-time feed speed of the cutting tool; the real-time feed speed of the cutting tool is obtained through the servo motor controller, the difference between the real-time feed speeds of the cutting tool at adjacent two moments and the ratio of the real-time feed speed at the previous moment are calculated, and the absolute value is taken to obtain the feed speed variation rate, which is taken as the abnormal impedance value; It needs to be explained that there is a close internal relationship between the feed speed and the force data, the speed variation rate of the real-time feed speed of the cutting tool is a direct reflection of the force change, and the real-time feed speed can be used as a proxy value of the force data to help evaluate the load condition and performance of the tool during the cutting process;

[0111] The product of the offset rate and the abnormal impedance value is compared with a preset path switching threshold value as a path switching feature value to determine whether to switch the path:

[0112] If the path switching feature value is greater than the preset path switching threshold value, the path switching mechanism is turned on.

[0113] If the path switching feature value is less than or equal to the preset path switching threshold value, the path switching mechanism is not turned on.

[0114] It should be explained that the absolute encoder of the cutting tool is a device for accurately measuring the position of the cutting tool to obtain the actual position of the cutting tool; the preset path switching threshold value refers to a limit or standard set in advance in the intelligent control system to determine when the target path needs to be adjusted or switched, which is set by professionals; the path switching mechanism refers to adjusting the path or motion trajectory of the cutting equipment according to certain rules and algorithms when the cutting equipment deviates from the predetermined path or encounters impassable areas, to ensure the task is completed successfully according to the predetermined target.

[0115] In step S4, the real-time feeding speed of the cutting tool is taken as the cutting speed of the cutting tool.

[0116] Taking the current cutting tool position as the center point, all adjacent cutting point positions within the preset radius are obtained and the distances between the adjacent cutting point positions and the current cutting tool position within the preset radius are calculated.

[0117] The cutting speed of the cutting tool and the cutting utilization rate of the cutting block area are compared with the preset cutting speed threshold value and the preset cutting utilization rate threshold value, respectively.

[0118] If the cutting speed of the cutting tool is greater than the preset cutting speed threshold value and the cutting utilization rate of the cutting block area is greater than the preset cutting utilization rate threshold value, the adjacent cutting point with the maximum distance from the current cutting tool position is selected as the next cutting point of the current path to adjust the target cutting path.

[0119] If the cutting speed of the cutting tool is less than or equal to the preset cutting speed threshold value and the cutting utilization rate of the cutting block area is less than or equal to the preset cutting utilization rate threshold value, the adjacent cutting point with the minimum distance from the current cutting tool position is selected as the next cutting point of the current path to adjust the target cutting path.

[0120] When the cutting speed of the cutting tool is high and the cutting utilization rate of the cutting block area is high, the cutting tool can advance quickly, and the farthest adjacent cutting point can be selected to reduce the path adjustment frequency and continue to advance along the target path.

[0121] When the cutting speed of the cutting tool is low and the cutting utilization rate of the cutting area is low, the progress of the cutting tool is slow, and the path needs to be controlled more accurately, the nearest adjacent cutting point is selected, and the cutting accuracy and efficient use of resources are ensured by fine-tuning the path.

[0122] It should be explained that the adjacent cutting point refers to the point on the target cutting path that is close to the current cutting position and will be cut during the cutting process; the preset cutting speed threshold and the preset cutting utilization rate threshold are standards for judging whether the cutting operation meets the predetermined requirements, which are set by professionals and will not be described here.

[0123] Finally, it should be noted that in this document, the terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations.

[0124] Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of another identical element in the process, method, article or device that includes the element.

[0125] In this document, the singular forms "a", "an" and "the" can also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms "include", "contain" or "have" and the like specify the presence of the stated features, integers, steps, operations, components, parts or combinations thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, components, parts or combinations thereof. The possibility, while the term "and / or" used in this specification includes any and all combinations of the related listed items.

[0126] The various embodiments in the specification are described in a progressive manner, each embodiment focuses on the difference from other embodiments, and each embodiment can be combined as needed, and the same and similar parts refer to each other.

[0127] Those skilled in the art will appreciate that the foregoing description is by way of example only, and is not intended to limit the application solely thereto. Numerous modifications and adaptations will be apparent to those skilled in this art. Therefore, the true scope of the application is indicated by the appended claims, rather than by the foregoing description, and all modifications which come within the scope of the claims are intended to be embraced therein.

Claims

1. An intelligent bud-eye location information-based slicing path planning method, characterized in that: Includes the following steps: Step S1: Acquire a three-dimensional image of the crop to be cut using a LiDAR scanner. After preprocessing the three-dimensional image, locate and mark the bud eyes. Collect attribute data of the marked locations. Calculate the activity weight of the marked locations based on the attribute data. The attribute data includes the density of bud eye neighborhood points and the depth of bud eyes. Step S2: Detect the moisture content at the marked position, analyze the target cutting path of the crop to be cut by combining the activity weight of the marked position and generate a driving signal, determine the cutting area according to the target cutting path and calculate the bud centroid offset and aggregation degree of the cutting area, and generate the cutting utilization rate of the cutting area by combining the bud centroid offset and aggregation degree. In step S2, the cutting area is determined according to the target cutting path, and the bud centroid offset and cohesion of the cutting area are calculated, including: Based on the target cutting path of the crop to be cut, and combined with the cutting width and cutting depth of the cutting tool, the portion of the crop to be cut off by the cutting tool is taken as the cutting area; The three-dimensional coordinates of the geometric center of the segmented region are obtained by averaging the three-dimensional coordinates of each pixel in the segmented region. The three-dimensional coordinates of the centroid of the buds in the cutting area are calculated by combining the three-dimensional coordinates of all bud positions in the cutting area. The offset of the centroid of the bud in the cutting area is calculated based on the three-dimensional coordinates of the geometric center of the cutting area and the three-dimensional coordinates of the centroid of the bud in the cutting area. The degree of aggregation of the cutting area is calculated by the distance between all bud positions within the cutting area; Step S3: After detecting the drive signal, perform the cutting operation, collect the motion data and force data of the cutting tool in real time, and calculate the offset rate and abnormal impedance value respectively. Combine the offset rate and abnormal impedance value to determine whether to enter the path switching mechanism. Step S4: When the path switching mechanism is activated, the cutting rate of the cutting tool is detected, and the adjacent cutting points are determined based on the cutting utilization rate of the cutting area. The target cutting path is then adjusted based on the adjacent cutting points.

2. The intelligent slicing path planning method based on bud position information according to claim 1, characterized in that, In step S1, a three-dimensional image of the crop to be cut is acquired using a lidar scanner, including: Divide the product of the laser beam's transmission speed and the time interval between the laser beam's emission and reception by 2 to obtain the distance between the laser beam emission point and the pixel on the surface of the crop to be cut. Based on the distance between the laser beam emission point and the pixel points on the surface of the crop to be cut, the three-dimensional coordinates of the pixel points on the surface of the crop to be cut are calculated using trigonometric functions. The Poisson reconstruction algorithm is used to process the three-dimensional coordinates of the pixels on the surface of the crop to be cut, thereby obtaining a three-dimensional image of the crop.

3. The intelligent bud-eye location information-based slicing path planning method according to claim 1, characterized in that, In step S1, after preprocessing the 3D image, the bud eye points are located and their positions are marked, including: The three-dimensional image of the crop to be cut is preprocessed by statistical outlier removal method; Each pixel of the preprocessed 3D image of the crop to be cut is used as the target point. A spatial domain with a preset radius is constructed with the target point as the center, and the average Z-axis height of all pixels in the spatial domain is calculated. The difference between the average Z-axis height of the target point and the average Z-axis height of all pixels in the spatial domain is used as the bud eye feature value; If the bud eye feature value is greater than or equal to 0, then the target point is determined not to be a bud eye point; If the bud eye feature value is less than 0 and the absolute value of the bud eye feature value is greater than the average Z-axis height of all pixels in the spatial domain, then the target point is determined to be a bud eye point and its position is marked.

4. The intelligent bud-eye location information-based block-cutting path planning method according to claim 1, characterized in that, In step S1, attribute data of the marked locations is collected, and the activity weight of the marked locations is calculated based on the attribute data, including: Traverse all pixels on the 3D image of the crop to be cut after preprocessing, and calculate the Euclidean distance from each pixel to the bud position. If the Euclidean distance is less than or equal to the preset radius and the absolute value of the Z-axis coordinate is greater than the absolute value of the Z-axis coordinate of the bud position, then the pixel is determined to belong to the bud region. Conversely, if the pixel does not belong to the bud eye region, then it is determined that the pixel does not belong to the bud eye region. The total number of pixels belonging to the bud eye region is counted as the number of bud eye region points, and the density of bud eye region points is calculated in combination with the preset radius; The absolute value of the bud eye feature value at the marked location is taken as the bud eye depth; The bud activity weights were calculated after normalizing the density and depth of bud neighborhoods using the Max-Min normalization method.

5. The intelligent slicing path planning method based on bud position information according to claim 1, characterized in that, In step S2, the water content at the marked location is detected, and the target cutting path of the crop to be cut is analyzed based on the activity weight of the marked location, including: The water content at the marked location is obtained by detecting the marked location using a plant-compatible capacitive moisture sensor; The target cutting path of the crop to be cut is obtained based on the A-Star algorithm combined with the target cutting path constraint condition; the target cutting path constraint condition is: If the moisture content at the marked location is less than or equal to a preset moisture content threshold and the activity weight at the marked location is less than or equal to a preset activity weight threshold, then the marked location is determined to be an impassable area. If the moisture content at the marked location is greater than a preset moisture content threshold and the activity weight at the marked location is greater than a preset activity weight threshold, then the marked location is determined to be a preferred selection area. If the moisture content at the marked location is less than or equal to a preset moisture content threshold and the activity weight at the marked location is greater than a preset activity weight threshold, then the marked location is determined to be a pass-avoided area.

6. The intelligent slicing path planning method based on bud position information according to claim 1, characterized in that, In step S3, the motion data and force data of the cutting tool are acquired in real time, and the offset rate and abnormal impedance value are calculated respectively, including: The absolute encoder of the cutting tool monitors the position change of the guide shaft in real time, and reads the position change value to convert it into the actual position of the cutting tool; the offset is calculated by combining the actual position of the cutting tool and the ideal position of the cutting tool at the same moment, and then normalized to obtain the offset rate. The real-time feed speed of the cutting tool is obtained by the servo motor controller. The ratio of the difference between the real-time feed speeds of the cutting tool at two adjacent moments to the real-time feed speed at the previous moment is calculated, and the absolute value is taken to obtain the abnormal impedance value.

7. The intelligent slicing path planning method based on bud position information according to claim 1, characterized in that, In step S3, the determination of whether to initiate the path switching mechanism is based on a combination of offset rate and abnormal impedance value, including: The product of the offset rate and the abnormal impedance value is used as the path switching characteristic value; If the path switching characteristic value is greater than the preset path switching threshold, the path switching mechanism will be activated. If the path switching characteristic value is less than or equal to the preset path switching threshold, the path switching mechanism will not be activated.

8. The intelligent slicing path planning method based on bud position information according to claim 1, characterized in that, Step S4 detects the cutting rate of the cutting tool, determines adjacent cutting points based on the cutting utilization rate of the cutting area, and adjusts the target cutting path based on the adjacent cutting points, including: The real-time feed rate of the cutting tool is used as the cutting rate of the cutting tool; Using the current cutting tool position as the center point, obtain the positions of all neighboring cutting points within a preset radius and calculate the distance between the positions of all neighboring cutting points within the preset radius and the current cutting tool position; The cutting speed of the cutting tool and the cutting utilization rate of the cutting area are compared with the preset cutting speed threshold and the preset cutting utilization rate threshold, respectively. Different neighboring cutting points are selected as the next cutting point of the current path to adjust the target cutting path.

Images