Excavator bucket adjusting method and device and excavator

Abstract

The invention discloses an excavator bucket adjusting method and device and an excavator, and relates to the technical field of operation machinery. The excavator bucket adjusting method comprises the steps that in response to an automatic control instruction, the pitch angle of a bucket and the inclination angle of materials are obtained in real time; based on the pitch angle of the bucket and the inclination angle of the material, a cut-in angle estimation value is obtained; and adjusting the attitude of the bucket of the excavator based on the estimated value of the cut-in angle. The cut-in angle, namely the cut-in angle estimated value, of the bucket relative to the material can be determined through the pitch angle of the bucket and the inclination angle of the material, the cut-in angle estimated value serves as a target reference for adjusting the posture of the bucket or the small arm, self-adaptive positioning and adjustment of the cut-in angle at the moment when the bucket makes contact with the material are achieved, cut-in is more accurate, and the work efficiency is improved. The cutting-in failure or rebounding risk is reduced, and the operation efficiency and the operation safety are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of working machines, in particular to a method for adjusting a bucket of an excavator, an adjusting device for the bucket of the excavator, and an excavator. BACKGROUND

[0002] When the excavator is performing the excavating operation, the operator needs to coordinate the combined actions of the three main oil cylinders of the boom, the stick, and the bucket in real time and dynamically according to the properties (such as hardness, viscosity, and looseness) of the material and the specific operation target (such as efficient excavation, precise grading, and ditching and slope repairing), to adjust the posture of the bucket or the stick (the stick), so that the bucket teeth can form an optimal cutting-in angle and move along an efficient cutting trajectory at the moment of contacting the material.

[0003] The existing adjustment method mainly relies on manual experience, which is susceptible to the operator's level and the on-site environment, and the efficiency and safety are difficult to guarantee, especially in extreme working conditions such as gravel, the risk of cutting failure or rebound is significant. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a method for adjusting a bucket of an excavator, an adjusting device for the bucket of the excavator, and an excavator, to solve the problem that the existing technology relies on manual experience to adjust the cutting-in angle, which is susceptible to the operator's level and the on-site environment, and the efficiency and safety are difficult to guarantee.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a method for adjusting a bucket of an excavator, comprising: in response to an automatic control instruction, acquiring the pitch angle of the bucket and the inclination angle of the material in real time; based on the pitch angle of the bucket and the inclination angle of the material, obtaining a cutting-in angle estimation value; based on the cutting-in angle estimation value, adjusting the posture of the bucket of the excavator.

[0006] In the embodiments of the present application, the adjusting the posture of the bucket of the excavator based on the cutting-in angle estimation value comprises: determining whether the cutting-in angle estimation value meets a preset cutting-in angle condition; in a case where it is determined that the cutting-in angle estimation value meets the preset cutting-in angle condition, controlling the excavator to keep the current posture of the bucket and perform the excavating operation; in a case where it is determined that the cutting-in angle estimation value does not meet the preset cutting-in angle condition, adjusting the posture of the bucket of the excavator.

[0007] In the embodiments of the present application, the determining whether the cutting-in angle estimation value meets the preset cutting-in angle condition comprises: acquiring the type of the material; determine a recommended cutting-in angle corresponding to the material based on a type of the material; compare the cutting-in angle estimation value with the recommended cutting-in angle corresponding to the material to obtain a comparison result; judge whether the cutting-in angle estimation value meets a preset cutting-in angle condition based on the comparison result.

[0008] In the embodiments of the present application, the adjusting the bucket posture of the excavator in the case where it is determined that the cutting-in angle estimation value does not meet the preset cutting-in angle condition comprises: In the case where it is determined that the cutting-in angle estimation value does not meet the preset cutting-in angle condition, calculate a difference value between the cutting-in angle estimation value and a preset recommended cutting-in angle value to obtain an error value; adjust the bucket posture of the excavator based on the error value.

[0009] In the embodiments of the present application, the obtaining the pitch angle of the bucket comprises: obtain bucket point cloud data and a three-dimensional model of the bucket; register the bucket point cloud data and the three-dimensional model of the bucket to obtain a transformation matrix; obtain the pitch angle of the bucket based on the transformation matrix.

[0010] In the embodiments of the present application, the obtaining the dip angle of the material comprises: obtain work area point cloud data; determine a candidate cutting-in region based on the work area point cloud data; perform plane fitting on the candidate cutting-in region to obtain a fitting plane; calculate an included angle between a normal vector of the fitting plane and a horizontal plane to obtain the dip angle of the material.

[0011] In the embodiments of the present application, the determining a candidate cutting-in region based on the work area point cloud data comprises: divide a plurality of sub-regions in the work area point cloud data based on a region growing segmentation method; determine a selectable cutting-in region in the plurality of sub-regions based on surface curvatures of the sub-regions; perform visibility evaluation on the selectable cutting-in region to obtain a visibility degree value of the selectable cutting-in region; determine a candidate cutting-in region based on the visibility degree value of the selectable cutting-in region.

[0012] In the embodiments of the present application, the performing visibility evaluation on the selectable cutting-in region to obtain a visibility degree value of the selectable cutting-in region comprises: An angle between a normal vector of the optional cutting-in region and the virtual central optical axis is calculated to obtain a visible angle of the optional cutting-in region. A visible degree value of the optional cutting-in region is obtained based on the visible angle of the optional cutting-in region.

[0013] In the embodiments of the present application, in the case of the working scene being a gravel scene, an inclination angle of the material is obtained, including: Obtaining working region point cloud data; Segmenting the working region point cloud data to obtain a plurality of local point cloud regions; Fitting a plane to each local point cloud region to obtain a plurality of local fitting planes; An angle between a normal vector of each local fitting plane and a horizontal plane is calculated to obtain an inclination angle corresponding to each local fitting plane; A weighted average of the inclination angles corresponding to each local fitting plane is obtained to obtain the inclination angle of the material.

[0014] In the embodiments of the present application, an inclination angle of the material is obtained, including: Obtaining an initial inclination angle of the material; Obtaining a cutting-in resistance estimation value; Based on the cutting-in resistance estimation value, the initial inclination angle of the material is corrected to obtain the inclination angle of the material.

[0015] In the embodiments of the present application, further comprising: In the case of detecting a manual control signal, stopping responding to the automatic control instruction.

[0016] The second aspect of the present application provides a shovel adjusting device of an excavator, including: An obtaining module is configured to obtain, in real time, a pitch angle of a shovel and an inclination angle of a material in response to an automatic control instruction; A calculation module is configured to obtain a cutting-in angle estimation value based on the pitch angle of the shovel and the inclination angle of the material; A control module is configured to adjust a posture of the shovel of the excavator based on the cutting-in angle estimation value.

[0017] The third aspect of the present application provides an excavator, which adopts the above-mentioned shovel adjusting method to adjust the posture of the shovel when the excavator performs a digging operation on the material.

[0018] By the technical solution, the dip angle of the material and the pitch angle of the bucket are acquired in real time in response to the automatic control instruction; the cut-in angle estimation value is obtained based on the pitch angle of the bucket and the dip angle of the material; and the bucket posture of the excavator is adjusted based on the cut-in angle estimation value. The cut-in angle of the bucket relative to the material, i.e., the cut-in angle estimation value, can be determined by the pitch angle of the bucket and the dip angle of the material. By taking the cut-in angle estimation value as a target reference for adjusting the bucket or the arm posture, adaptive positioning and adjustment of the cut-in angle of the bucket at the instant of contact with the material are realized, so that the cut-in is more accurate, the risk of cut-in failure or rebound is reduced, and the operation efficiency and operation safety are improved.

[0019] Other features and advantages of the embodiments of the present application will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings are included to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the embodiments of the present application together with the following specific embodiments, but do not constitute a limitation of the embodiments of the present application. In the drawings: Figure 1 A flowchart of a bucket adjustment method of an excavator according to an embodiment of the present application is schematically shown; Figure 2 An excavating operation diagram of an excavator according to an embodiment of the present application is schematically shown; Figure 3 A closed-loop flowchart of a bucket adjustment of an excavator according to an embodiment of the present application is schematically shown; Figure 4 A general framework diagram of a bucket adjustment system of an excavator according to an embodiment of the present application is schematically shown; Figure 5 A structure diagram of a bucket adjustment device of an excavator according to an embodiment of the present application is schematically shown.

[0021] Explanation of reference signs 410-acquisition module; 420-computation module; 430-control module. DETAILED DESCRIPTION

[0022] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, 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. It should be understood that the specific embodiments described herein are only used to explain and explain the embodiments of the present application, and do not limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0023] It should be noted that the acquisition, transmission, storage, use, processing and the like of data in the technical solutions of the present application comply with the relevant provisions of laws and regulations. In the embodiments of the present application, some existing industry solutions such as software, components, models and the like may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility in the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solutions.

[0024] It should be noted that if the directionality indication (such as up, down, left, right, front, back, etc.) is involved in the embodiments of the present application, the directionality indication is only used to explain the relative position relationship, motion condition and the like between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directionality indication also changes accordingly.

[0025] In addition, if the description of "first", "second" and the like is involved in the embodiments of the present application, the description of "first", "second" and the like is only for the purpose of description, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, nor within the scope of protection claimed by the present application.

[0026] Figure 1 A flowchart of a method for adjusting a bucket of an excavator according to an embodiment of the present application is schematically shown. As shown in Figure 1 The method for adjusting a bucket of an excavator according to an embodiment of the present application can include the following steps: Step 210: In response to an automatic control instruction, the pitch angle of the bucket and the inclination angle of the material are acquired in real time; In the present embodiment, the automatic control instruction can be issued by the operator operating the automatic control button, or the automatic control instruction can be automatically triggered. For example, when it is detected that the single boom of the excavator is lowered, the pitch angle of the bucket and the inclination angle of the material are acquired in real time. Please refer to Figure 2 , Figure 2A schematic diagram of a digging operation of a shovel is shown. The pitch angle of the bucket refers to the pitch angle of the bucket relative to the world coordinate system or the vehicle coordinate system, which can refer to the angle of the bucket tilting around an axis (usually the left-right direction axis), which determines the posture of the bucket cutting into the material. For example, based on the actual scene of the excavator, the posture of the bucket can be defined in the order of XYZ (Roll-Pitch-Yaw), Roll is the roll angle, corresponding to rotation around the X axis, Pitch is the pitch angle, corresponding to rotation around the Y axis, and Yaw is the yaw angle, corresponding to rotation around the Z axis. The pitch angle of the material refers to Pitch. The pitch angle of the material refers to the maximum angle between the conical slope of the material in the natural state and the horizontal ground. The material refers to the material excavated by the excavator, including loose soil, clay, medium-hard soil, gravel / mixed stone, etc. The pitch angle of the bucket and the pitch angle of the material can be obtained by installing a pitch sensor to collect in real time, or can be obtained based on visual recognition.

[0027] In some embodiments, the pitch angle of the bucket is obtained by: First, obtain the bucket point cloud data and the three-dimensional model of the bucket. In this embodiment, the bucket point cloud data can be obtained by setting a binocular vision acquisition module to collect in real time, which can directly collect the bucket point cloud data, or can separate the bucket area from the point cloud based on semantic segmentation or geometric constraints, and extract the clustered point set to obtain the bucket point cloud data. The binocular vision acquisition module can include a multi-view camera, such as two high-frame-rate (≥60 fps), global shutter industrial cameras fixed on the top of the cab by a sturdy bracket, with a baseline distance of about 20 cm, covering the bucket and the material pile area. By synchronously triggering two industrial cameras to collect, a semi-global matching or deep learning stereo matching algorithm (such as GA-Net) is used to generate a high-density disparity map, and output dense point cloud data with a resolution of up to tens of thousands of valid points per square meter. Then, the bucket area can be segmented in the dense point cloud data, and the Euclidean cluster (Euclidean Cluster) method is applied to extract the clustered point set, i.e. the bucket point cloud data can be obtained. The three-dimensional model of the bucket is a standard three-dimensional model of the working device of the excavator, such as the posture model when the excavator is not working, which can be obtained by using a three-dimensional modeling software such as CAD, and belongs to the prior art, which will not be described here.

[0028] Then, the bucket point cloud data and the three-dimensional model of the bucket are registered to obtain a transformation matrix. In the embodiment, the registration is achieved by finding the optimal rotation and translation parameters so that the 3D model of the bucket can be aligned with the real scanned bucket point cloud in space after the 3D model of the bucket is converted by the transformation matrix. Specifically, the 3D model of the bucket can be substituted into the bucket point cloud data, and the cluster points in the bucket point cloud data can be registered with the 3D model of the bucket. The registration can be achieved by using one or more registration algorithms. For example, the cluster points in the bucket point cloud data can be coarsely registered with the 3D model of the bucket by using the iterative closest point (ICP) algorithm, and then the extracted feature points (such as the tip of the bucket and the center of the hinge) can be used for fine registration, so that the registration is more accurate. The registration process can be achieved by using existing technologies, and thus will not be described here. After the registration is completed, the transformation matrix can be obtained.

[0029] Finally, based on the transformation matrix, the pitch angle of the bucket can be obtained.

[0030] In the embodiment, the transformation matrix contains a rotation matrix specially describing the bucket, and the rotation matrix contains three rotation angles of the bucket: pitch, yaw, and roll. A value can be extracted from a specific number in the rotation matrix (such as the number in the first column of the third row) to determine the degree of up-and-down inclination of the bucket. The value can be directly converted into an angle by a mathematical operation (inverse trigonometric function), and the angle can be converted to the bucket relative to the world coordinate system or the vehicle coordinate system, that is, the pitch angle of the bucket can be obtained.

[0031] It should be noted that the camera can take many frames (more than 60 frames) per second, and an angle can be calculated for each frame. However, the point cloud can have noise (such as jitter or occlusion), which can cause the angle to jump. Therefore, Kalman filtering can be added between consecutive frames to achieve smooth output of the pitch angle of the bucket and suppress jitter.

[0032] By registering the bucket point cloud data and the 3D model of the bucket, the accurate transformation relationship from the 3D model coordinate system of the bucket to the excavator / world coordinate system can be determined, so that the accurate pitch angle of the bucket can be obtained based on the transformation matrix. Meanwhile, the method can be achieved without sensors, which reduces the hardware cost.

[0033] In some embodiments, the inclination of the material is obtained, including: First, the point cloud data of the working area is obtained. In this embodiment, the point cloud data of the aforementioned work area can be acquired in real time by setting up a binocular vision acquisition module. This can be done by directly acquiring the work area or by separating the work area from the point cloud based on semantic segmentation or geometric constraints. For example, two high frame rate (≥60fps) global shutter industrial cameras can be fixed on the top of the cab using a robust bracket, with a baseline distance of approximately 20cm, covering the bucket and material pile areas. Acquisition is triggered synchronously by the two industrial cameras, and a high-density disparity map is generated using a semi-global matching or deep learning stereo matching algorithm (such as GA-Net), outputting dense point cloud data with a resolution of tens of thousands of effective points per square meter. The dense point cloud data can then be preprocessed to segment out the work area. This preprocessing includes filtering and noise reduction, ground and interference removal, etc., which can be achieved using existing technologies, such as using voxel grid filtering and statistical outlier removal to simplify the point cloud and ensure the real-time performance and robustness of subsequent algorithms. The aforementioned ground and interference removal can be based on known camera tilt information and a ground model to remove ground and distant interference, thereby locating the work area. Specifically, a ground model can be built using known camera extrinsic parameters, and a large-area ground point cloud can be identified using a plane fitting algorithm. This allows all points that meet the ground plane conditions to be removed, avoiding interference with the fitting of the material area. Simultaneously, considering the work area requirements, far-field points exceeding a preset distance in the point cloud can be cropped, retaining only the near-field point cloud within the bucket's working area. This achieves precise positioning and data purification of the work area, resulting in accurate point cloud data for the work area.

[0034] Then, based on the point cloud data of the work area, candidate entry areas are determined; In this embodiment, after obtaining the point cloud of the working area, the area that the bucket can cut into can be determined from the point cloud.

[0035] In some embodiments, determining the candidate entry region based on the point cloud data of the work area includes: The first step is to divide the point cloud data of the work area into multiple sub-regions based on the region growing segmentation method; In this embodiment, the material surface can be divided into multiple sub-regions in the point cloud data of the working area based on the region growth segmentation method. The aforementioned region growth segmentation method is prior art and will not be described in detail here.

[0036] The second step is to determine the selectable cutting areas in the multiple sub-regions based on the surface curvature of each sub-region. In this embodiment, surface curvature represents the overall flatness / curvature of the region. Regions with smaller curvature are considered to have better flatness and are suitable as potential entry surfaces, thus obtaining selectable entry regions. The surface curvature of each sub-region can be calculated by searching for multiple nearest neighbor points in the sub-region, calculating the three-dimensional covariance matrix of the points in the region, obtaining the eigenvalues ​​of the three-dimensional covariance matrix, and then calculating the surface curvature of the sub-region using the curvature calculation formula based on the eigenvalues. The above-mentioned process for calculating the surface curvature of the sub-region is prior art and will not be described in detail here.

[0037] The third step is to evaluate the visibility of the optional cut-in area to obtain the visibility value of the optional cut-in area; In this embodiment, the aforementioned visibility assessment may refer to assessing the visibility of the point cloud surface toward the camera.

[0038] The step of evaluating the visibility of the selectable cut-in area to obtain a visibility value for the selectable cut-in area includes: First, calculate the angle between the normal vector of the optional cutting area and the virtual central optical axis to obtain the visible angle of the optional cutting area; In this embodiment, the normal vector of the selectable cutting area represents the orientation of the surface of the selectable cutting area, while the virtual central optical axis is the central direction of the excavator's operation. By calculating the angle between the two, it is actually measuring whether the surface of the selectable cutting area is facing the excavator.

[0039] Then, based on the viewing angle of the optional cut-in area, the visibility value of the optional cut-in area is obtained.

[0040] In this embodiment, the viewing angle of the selectable cut-in area can be used as the visibility value of the selectable cut-in area.

[0041] By calculating the angle between the normal vector of the optional cutting area and the virtual central optical axis, the visibility angle of the optional cutting area is obtained. Based on the visibility angle of the optional cutting area, it is possible to accurately measure whether the surface of the optional cutting area is facing the excavator, that is, to accurately obtain the visibility value of the optional cutting area.

[0042] The fourth step is to determine the candidate cutting areas based on the visibility values ​​of the selectable cutting areas.

[0043] In this embodiment, the visibility value of the selectable cut-in area can be compared with a preset threshold to filter out selectable cut-in areas with higher visibility as candidate cut-in areas. For example, when the included angle is less than the preset threshold (such as 60°), the selectable cut-in area is determined to be a valid visible area; otherwise, the selectable cut-in area is discarded.

[0044] By calculating the surface curvature of each sub-region and evaluating the visibility based on the available cut-in areas, areas that are facing away or not visible can be filtered out. This ensures that the candidate cut-in areas are both flat enough and can be effectively photographed, thus improving the reliability of the candidate cut-in areas.

[0045] Then, a plane fitting is performed on the candidate cutting region to obtain the fitting plane; In this embodiment, the above-mentioned plane fitting can be achieved using existing plane fitting methods such as Random Sample Consensus (RANSAC) plane fitting and least squares plane fitting, which will not be elaborated here.

[0046] Finally, the angle between the normal vector of the fitted plane and the horizontal plane is calculated to obtain the inclination angle of the material.

[0047] In this embodiment, the normal vector of the fitted plane can be first transformed to the excavator coordinate system or the world coordinate system, and then the angle between the normal vector and the horizontal plane can be calculated to obtain the tilt angle of the material.

[0048] Candidate entry areas are determined based on the point cloud data of the work area; a plane fitting is performed on the candidate entry areas to obtain a fitting plane; the angle between the normal vector of the fitting plane and the horizontal plane is calculated, which can quickly and accurately obtain the tilt angle of the material without the need for an external tilt sensor, thus saving maintenance costs.

[0049] In some embodiments, the candidate cutting regions may be one or more, and when there are multiple candidate cutting regions, the step of performing planar fitting on the candidate cutting regions to obtain a fitting plane includes: Each candidate cutting region is fitted with a plane to obtain multiple fitting planes; Accordingly, calculating the angle between the normal vector of the fitted plane and the horizontal plane to obtain the inclination angle of the material includes: First, calculate the angle between the normal vector of each fitted plane and the horizontal plane to obtain the tilt angle of each fitted plane; Then, based on the inclination angles corresponding to each fitted plane, the inclination angle of the material is obtained.

[0050] In this embodiment, when there are multiple candidate cutting areas, the inclination angle corresponding to each fitted plane can be calculated separately, and then a weighted average of the inclination angles can be performed to obtain the inclination angle of the material. It should be noted that an iterative filtering algorithm can also be used to remove outlier fitted planes before calculating the included angle, so as to obtain a more accurate inclination angle of the material.

[0051] In some embodiments, when the work scenario is a crushed stone scenario, obtaining the inclination angle of the material includes: First, acquire point cloud data of the work area; Then, the point cloud data of the work area is segmented to obtain multiple local point cloud regions; Then, planar fitting is performed on each local point cloud region to obtain multiple local fitting planes; Then, the angle between the normal vector of each local fitting plane and the horizontal plane is calculated to obtain the tilt angle corresponding to each local fitting plane; Finally, the tilt angles corresponding to each of the local fitting planes are weighted and averaged to obtain the tilt angle of the material.

[0052] In this embodiment, the above-mentioned crushed stone scenario is that the material is classified as crushed stone / mixed stone. In this scenario, point cloud segmentation can be performed first. For example, a point cloud segmentation algorithm can be started to segment the point cloud data of the working area into multiple local planes, that is, to obtain multiple local point cloud regions. Then, plane fitting is performed on each local point cloud region, and the angle between the normal vector of each local fitting plane and the horizontal plane is calculated. Then, the tilt angle of the material is calculated more accurately by weighted averaging.

[0053] In some embodiments, obtaining the tilt angle of the material includes: First, obtain the initial tilt angle of the material; In this embodiment, the initial tilt angle of the material can be obtained by using the steps of obtaining the tilt angle of the material in the above embodiment.

[0054] Then, obtain the estimated value of the cutting resistance; In this embodiment, considering that the initial tilt angle of the material may not be accurate enough, it needs to be corrected. For example, in the above embodiment, the initial tilt angle can be obtained based on visual recognition, specifically by continuously acquiring point computing data from multiple frames of material. Large fluctuations in the tilt angle calculated over multiple frames—for example, 8° in one frame, 20° in the next, and then back to 10° in the following frame—indicate unstable visual recognition. Furthermore, if the variance of the calculated initial tilt angle exceeds a set threshold within a certain time window (e.g., the last 10 frames), it indicates unreliable visual recognition. Therefore, correction can be made using an estimated cutting resistance value. The estimated cutting resistance value can be obtained by first establishing a force-displacement curve. Here, force refers to the cutting resistance exerted by the hydraulic cylinder on the bucket, and displacement refers to the displacement of the hydraulic cylinder piston rod, or indirectly equivalent to the angular displacement of the bucket relative to the hinge. This can be obtained using a cylinder length sensor (LVDT), magnetic scale, or angle encoder. When the bucket cuts into the material, a force-displacement curve can be plotted. The horizontal axis represents the displacement (or time / angle) of the bucket entering the material, and the vertical axis represents the resistance (F) measured by the hydraulic cylinder. If the resistance increases rapidly in a short period of time, it indicates that the cutting angle is too steep and needs to be adjusted. The slope of this curve can be used to estimate the cutting difficulty, that is, to obtain the estimated value of the cutting resistance. If the force-displacement curve shows that the resistance is much greater than expected, it means that the angle underestimates the difficulty.

[0055] Finally, based on the estimated cutting resistance value, the initial tilt angle of the material is corrected to obtain the tilt angle of the material.

[0056] The above correction process can be performed according to the following formula: , in, This is the correction term calculated from the force-displacement curve, i.e., the estimated value of the cutting resistance. This is an empirical coefficient. The initial inclination angle of the material. The angle of inclination of the material.

[0057] By correcting the initial tilt angle of the material, a more accurate and reliable tilt angle can be obtained, which helps to improve control stability.

[0058] Step 220: Based on the pitch angle of the bucket and the tilt angle of the material, obtain an estimated entry angle, wherein the estimated entry angle is the entry angle of the bucket relative to the material; In this embodiment, the above-mentioned cut-in angle estimate can be obtained by calculating the difference between the pitch angle of the bucket and the tilt angle of the material, and can be expressed as: Δθ = θ_bucket - θ_material, where θ_bucket is the pitch angle of the bucket, θ_material is the tilt angle of the material, and Δθ is the cut-in angle estimate.

[0059] Step 230: Based on the estimated cut angle, adjust the bucket posture of the excavator.

[0060] In this embodiment, the attitude of the bucket or boom can be adjusted based on the estimated angle of entry so that the angle of entry of the bucket meets the requirements.

[0061] In some embodiments, adjusting the bucket posture of the excavator based on the estimated approach angle includes: First, determine whether the estimated angle of entry meets the preset angle of entry conditions; In this embodiment, the preset entry angle condition can be set in advance based on experience, and can be a range of recommended entry angles. The judgment can be to determine whether the estimated entry angle is within the range of recommended entry angles.

[0062] In some embodiments, determining whether the estimated angle of approach satisfies a preset angle of approach condition includes: The first step is to obtain the type of the material; In this embodiment, the type of material can be predetermined or identified. For example, an image recognition model can be used to classify the material texture and color of an RGB image to distinguish between loose soil, clay, medium-hard soil, and crushed / mixed stone, thus determining the type of material. The aforementioned image recognition model can be constructed using a lightweight CNN model, which is existing technology and will not be elaborated upon here.

[0063] The second step is to determine the recommended entry angle for the material based on its type. The third step is to compare the estimated cutting angle with the recommended cutting angle corresponding to the material to obtain the comparison result; Fourth step: Based on the comparison results, determine whether the estimated entry angle meets the preset entry angle conditions.

[0064] In this embodiment, considering that different material characteristics have significantly different requirements for the entry angle during excavator operation, as shown in Table 1 below, the corresponding recommended entry angle can be matched with the material type in the preset material characteristics and recommended entry angle correspondence table. Then, the estimated entry angle value is compared with the corresponding recommended entry angle to obtain the comparison result. If the comparison result is that the estimated entry angle value is within the corresponding recommended entry angle range, then the estimated entry angle value meets the preset entry angle condition; otherwise, the estimated entry angle value does not meet the preset entry angle condition.

[0065] Table 1. Correspondence between material properties and recommended entry angle

[0066] By determining the recommended entry angle corresponding to the material based on the material type, and comparing the estimated entry angle with the recommended entry angle corresponding to the material to determine whether the estimated entry angle meets the preset entry angle conditions, different types of materials can be judged separately, improving the accuracy and reliability of the judgment.

[0067] Then, if the estimated cut-in angle meets the preset cut-in angle conditions, the excavator is controlled to maintain the current bucket posture and perform excavation operations. Then, if it is determined that the estimated cut-in angle does not meet the preset cut-in angle conditions, the bucket posture of the excavator is adjusted.

[0068] In this embodiment, if the estimated entry angle meets the preset entry angle condition, it means that the current posture of the excavator meets the entry angle requirement, and the current posture is maintained for excavation. Otherwise, it means that the current posture of the excavator does not meet the entry angle requirement, and the bucket posture of the excavator needs to be adjusted. After adjusting the bucket posture of the excavator, step 210 can be executed again, and so on, until the estimated entry angle meets the preset entry angle condition, thus achieving closed-loop control.

[0069] In some embodiments, adjusting the bucket posture of the excavator when it is determined that the estimated cut-in angle does not meet the preset cut-in angle conditions includes: The first step is to calculate the difference between the estimated entry angle and the preset recommended entry angle value when it is determined that the estimated entry angle does not meet the preset entry angle conditions, and obtain the error value. The second step is to adjust the bucket posture of the excavator based on the error value.

[0070] In this embodiment, the aforementioned preset recommended angle of incidence can be pre-set or be an intermediate value within the recommended range of incident angles. The adjustment can be performed according to a preset control algorithm, such as a PID closed-loop control algorithm or a feedforward compensation algorithm.

[0071] For example, a PWM-angle open-loop mapping is established based on the characteristics of the hydraulic cylinder to provide a basic control quantity. Real-time corrections are then made based on error values ​​and rates of change to ensure smooth bucket retraction / extension movements, achieving feedforward + PID control. Here, the PWM signal refers to the pulse width modulation signal (which can be equivalent to current magnitude) output by the controller to the proportional solenoid valve. The angle refers to the change in bucket angle after the hydraulic cylinder actuates (e.g., retracting the bucket by 2°, extending it by 3°). The PWM-angle open-loop mapping establishes an open-loop characteristic curve through calibration. The controller outputs a PWM signal, which, after proportional amplification, drives the hydraulic proportional solenoid valve to fine-tune the boom and bucket cylinders. The cylinder actuation changes the bucket's attitude relative to the stick, gradually pulling the estimated angle of entry back to the recommended incident angle range.

[0072] By calculating the difference between the estimated entry angle and the preset recommended entry angle, the excavator's attitude can be quickly and accurately adjusted based on the error value so that the estimated entry angle meets the preset entry angle conditions.

[0073] In the above implementation process, the bucket pitch angle and material tilt angle are acquired in real time in response to automatic control commands; based on the bucket pitch angle and material tilt angle, an estimated cutting angle is obtained; and based on the estimated cutting angle, the excavator's bucket attitude is adjusted. The bucket pitch angle and material tilt angle determine the bucket's cutting angle relative to the material, i.e., the estimated cutting angle. By using the estimated cutting angle as a target reference for adjusting the bucket or boom attitude, adaptive positioning and adjustment of the cutting angle at the moment of contact between the bucket and the material are achieved, making the cutting more accurate, reducing the risk of cutting failure or rebound, and improving operational efficiency and safety.

[0074] The following example illustrates the solution; please refer to it. Figure 3 , Figure 3 The schematic diagram illustrates the closed-loop flowchart of excavator bucket adjustment according to an embodiment of this application. Upon detecting a single boom descent, binocular image acquisition is initiated to generate a point cloud digital matrix; this generates target recognition data. The point cloud is segmented into a bucket region, and a 3D model is used for matching to obtain the bucket's current angle in world coordinates, i.e., the bucket's pitch angle. Material sub-regions are segmented in the point cloud, and material plane fitting (world coordinate system) is performed to obtain the material's tilt angle. The estimated cut-in angle in world coordinates is calculated using the bucket's pitch angle and the material's tilt angle. Based on the material classification, it can be determined whether the estimated cut-in angle is within the target range. If so, the current bucket posture is maintained, and autonomous digging begins after cutting into the soil. If not, a PWM is calculated using PID + feedforward, and the PWM drives the solenoid valve for fine-tuning, achieving closed-loop control. Specific working conditions and parameter examples are shown in Table 2 below.

[0075] Table 2. Typical Operating Conditions and Parameter Examples

[0076] In some embodiments, it also includes: If a manual control signal is detected, the automatic control command will cease to be responded to.

[0077] In this embodiment, if a valid operator input (arm / bucket joystick signal), i.e., a manual control signal, is detected, automatic control is immediately interrupted, and manual commands are given priority, making control more flexible. In practical implementation, a one-button switch can be provided to allow the operator to quickly switch between automatic and manual modes.

[0078] Figure 1 This is a flowchart illustrating the excavator bucket adjustment method in this embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0079] Please refer to Figure 4 , Figure 4 This illustration schematically shows a general framework diagram of an excavator bucket adjustment system according to an embodiment of this application. This embodiment provides an excavator bucket adjustment system, including a controller; The controller is used to respond to automatic control commands, acquire the pitch angle of the bucket and the tilt angle of the material in real time; obtain an estimated entry angle based on the pitch angle of the bucket and the tilt angle of the material, the estimated entry angle being the entry angle of the bucket relative to the material; and adjust the bucket attitude of the excavator based on the estimated entry angle.

[0080] In this embodiment, the controller can be the main controller on the excavator, such as an AI intelligent controller.

[0081] The controller, responding to automatic control commands, acquires the bucket's pitch angle and the material's tilt angle in real time. Based on these parameters, an estimated entry angle is obtained. The excavator's bucket posture is then adjusted based on this estimated entry angle. The bucket's pitch angle and the material's tilt angle determine the bucket's entry angle relative to the material—the estimated entry angle. By using this estimated entry angle as a target reference for adjusting the bucket or boom posture, adaptive positioning and adjustment of the entry angle at the moment of contact between the bucket and the material are achieved. This results in more accurate entry, reduces the risk of entry failure or rebound, and improves operational efficiency and safety.

[0082] In some embodiments, a data acquisition device is also included; The data acquisition device is used to acquire operation image frames in real time and send the operation image frames to the controller; The controller is used to determine the tilt angle of the material and the bucket point cloud data based on the operation image frame.

[0083] In this embodiment, the data acquisition device can be a binocular camera, which can be mounted on the top of the cab and fixed with a sturdy bracket, covering the bucket and material pile area. A protective cover can also be installed on the binocular camera. After receiving the operation image frame, the controller can obtain the position and orientation of the bucket and the material surface using the point cloud data in the operation image frame according to the above method, and then obtain the tilt angle of the material and the bucket point cloud data, which will not be elaborated further here. By using binocular stereo vision and point cloud algorithms, the bucket and the material surface can be reconstructed simultaneously without the need for an external tilt sensor, saving maintenance costs.

[0084] By integrating visual solutions with the excavation angle to influence excavator efficiency, this approach can be widely applied to scenarios such as construction, mining operations, and urban infrastructure. In particular, it can significantly improve production efficiency and reduce operation and maintenance costs in environments requiring efficient and continuous excavation.

[0085] In some embodiments, the real-time pitch angle of the bucket, the tilt angle of the material, and the estimated cut angle can be displayed on the cab instrument interface for operator monitoring. The controller can also send operating data to the T-BOX, which can transmit parameter commands to the AI ​​intelligent controller. The T-BOX then transmits the data to the operating data big data platform. The AI ​​intelligent controller controls the solenoid valves by controlling the current to control the working device.

[0086] This embodiment provides an excavator in which the bucket posture is adjusted using the above-described excavator bucket adjustment method when the excavator is performing excavation work on materials.

[0087] In the above implementation process, the excavator, in response to automatic control commands, acquires the bucket pitch angle and the material tilt angle in real time; based on the bucket pitch angle and the material tilt angle, an estimated cutting angle is obtained; and based on the estimated cutting angle, the excavator's bucket posture is adjusted. The bucket pitch angle and the material tilt angle determine the bucket's cutting angle relative to the material, i.e., the estimated cutting angle. By using this estimated cutting angle as a target reference for adjusting the bucket or boom posture, adaptive positioning and adjustment of the cutting angle at the moment of contact between the bucket and the material are achieved, making the cutting more accurate, reducing the risk of cutting failure or rebound, and improving operational efficiency and safety.

[0088] Please refer to Figure 5 , Figure 5 This schematic diagram illustrates the structure of an excavator bucket adjustment device according to an embodiment of the present application. This embodiment provides an excavator bucket adjustment device, including an acquisition module 410, a calculation module 420, and a control module 430, wherein: The acquisition module 410 is used to acquire the pitch angle of the bucket and the tilt angle of the material in real time in response to automatic control commands; The calculation module 420 is used to obtain an estimated entry angle based on the pitch angle of the bucket and the tilt angle of the material, wherein the estimated entry angle is the entry angle of the bucket relative to the material; The control module 430 is used to adjust the bucket posture of the excavator based on the estimated cut angle.

[0089] The excavator bucket adjustment device includes a processor and a memory. The aforementioned acquisition module 410, calculation module 420, and control module 430 are all stored in the memory as program units. The processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0090] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting the kernel parameters allows for adjustments to the excavator bucket.

[0091] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0092] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0094] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0095] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0096] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0097] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0098] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0100] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for adjusting the bucket of an excavator, characterized in that, include: In response to automatic control commands, the bucket pitch angle and material tilt angle are acquired in real time; Based on the pitch angle of the bucket and the tilt angle of the material, an estimated cut angle is obtained; Based on the estimated entry angle, the bucket posture of the excavator is adjusted.

2. The method according to claim 1, characterized in that, Adjusting the bucket posture of the excavator based on the estimated entry angle includes: Determine whether the estimated angle of entry meets the preset angle of entry condition; If the estimated angle of entry meets the preset angle of entry conditions, the excavator is controlled to maintain the current bucket posture and perform excavation operations. If the estimated entry angle does not meet the preset entry angle conditions, the bucket posture of the excavator is adjusted.

3. The method according to claim 2, characterized in that, The step of determining whether the estimated angle of entry meets the preset angle of entry condition includes: Obtain the type of the material; Based on the type of the material, the recommended entry angle corresponding to the material is determined; The estimated cutting angle is compared with the recommended cutting angle corresponding to the material to obtain the comparison result; Based on the comparison results, it is determined whether the estimated entry angle meets the preset entry angle conditions.

4. The method according to claim 2, characterized in that, The step of adjusting the bucket posture of the excavator when it is determined that the estimated cut-in angle does not meet the preset cut-in angle conditions includes: If it is determined that the estimated entry angle does not meet the preset entry angle conditions, the difference between the estimated entry angle and the preset recommended entry angle is calculated to obtain the error value; Based on the error value, the bucket posture of the excavator is adjusted.

5. The method according to claim 1, characterized in that, The process of obtaining the bucket's pitch angle includes: Acquire bucket point cloud data and bucket 3D model; The bucket point cloud data and the bucket 3D model are registered to obtain the transformation matrix; Based on the transformation matrix, the pitch angle of the bucket is obtained.

6. The method according to claim 1, characterized in that, Obtain the inclination angle of the material, including: Acquire point cloud data of the work area; Based on the point cloud data of the work area, candidate entry areas are determined; Perform planar fitting on the candidate cutting region to obtain the fitting plane; The angle between the normal vector of the fitted plane and the horizontal plane is calculated to obtain the inclination angle of the material.

7. The method according to claim 6, characterized in that, The process of determining candidate entry regions based on the point cloud data of the work area includes: Based on the region growing segmentation method, multiple sub-regions are obtained in the point cloud data of the work area; Based on the surface curvature of each sub-region, an optional cutting region is determined in the plurality of sub-regions; The visibility of the optional cut-in area is evaluated to obtain the visibility value of the optional cut-in area; Based on the visibility value of the selectable cut-in region, candidate cut-in regions are determined.

8. The method according to claim 7, characterized in that, The step of evaluating the visibility of the optional cut-in area to obtain the visibility value of the optional cut-in area includes: Calculate the angle between the normal vector of the optional cutting area and the virtual central optical axis to obtain the visible angle of the optional cutting area; Based on the viewing angle of the optional cut-in area, the visibility value of the optional cut-in area is obtained.

9. The method according to claim 1, characterized in that, In the case of a gravel-filled work environment, the inclination angle of the material is obtained, including: Acquire point cloud data of the work area; The point cloud data of the work area is segmented to obtain multiple local point cloud regions; Plane fitting is performed on each local point cloud region to obtain multiple local fitting planes; Calculate the angle between the normal vector of each local fitting plane and the horizontal plane to obtain the tilt angle corresponding to each local fitting plane; The tilt angle of the material is obtained by weighted averaging the tilt angles corresponding to each of the local fitting planes.

10. The method according to claim 1, characterized in that, Obtain the inclination angle of the material, including: Obtain the initial tilt angle of the material; Obtain the estimated value of the cutting resistance; Based on the estimated cutting resistance value, the initial tilt angle of the material is corrected to obtain the tilt angle of the material.

11. The method according to claim 1, characterized in that, Also includes: If a manual control signal is detected, the automatic control command will cease to be responded to.

12. An excavator bucket adjustment device, characterized in that, include: The acquisition module is used to acquire the pitch angle of the bucket and the tilt angle of the material in real time in response to automatic control commands; The calculation module is used to obtain an estimated cut-in angle based on the pitch angle of the bucket and the tilt angle of the material; The control module is used to adjust the bucket posture of the excavator based on the estimated cut angle.

13. An excavator, characterized in that, When the excavator is digging materials, the bucket posture is adjusted using the excavator bucket adjustment method according to any one of claims 1-11.

Images