Shovel control method, device, electronic equipment, storage medium and program product

Abstract

The application discloses a shovel control method and device, electronic equipment, storage medium and program product, relates to the technical field of computer processing, and the method comprises the steps that first point cloud data is acquired; second point cloud data is acquired from the first point cloud data based on the initial estimated pose information of a shovel; the accurate pose of the shovel is obtained by registering the second point cloud data based on the preset three-dimensional model of the shovel; a ground elevation map is constructed based on third point cloud data; the real-time ground-hugging distance of the shovel is determined based on the accurate pose of the shovel, the preset three-dimensional model of the shovel, the second point cloud data and the ground elevation map; and the shovel is controlled to hug the ground based on the deviation of the real-time ground-hugging distance and a target distance threshold. The ground elevation map can represent the ground undulation, improve the environmental adaptability of the shovel pose control, improve the ground-hugging effect of the shovel, and improve the stability of the shovel pose control.

Description

Technical Field

[0001] This application relates to the field of bucket control technology, specifically to bucket control methods, devices, electronic equipment, storage media, and program products. Background Technology

[0002] In loading and unloading operations of construction machinery, the relative position and posture control of the bucket and the ground directly affects operational efficiency. In related technologies, bucket control often relies on pre-set motion trajectories or open-loop control based on limited sensor information. Because these methods lack efficient perception and real-time processing capabilities for three-dimensional spatial information of the working environment, it is difficult to dynamically and accurately estimate and adjust the bucket's position and posture in complex terrain, resulting in insufficient stability and environmental adaptability of the bucket's position and posture control. Summary of the Invention

[0003] In view of this, this application provides a bucket control method, device, electronic equipment, storage medium, and program product to solve the problems of insufficient stability and environmental adaptability of bucket position control.

[0004] In a first aspect, this application provides a bucket control method for an operating device having a bucket, the method comprising: Acquire first point cloud data, which is used to characterize the three-dimensional environmental point cloud within a first preset range of the operating equipment; Based on the initial estimated pose information of the bucket, the second point cloud data is obtained from the first point cloud data; Based on the preset 3D model of the bucket, the model is registered with the second point cloud data to obtain the precise pose of the bucket. A ground elevation map is constructed based on the third point cloud data, wherein the third point cloud data is used to characterize other point cloud data in the first point cloud data other than the second point cloud data. Based on the precise position of the bucket, the preset three-dimensional model of the bucket, the second point cloud data, and the ground elevation map, the real-time ground contact distance of the bucket is determined. Based on the deviation between the real-time ground contact distance and the target distance threshold, the bucket is controlled to maintain ground contact.

[0005] Secondly, this application provides a bucket control device for working equipment with a bucket, the device comprising: The first acquisition module is used to acquire first point cloud data, which is used to characterize the three-dimensional environmental point cloud within a first preset range of the operating equipment. The second acquisition module is used to acquire second point cloud data from the first point cloud data based on the initial estimated pose information of the bucket; The pose acquisition module is used to register the bucket with the second point cloud data based on the preset three-dimensional model of the bucket to obtain the precise pose of the bucket. An elevation construction module is used to construct a ground elevation map based on third point cloud data, wherein the third point cloud data is used to characterize other point cloud data in the first point cloud data other than the second point cloud data. The distance acquisition module is used to determine the real-time ground contact distance of the bucket based on the precise pose of the bucket, the preset three-dimensional model of the bucket, the second point cloud data and the ground elevation map; The bucket control module controls the bucket's contact with the ground based on the deviation between the real-time ground contact distance and the target distance threshold.

[0006] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the bucket control method of the first aspect or any corresponding embodiment described above.

[0007] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the bucket control method of the first aspect or any corresponding embodiment described above.

[0008] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the bucket control method of the first aspect or any corresponding embodiment described above.

[0009] The bucket control method provided in this application embodiment obtains the second point cloud data corresponding to the bucket by combining the three-dimensional environmental point cloud within a first preset range of the working equipment with the initial estimated pose information of the bucket. Based on the preset three-dimensional model of the bucket, the second point cloud data is registered to obtain the precise pose of the bucket. A ground elevation map is constructed based on the other point cloud data in the three-dimensional environmental point cloud besides the second point cloud data. Then, based on the precise pose of the bucket, the second point cloud data of the preset three-dimensional model of the bucket, and the ground elevation map, the real-time ground contact distance of the bucket is determined. Ground contact control of the bucket is performed according to the deviation between the real-time ground contact distance and the target distance threshold. Since the ground elevation map can represent the ground undulation, the real-time ground contact distance of the bucket relative to the ground can be accurately obtained based on the ground elevation map. The accurate real-time ground contact distance is beneficial to providing basic data for subsequent accurate ground contact control, improving the environmental adaptability of the bucket pose control, improving the overall ground contact effect of the bucket, and thus improving the stability of the bucket pose control. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of this application, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this application; Figure 2 This is a schematic flowchart of a first embodiment of the bucket control method according to this application. Figure 3 This is a structural block diagram of a bucket control device according to an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0013] It should be noted that the information (including but not limited to user input information, such as information entered by the user into input boxes), data (including but not limited to data used for analysis, stored data, and displayed data, such as context code, all code of the current project, the service pressure corresponding to operations performed on all code of the current project, and the code development status of the current project), and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with relevant laws, regulations, and standards. For example, the context code, operations performed on all code of the current project, the corresponding service pressure, and the code development status involved in this application were all obtained with full authorization.

[0014] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0015] As one optional application scenario in the embodiments of this application, such as Figure 1 As shown, the system may include working equipment 10 and electronic equipment 20.

[0016] The work equipment 10 is used to excavate and load materials. Optionally, the work equipment 10 is equipped with a bucket for performing the excavation function. Exemplarily, the work equipment 10 also includes components such as a boom, arm, and slewing platform. Exemplarily, the work equipment 10 is a loader, excavator, etc.

[0017] Electronic device 20 is used to control the bucket of the working equipment 10. Optionally, computer device 20 may be an electronic device such as a vehicle terminal, mobile phone, tablet computer, wearable device, back-end server, server cluster, distributed system, cloud server or PC (Personal Computer).

[0018] The work equipment 10 and the electronic device 20 are connected via a network. For example, one electronic device 20 can control multiple work equipment 10s. The network can be a wired or wireless network, examples of which include, but are not limited to, the Internet, intranets, local area networks, wide area networks, mobile communication networks, and combinations thereof. Of course, in other possible implementations, one electronic device 20 may also control only one work equipment 10. For example, the electronic device 20 may be an onboard device for the work equipment 10.

[0019] In related technologies, one approach involves controlling the bucket's digging trajectory during loading operations through pre-programmed human instruction or preset movement trajectories for the boom and bucket. However, relying on preset trajectories cannot adapt to the varying terrain in actual operations, resulting in poor ground contact with the bucket. Another approach involves installing sensors on the bucket to control its ground contact. Commonly used sensors include tilt sensors and distance sensors. The tilt sensor controls the bucket's angle relative to the horizontal plane to remain constant. However, tilt sensors cannot accurately determine the actual contact between the bucket and the ground when there is a slope, easily leading to poor ground contact.

[0020] Furthermore, to address the problems existing in the aforementioned related technologies, in this embodiment, the second point cloud data corresponding to the bucket is obtained by combining the three-dimensional environmental point cloud within the first preset range of the working equipment with the initial estimated pose information of the bucket. Based on the preset three-dimensional model of the bucket, the second point cloud data is registered to obtain the precise pose of the bucket. A ground elevation map is constructed based on other point cloud data in the three-dimensional environmental point cloud besides the second point cloud data. Then, based on the precise pose of the bucket, the second point cloud data of the preset three-dimensional model of the bucket, and the ground elevation map, the real-time ground contact distance of the bucket is determined. Ground contact control of the bucket is then performed based on the deviation between the real-time ground contact distance and the target distance threshold. Since the ground elevation map can characterize the ground undulation, the real-time ground contact distance of the bucket relative to the ground can be accurately obtained based on the ground elevation map. The accurate real-time ground contact distance is beneficial for providing basic data for subsequent accurate ground contact control, improving the environmental adaptability of the bucket pose control, improving the overall ground contact effect of the bucket, and thus improving the stability of the bucket pose control.

[0021] According to an embodiment of this application, a bucket control method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0022] This embodiment provides a bucket control method that can be used in the aforementioned electronic devices, such as vehicle-mounted terminals, mobile phones, tablets, wearable devices, backend servers, server clusters, distributed systems, cloud servers, or PCs (Personal Computers). Figure 2 This is a flowchart of a bucket control method according to an embodiment of this application. The bucket control method is used for working equipment having a bucket, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain the first point cloud data.

[0023] In this embodiment of the application, when controlling the bucket, the electronic device acquires first point cloud data. The first point cloud data is used to characterize the three-dimensional environmental point cloud within a first preset range of the operating equipment.

[0024] For example, multiple laser sensors are configured on the top of the operating equipment. Electronic devices acquire first point cloud data through these laser sensors. For example, the first preset range is an arbitrary value, which can be flexibly set and adjusted according to actual conditions, and the laser sensors can be flexibly selected or arranged based on this range. For instance, to save data and improve the efficiency of subsequent ground-hugging control of the bucket, the first preset range is determined based on the bucket's size information; or, to ensure the accuracy and completeness of the subsequent ground elevation map, the first preset range is determined based on the bucket's size information and the operating equipment's footprint.

[0025] In one possible implementation, the first preset range is the acquisition range of the laser sensor, and the electronic device directly acquires the first point cloud data through the laser sensor.

[0026] In another possible implementation, the first preset range is smaller than the acquisition range of the laser sensor. The electronic device acquires initial point cloud data through the laser sensor, and further acquires first point cloud data from the initial point cloud data based on the first preset range.

[0027] Step S202: Based on the initial estimated pose information of the bucket, obtain the second point cloud data from the first point cloud data.

[0028] In this embodiment of the application, after acquiring the first point cloud data, the electronic device acquires the second point cloud data from the first point cloud data based on the initial estimated pose information of the bucket.

[0029] For example, an IMU (Inertial Measurement Unit) is configured on the bucket. The electronic device obtains the initial estimated pose information of the bucket through the IMU. Further, based on the initial estimated pose information of the bucket, the initial position of the bucket in the three-dimensional environment is determined, and then based on the initial position and the size information of the bucket, the second point cloud data is extracted from the first point cloud data.

[0030] Step S203: Based on the preset 3D model of the bucket, register it with the second point cloud data to obtain the precise pose of the bucket.

[0031] In this embodiment of the application, after acquiring the second point cloud data, the electronic device registers the second point cloud data with the preset three-dimensional model of the bucket to obtain the precise pose of the bucket.

[0032] Optionally, in this embodiment of the application, the electronic device uses the constrained Iterative Closest Point (ICP) algorithm to register the second point cloud data with a preset three-dimensional model to obtain the six-degree-of-freedom pose of the bucket; further, based on the six-degree-of-freedom pose, the precise pose is obtained.

[0033] For example, the six-degree-of-freedom pose is used to characterize the bucket's translational degrees of freedom in three directions, and its rotational degrees of freedom about those three directions. These three directions are the X-axis, Y-axis, and Z-axis, as described below.

[0034] For example, constraints are used to characterize the movement constraints of the bucket. For instance, constraints include the bucket's range of movement in three directions and its range of rotation about those three directions. For example, the registration described above includes coarse registration and fine registration.

[0035] For example, in the coarse registration process, the electronic device samples a preset 3D model to obtain model point cloud data; further, the model point cloud data and the second point cloud data are both placed in the same 3D coordinate system, such as the wheel coordinate system below; further, the first key point is extracted from the model point cloud data, and the second key point is extracted from the second point cloud data; further, based on the geometry of the area surrounding each first key point and the geometry of the area surrounding each second key point, the second key point with the most similar geometry is matched for each first key point to obtain key point pairs; further, based on the key point pairs, the model point cloud data is repeatedly moved in different ways as a whole to select the movement method that can align the most key point pairs at the same time; further, the initial pose represented by the movement method is used as the starting point to enter the fine registration process.

[0036] For example, during the fine registration process, the electronic device finds the nearest point pair between the model point cloud data and the second point cloud data based on the current pose, and calculates the rigid body transformation that minimizes the sum of the squares of the distances between the nearest point pairs to obtain a candidate pose. Then, if the movement indicated by the candidate pose satisfies the constraints, this candidate pose is used as the new current pose, and the calculation is repeated to obtain new candidate poses until the maximum number of iterations is reached, resulting in a six-DOF pose. If the movement indicated by the candidate pose does not satisfy the constraints, the maximum movement represented by the constraints is superimposed on the current pose to obtain an adjusted candidate pose. This adjusted candidate pose is then used as the new current pose, and the calculation is repeated to obtain new candidate poses until the maximum number of iterations is reached, resulting in a six-DOF pose. For example, at the start of the iteration, the aforementioned current pose is the aforementioned initial pose.

[0037] For example, the six-degree-of-freedom pose is the precise pose described above.

[0038] Of course, in other possible implementations, the electronic device may also use NDT (Normal Distribution Transform) algorithm or FPFH (Fast Point Feature Histograms) algorithm to register the second point cloud data with the preset three-dimensional model to obtain the six-degree-of-freedom pose of the bucket.

[0039] Step S204: Construct a ground elevation map based on the third point cloud data.

[0040] In this embodiment of the application, after acquiring the first point cloud data, the electronic device constructs a ground elevation map based on the third point cloud data. The third point cloud data is used to characterize the other point cloud data in the first point cloud data besides the second point cloud data.

[0041] For example, in order to improve the efficiency of building a ground elevation map, after acquiring the aforementioned third point cloud data, the electronic device filters out ground point cloud data from the third point cloud data, and then builds a ground elevation map based on the ground point cloud data.

[0042] In one possible implementation, the electronic device constructs a ground elevation map based on third-point cloud data using a rasterization method. Details are provided below and will not be repeated here.

[0043] In another possible implementation, the electronic device constructs a ground elevation map based on third point cloud data using triangulation interpolation. For example, the electronic device projects the point cloud contained in the third point cloud data onto a horizontal plane; further, it constructs a Delaunay triangulation based on the projected discrete points, with each triangle vertex representing a point cloud contained in the third point cloud data; further, for each preset grid cell of the ground elevation map, it locates the triangle containing the center point of the grid cell, and uses the elevation values ​​(i.e., Z-values) of the three vertices of that triangle to perform linear interpolation to calculate the corresponding height value of the grid cell; further, it combines the height values ​​of all grid cells to obtain the ground elevation map.

[0044] In another possible implementation, the electronic device constructs a ground elevation map based on third point cloud data using inverse distance weighted interpolation. For example, the electronic device acquires a preset target grid range and resolution for the ground elevation map; further, for the center point of each target grid, it searches the third point cloud data for neighboring point clouds within a preset range from the center point; further, it calculates weights based on the inverse of the distance from each neighboring point cloud to the center point, and performs a weighted average of the elevation values ​​(i.e., Z-values) of each neighboring point cloud to obtain the height value corresponding to the target grid; by traversing all target grids, the ground elevation map is obtained.

[0045] Step S205: Based on the bucket's precise position, the bucket's preset 3D model, the second point cloud data, and the ground elevation map, determine the bucket's real-time ground contact distance.

[0046] In this embodiment of the application, after obtaining the precise pose of the bucket, the electronic device determines the real-time ground contact distance of the bucket based on the precise pose of the bucket, the second point cloud data of the preset three-dimensional model of the bucket, and the ground elevation map.

[0047] For example, the ground elevation map includes multiple grids, each storing a height value that represents the height of the ground point indicated by the grid relative to the horizontal plane. The electronic device determines the real-time ground contact distance of the bucket based on the first three-dimensional coordinates of each point cloud in the second point cloud data, combined with the height values ​​stored in the ground elevation map.

[0048] For example, the real-time ground contact distance is used to characterize the vertical distance between the feature points of the bucket's bottom plate and the ground. Here, the ground is the ground represented by the ground elevation map. For example, the electronic device obtains a thickness compensation value based on a preset 3D model of the bucket; further, after obtaining the corresponding values ​​(i.e., preset statistical values ​​hereinafter) based on the bucket's precise pose, the bucket's preset 3D model, second point cloud data, and the ground elevation map, the real-time ground contact distance is determined based on the thickness compensation value. The thickness compensation value characterizes the bucket's thickness, and the real-time ground contact distance obtained after the thickness compensation value characterizes the vertical distance between the outer surface of the bucket's bottom plate and the ground. This helps avoid collisions or insufficient digging depth caused by ignoring the bottom plate thickness, improving the accuracy of ground contact control for the bucket.

[0049] For example, the first three-dimensional coordinates are used to characterize the position of the point cloud in the wheel coordinate system, and the horizontal plane refers to the plane formed by the X-axis and Y-axis in the wheel coordinate system. For example, the wheel coordinate system refers to a three-dimensional coordinate system constructed with the first ground contact point as the origin, the first wheel direction as the X-axis, and the second wheel direction as the Y-axis. Of course, this three-dimensional coordinate system includes a Z-axis perpendicular to the aforementioned horizontal plane. The first wheel direction refers to the direction from the first ground contact point to the second ground contact point, the second wheel direction refers to the direction from the first ground contact point to the third ground contact point, the first ground contact point is the point where the first front wheel of the working equipment contacts the ground, the second ground contact point is the point where the first rear wheel of the working equipment contacts the ground, and the third ground contact point is the point where the second front wheel of the working equipment contacts the ground. The first front wheel and the first rear wheel are located on the same side of the working equipment.

[0050] For example, when acquiring the first point cloud data, the electronic device acquires the three-dimensional information of each point cloud in the first point cloud data in the laser coordinate system. Further, after acquiring the second point cloud data from the first point cloud data, based on the transformation information (such as a transformation matrix) between the laser coordinate system and the wheel coordinate system, the three-dimensional information of each point cloud in the second point cloud data in the laser coordinate system is transformed to obtain the first three-dimensional coordinates of each point cloud in the second point cloud data. For example, the three-dimensional information of each point cloud in the laser coordinate system is the three-dimensional coordinate of each point cloud in the laser coordinate system; for distinction, the three-dimensional coordinates of each point cloud in the laser coordinate system can be referred to as the second three-dimensional coordinates.

[0051] Step S206: Based on the deviation between the real-time ground contact distance and the target distance threshold, ground contact control is performed on the bucket.

[0052] In this embodiment of the application, after obtaining the above-mentioned ground contact distance, the electronic device performs ground contact control on the bucket based on the deviation between the real-time ground contact distance and the target distance threshold.

[0053] For example, the target distance threshold can be any preset data, and can be flexibly set and adjusted according to the actual situation. For instance, the electronic device obtains the thickness of the bucket based on a preset three-dimensional model of the bucket, and then sets the target distance threshold based on the thickness of the bucket; or, for another example, different target distance thresholds can be set based on the hardness of the ground material or the softness of the material.

[0054] For example, after obtaining the above deviation, the electronic device obtains the control rate for the bucket based on the deviation in order to control the bucket to stay close to the ground.

[0055] For example, there is a positive correlation between the control rate and the deviation, that is, the larger the deviation, the larger the control rate, and the smaller the deviation, the smaller the control rate.

[0056] In one possible implementation, the control rate is a fixed value during ground contact control. For example, the electronic device, in response to an actual ground contact distance greater than a target distance threshold, obtains a descent rate for the bucket based on the deviation to control the bucket's descent; conversely, in response to an actual ground contact distance less than the target distance threshold, it obtains an ascent rate for the bucket based on the deviation to control the bucket's ascent.

[0057] In another possible implementation, during ground contact control, the control rate dynamically changes with the deviation, and there is a positive correlation between the control rate and the deviation. For example, the electronic equipment uses a PID (Proportion Integral Differential) algorithm to control the bucket's ground contact. See below for details, which will not be elaborated upon here.

[0058] The bucket control method provided in this embodiment obtains the second point cloud data corresponding to the bucket by combining the three-dimensional environmental point cloud within a first preset range of the working equipment with the initial estimated pose information of the bucket. Based on the preset three-dimensional model of the bucket, the second point cloud data is registered to obtain the precise pose of the bucket. A ground elevation map is constructed based on the other point cloud data in the three-dimensional environmental point cloud besides the second point cloud data. Then, based on the precise pose of the bucket, the second point cloud data of the preset three-dimensional model of the bucket, and the ground elevation map, the real-time ground contact distance of the bucket is determined. Ground contact control of the bucket is performed according to the deviation between the real-time ground contact distance and the target distance threshold. Since the ground elevation map can represent the ground undulation, the real-time ground contact distance of the bucket relative to the ground can be accurately obtained based on the ground elevation map. The accurate real-time ground contact distance is beneficial to providing basic data for subsequent accurate ground contact control, improving the environmental adaptability of the bucket pose control, improving the overall ground contact effect of the bucket, and thus improving the stability of the bucket pose control.

[0059] In addition, a constrained iterative nearest point algorithm is used to register the second point cloud data with a preset 3D model to obtain the precise pose of the bucket. The determination of the precise pose helps to improve the accuracy of the real-time ground contact distance, thereby improving the accuracy of the bucket ground contact control.

[0060] In an exemplary embodiment, step S204 includes: Step S2041: Obtain the fourth point cloud data from the third point cloud data.

[0061] In this embodiment of the application, after acquiring the third point cloud data, the electronic device acquires fourth point cloud data from the third point cloud data. The fourth point cloud data is used to characterize the ground point cloud within a second preset range of the operating equipment, and the second preset range is smaller than the first preset range. For example, the fourth point cloud data can be referred to as ground point cloud data.

[0062] In one possible implementation, the second preset range corresponds to a fixed range. After acquiring the third point cloud data, the electronic device acquires the fourth point cloud data from the third point cloud data based on the second preset range.

[0063] In another possible implementation, the second preset range does not correspond to a fixed range; that is, the second preset range refers to the range indicated by the fourth point cloud data obtained after filtering the third point cloud data.

[0064] Specifically, step S2041 includes: Step S2041a: Cluster the third point cloud data based on spatial distance to obtain at least one first point cloud cluster.

[0065] In this embodiment of the application, after acquiring the aforementioned third point cloud data, the electronic device clusters the third point cloud data based on spatial distance to obtain at least one first point cloud cluster. For example, clustering the third point cloud data based on spatial distance is Euclidean clustering.

[0066] In one possible implementation, in order to ensure the accuracy and completeness of the ground elevation map as much as possible, the electronic device directly clusters the third point cloud data based on spatial distance to obtain at least one first point cloud cluster.

[0067] In another possible implementation, to improve the processing efficiency of subsequent point cloud data, the electronic device acquires intermediate point cloud data from the third point cloud data based on a third preset range, and then clusters the intermediate point cloud data based on spatial distance to obtain at least one first point cloud cluster. The third preset range is smaller than the first preset range and larger than the second preset range. For example, the third preset range can be any value and can be flexibly set and adjusted according to actual conditions. For example, the third preset range is 10 meters in front of the working equipment and 2 meters to the left and right. Since it is for ground-level control of the bucket, the location of the bucket is considered the front of the working equipment. After acquiring the second point cloud data, the electronic device uses the bucket position indicated by the second point cloud data as a reference and acquires intermediate point cloud data from the third point cloud data based on the third preset range.

[0068] Step S2041b: Filter out the first point cloud clusters whose centroid height is greater than the first threshold, and obtain at least one second point cloud cluster.

[0069] In this embodiment of the application, after obtaining the first point cloud cluster, the electronic device filters out the first point cloud cluster whose centroid height is greater than a first threshold, and obtains at least one second point cloud cluster. Exemplarily, the first threshold can be any value, and can be flexibly set and adjusted according to actual conditions.

[0070] For example, the electronic device obtains the centroid height of each first point cloud cluster based on the first three-dimensional coordinates of each point cloud in the third point cloud data; further, it filters out the first point cloud clusters whose centroid height is greater than a first threshold to obtain at least one second point cloud cluster.

[0071] For example, when obtaining the centroid height, the electronic device averages the Z values ​​in the first three-dimensional coordinates of each point cloud in the first point cloud cluster to obtain the centroid height of the first point cloud cluster.

[0072] Step S2041c: Filter out second point cloud clusters whose angle between the normal vector and the vertical direction is greater than the second threshold, and obtain at least one third point cloud cluster.

[0073] In this embodiment, after acquiring at least one second point cloud cluster, the electronic device filters out second point cloud clusters whose angle between the normal vector and the vertical direction is greater than a second threshold, obtaining at least one third point cloud cluster. The fourth point cloud data includes the at least one third point cloud cluster. Exemplarily, the second threshold can be any value, and can be flexibly set and adjusted according to actual conditions. Exemplarily, the vertical direction refers to the normal vector of the horizontal plane, i.e., the Z-axis.

[0074] For example, the electronic device obtains the normal vector of each second point cloud cluster based on the first three-dimensional coordinates of each point cloud in the second point cloud cluster; further, it filters out second point cloud clusters whose angle between the normal vector and the vertical direction is greater than a second threshold to obtain at least one third point cloud cluster.

[0075] Step S2042: Construct the original elevation map based on the fourth point cloud data.

[0076] In this embodiment of the application, after obtaining the aforementioned fourth point cloud data, the electronic device constructs an original elevation map based on the fourth point cloud data.

[0077] For example, the electronic device projects the point cloud contained in the fourth point cloud data onto the aforementioned horizontal plane; further, the projected horizontal plane is discretized into multiple grids; further, the corresponding height value is stored in each grid to generate an original elevation map. For example, the height value refers to the minimum Z value or the average Z value of the first three-dimensional coordinates of the point cloud projected in the grid. For example, the height value recorded by the grid can be called the elevation value of the grid.

[0078] Step S2043: Interpolate and fill the holes in the original elevation map to obtain a ground elevation map.

[0079] In this embodiment of the application, after obtaining the original elevation map, the electronic device interpolates and fills the holes in the original elevation map to obtain a ground elevation map.

[0080] In one possible implementation, the electronic device uses the FMM (Fast Marching Method) to start from the edge grid of the hole, take the height data of the adjacent grids, calculate the average, and then interpolate to fill the hole in the grid.

[0081] In another possible implementation, the electronic device obtains the average height data of the original elevation map based on the original elevation map, and then interpolates the average height data to fill the gaps in the grid.

[0082] In another possible implementation, the electronic device directly takes the height data of the nearest grid and interpolates it to fill the hole in the grid.

[0083] This embodiment provides a bucket control method that obtains ground point cloud data within a second preset range of the working equipment through third point cloud data. The second preset range is smaller than the first preset range, which reduces the amount of data that needs to be processed during the construction of the ground elevation map, improves the construction efficiency of the ground elevation map, and improves the overall control efficiency of the bucket. In addition, interpolation is performed to fill in the gaps, which improves the accuracy of the ground elevation map.

[0084] In addition, the point cloud contained in the fourth point cloud data is projected onto the horizontal plane, and the projected horizontal plane is discretized into multiple grids. The corresponding height value is stored in each grid to generate the original elevation map. The three-dimensional data is reduced to a two-dimensional horizontal plane, and then the horizontal plane is discretized into multiple grids. This achieves accurate alignment between the grids and the three-dimensional space, which helps to ensure the accuracy of the ground elevation map.

[0085] In addition, multiple first point cloud clusters are obtained by clustering the third point cloud data by spatial distance. Then, point clouds that are significantly higher than the ground are filtered out based on the centroid height, and point clouds that are significantly tilted to the ground are filtered out based on the angle between the normal vector and the vertical direction. This improves the accuracy of ground point cloud data, reduces the amount of data that needs to be processed in the process of building ground elevation maps, and improves the accuracy and efficiency of ground elevation map construction.

[0086] In an exemplary embodiment, step S205 includes: Step S2051: Based on the precise pose of the bucket and the preset three-dimensional model of the bucket, obtain the first three-dimensional coordinates of at least one bottom plate feature point of the bucket.

[0087] In this embodiment of the application, after obtaining the above-mentioned precise pose, the electronic device obtains the first three-dimensional coordinates of at least one bottom plate feature point of the bucket based on the precise pose of the bucket and the preset three-dimensional model of the bucket.

[0088] For example, the electronic device, based on a precise pose and combined with a preset 3D model, obtains at least one bottom plate feature point of the bucket and the first 3D coordinates of each bottom plate from the second point cloud data. Here, a bottom plate feature point is a point cloud in the second point cloud data used to represent the bottom plate. For example, the electronic device extracts at least one bottom plate feature point of the bucket based on the preset 3D model; further, based on the correspondence between the preset 3D model and the aforementioned model point cloud data, and combined with the initial pose of the model point cloud data in the aforementioned wheel coordinates, it obtains the initial 3D coordinates of each bottom plate feature point; further, based on the six-degree-of-freedom pose represented by the precise pose, it calculates the candidate 3D coordinates corresponding to the initial 3D coordinates; further, in the second point cloud data, the first 3D coordinate closest to the candidate 3D coordinates is determined as the first 3D coordinate of the bottom plate feature point.

[0089] Step S2052: Based on the first three-dimensional coordinates, obtain the grid to which each base plate feature point belongs in the ground elevation map.

[0090] In this embodiment of the application, after obtaining the above-mentioned base plate feature points and the first three-dimensional coordinates of each base plate feature point, the electronic device obtains the grid to which each base plate feature point belongs in the ground elevation map based on the first three-dimensional coordinates.

[0091] For example, since the ground elevation map is constructed based on the aforementioned first three-dimensional coordinates, the electronic device determines the projected coordinates (X, Y) of the base plate feature point in the aforementioned horizontal plane based on the X and Y values ​​of the first three-dimensional coordinates of the base plate feature point, and then determines the grid where the projected coordinates are located as the grid to which the base plate feature point belongs in the ground elevation map.

[0092] Step S2053: Based on the height coordinates in the first three-dimensional coordinate system and the height values ​​stored in the grid, determine the distance between each base plate feature point and the ground.

[0093] In this embodiment of the application, after determining the grid to which the base plate feature point belongs in the ground elevation map, the electronic device determines the distance between each base plate feature point and the ground based on the height coordinate (i.e., Z value) in the first three-dimensional coordinate system and the height value stored in the grid.

[0094] For example, the electronic device obtains the absolute value of the difference between the height coordinates corresponding to each base plate feature point and the aforementioned height value based on the height coordinates in the first three-dimensional coordinate system, and determines the absolute value of the difference as the distance between the base plate feature point and the ground.

[0095] Step S2054: Determine the preset statistical value in the distance as the real-time ground contact distance.

[0096] In this embodiment, after obtaining the distances between each of the aforementioned base plate feature points and the ground, the electronic device determines a preset statistical value from the distance as the real-time ground contact distance. For example, the preset statistical value can be the minimum value, average value, or median.

[0097] In one possible implementation, to ensure the accuracy of subsequent ground contact control, the electronic device selects the minimum value from the distances; further, the minimum value is corrected based on the thickness compensation value of the preset three-dimensional model of the bucket; further, the corrected minimum value is determined as the real-time ground contact distance. For example, since the minimum value is the bottom plate feature point closest to the ground, the electronic device superimposes the thickness compensation value on the minimum value to obtain the corrected minimum value.

[0098] In another possible implementation, to reduce the randomness of the ground contact distance, the electronic device averages the various distances to obtain an average value. Further, the average value is corrected based on the thickness compensation value of a preset 3D model of the bucket. Finally, the corrected average value is determined as the real-time ground contact distance. For example, since the average value neutralizes the difference between the maximum and minimum values, to further improve the accuracy of ground contact control, the electronic device subtracts the thickness compensation value from the average value to obtain the corrected average value. This embodiment provides a bucket control method that obtains the bucket's bottom plate feature points through the bucket's precise pose and a preset 3D model. Then, based on the first 3D coordinates of the bottom plate feature points, the grid to which the bottom plate feature points belong on the ground elevation map is located. And based on the height coordinates in the first 3D coordinates of the bottom plate feature points, combined with the height values ​​stored in the grid, the real-time ground contact distance is obtained. The extraction of the bottom plate feature points reduces the data processing required in the distance acquisition process, improving the efficiency of ground contact control for the bucket.

[0099] In an exemplary embodiment, step S206 includes: Step S2061: The control rate for the bucket is obtained based on the deviation using a PID algorithm.

[0100] In this embodiment of the application, after obtaining the above-mentioned deviation, the electronic device obtains the control rate for the bucket based on the deviation.

[0101] For example, there is a positive correlation between the control rate and the deviation, that is, the larger the deviation, the larger the control rate, and the smaller the deviation, the smaller the control rate. Moreover, through the PID algorithm, the control rate changes dynamically with the deviation during the movement of the bucket in the ground-following control.

[0102] Step S2062: Control the bucket to stay close to the ground based on the control rate.

[0103] In this embodiment of the application, after obtaining the control rate, the electronic device performs ground-following control on the bucket based on the control rate.

[0104] For example, the electronic device determines the control rate as the descent rate for the bucket in response to a real-time ground contact distance greater than a target distance threshold, so as to control the bucket to descend; conversely, in response to a real-time ground contact distance less than the target distance threshold, it determines the control rate as the ascent rate for the bucket, so as to control the bucket to ascend.

[0105] This embodiment provides a bucket control method that uses a PID algorithm to obtain the control efficiency for the bucket. Compared with the traditional "bang-bang control", it helps to avoid severe shaking of the bucket during ground-hugging control and improves the smoothness of the bucket's actual operation.

[0106] In an exemplary embodiment, step S202 includes: Step S2021: Based on the motion parameters of the bucket, obtain the initial estimated pose information of the bucket.

[0107] In this embodiment of the application, during the operation of the bucket, the electronic device obtains the initial estimated pose information of the bucket based on the bucket's motion parameters. For example, the electronic device obtains the bucket's motion parameters based on the aforementioned IMU.

[0108] In another possible implementation, the electronic device can also obtain the motion parameters of the bucket through the joint angle sensors of the boom, arm and bucket cylinders of the working equipment, and then calculate the initial estimated pose information of the bucket through forward kinematics.

[0109] Step S2022: Obtain the cut-off range based on the bucket size information.

[0110] In this embodiment, the electronic device obtains the cut-off range based on the bucket's size information. For example, the cut-off range is larger than the actual bucket size indicated by the bucket's size information. For example, the cut-off range can be any shape such as a rectangle or trapezoid.

[0111] For example, the electronic device determines a first dimension of the bucket in three coordinate axes based on the bucket's size information; further, it expands the first dimension of the bucket in the negative direction of a specified coordinate axis into a second dimension, while keeping the first dimension of the bucket in a non-specified coordinate axis unchanged, thus obtaining the intercept range. The second dimension is larger than the first dimension. Optionally, the specified coordinate axis can be any one of the X-axis, Y-axis, and Z-axis mentioned above.

[0112] Step S2023: Using the initial estimated pose information as the localization, and based on the interception range, the second point cloud data is intercepted from the first point cloud data.

[0113] In this embodiment of the application, after obtaining the above-mentioned initial estimated pose information and the above-mentioned interception range, the electronic device uses the initial estimated pose information as the positioning and intercepts the second point cloud data from the first point cloud data based on the interception range.

[0114] This embodiment provides a bucket control method. The method obtains the initial estimated pose information of the bucket through the bucket's motion parameters and obtains the interception range through the bucket's size information. Then, the method uses the initial estimated pose information as the positioning and intercepts the second point cloud data from the first point cloud data based on the interception range. The combination of the initial estimated pose information and the size information ensures the coverage of the second point cloud data for the bucket while obtaining as much accurate and small amount of point cloud data as possible to characterize the bucket. This helps to reduce the processing efficiency of the second point cloud data in the future, thereby improving the overall ground-following control efficiency of the bucket.

[0115] This embodiment also provides a bucket control device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0116] This embodiment provides a bucket control device for working equipment with a bucket, such as... Figure 3 As shown, it includes: The first acquisition module 301 is used to acquire first point cloud data, which is used to characterize the three-dimensional environmental point cloud within a first preset range of the working equipment. The second acquisition module 302 is used to acquire second point cloud data from the first point cloud data based on the initial estimated pose information of the bucket; The pose acquisition module 303 is used to register the bucket's preset 3D model with the second point cloud data to obtain the bucket's precise pose. The elevation construction module 304 is used to construct a ground elevation map based on the third point cloud data, which is used to characterize the other point cloud data in the first point cloud data except for the second point cloud data. The distance acquisition module 305 is used to determine the real-time ground contact distance of the bucket based on the bucket's precise pose, the second point cloud data of the bucket's preset three-dimensional model, and the ground elevation map. The bucket control module 306 controls the bucket's contact with the ground based on the deviation between the real-time ground contact distance and the target distance threshold.

[0117] In some alternative implementations, the elevation construction module 304 includes: The fourth acquisition unit is used to acquire fourth point cloud data from the third point cloud data. The fourth point cloud data is used to characterize the ground point cloud within a second preset range of the operating equipment. The second preset range is smaller than the first preset range. The first building unit is used to construct the original elevation map based on the fourth point cloud data; The void filling unit is used to interpolate and fill voids in the original elevation map to obtain a ground elevation map.

[0118] In some alternative implementations, the first building unit is used for: Project the point cloud contained in the fourth point cloud data onto the horizontal plane; Discretize the projected horizontal plane into multiple grids; Store the corresponding height value in each grid to generate the original elevation map.

[0119] In some optional implementations, the fourth acquisition unit is used for: Clustering of the third point cloud data based on spatial distance yields at least one first point cloud cluster; Filter out the first point cloud cluster whose centroid height is greater than the first threshold, and obtain at least one second point cloud cluster; Second point cloud clusters are filtered out by removing those whose angle between the normal vector and the vertical direction is greater than the second threshold, resulting in at least one third point cloud cluster; wherein, the fourth point cloud data includes at least one third point cloud cluster.

[0120] In some alternative implementations, the distance acquisition module 305 includes: The coordinate acquisition unit is used to obtain the first three-dimensional coordinates of at least one bottom plate feature point of the bucket based on the precise pose of the bucket and the preset three-dimensional model of the bucket. The grid determination unit is used to obtain the grid to which each feature point of the base plate belongs in the ground elevation map based on the first three-dimensional coordinates; The distance acquisition unit is used to determine the distance between each base plate feature point and the ground based on the height coordinates in the first three-dimensional coordinate system and the height values ​​stored in the grid. The distance statistics unit is used to determine the preset statistical value in the distance as the real-time ground-level distance.

[0121] In some alternative implementations, the distance statistics unit is used for: Select the minimum value from the distances; The minimum value is corrected based on the thickness compensation value of the preset 3D model of the bucket. The corrected minimum value is determined as the real-time ground contact distance.

[0122] In some alternative implementations, the bucket control module 306 includes: The rate acquisition unit is used to obtain the control rate for the bucket based on the deviation using a PID algorithm; The bucket control unit is used to control the bucket's ground contact based on the control rate.

[0123] In some alternative implementations, the bucket control unit is used for: In response to a real-time ground contact distance exceeding a target distance threshold, the control rate is determined as the descent rate for the bucket to control the bucket descent. In response to a real-time ground contact distance being less than a target distance threshold, the control rate is determined as the bucket's ascent rate to control the bucket's ascent.

[0124] In some alternative implementations, the second acquisition module 302 includes: The initial estimation unit is used to obtain the initial estimated pose information of the bucket based on the bucket's motion parameters; The range acquisition unit is used to obtain the interception range based on the size information of the bucket; The data interception unit is used to locate the second point cloud data from the first point cloud data based on the initial estimated pose information and the interception range.

[0125] In some optional implementations, the range acquisition unit is used for: Based on the bucket's dimensions, determine the bucket's first dimension in the three coordinate axes. The first dimension of the bucket in the negative direction of a specified coordinate axis among the three coordinate axes is expanded into the second dimension to obtain the interception range; The second dimension is larger than the first dimension.

[0126] In some alternative implementations, the pose acquisition module 303 is used for: The constrained iterative nearest point algorithm is used to register the second point cloud data with the preset 3D model to obtain the six-degree-of-freedom pose of the bucket. Based on the six degrees of freedom pose, the accurate pose is obtained.

[0127] The bucket control device provided in this application can execute the bucket control method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0128] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0129] The following is a detailed reference. Figure 4The diagram illustrates a structural schematic suitable for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from memory 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the electronic device. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0130] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0131] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 409, or installed from memory 408, or installed from ROM 402. When the computer program is executed by processor 401, it performs the functions defined in the bucket control method of embodiments of this application.

[0132] Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0133] This application also provides a computer-readable storage medium. The methods described above according to this application can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the bucket control method shown in the above embodiments is implemented.

[0134] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0135] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A bucket control method, characterized in that, For working equipment with a bucket, the method includes: Acquire first point cloud data, which is used to characterize the three-dimensional environmental point cloud within a first preset range of the operating equipment; Based on the initial estimated pose information of the bucket, the second point cloud data is obtained from the first point cloud data; Based on the preset 3D model of the bucket, the model is registered with the second point cloud data to obtain the precise pose of the bucket. A ground elevation map is constructed based on the third point cloud data, wherein the third point cloud data is used to characterize other point cloud data in the first point cloud data other than the second point cloud data. Based on the precise position of the bucket, the preset three-dimensional model of the bucket, the second point cloud data, and the ground elevation map, the real-time ground contact distance of the bucket is determined. Based on the deviation between the real-time ground contact distance and the target distance threshold, the bucket is controlled to maintain ground contact.

2. The method according to claim 1, characterized in that, The construction of the ground elevation map based on third-point cloud data includes: A fourth point cloud data is obtained from the third point cloud data. The fourth point cloud data is used to characterize the ground point cloud within a second preset range of the operating equipment. The second preset range is smaller than the first preset range. The original elevation map is constructed based on the fourth point cloud data; The holes in the original elevation map are filled by interpolation to obtain the ground elevation map.

3. The method according to claim 2, characterized in that, The construction of the original elevation map based on the fourth point cloud data includes: Project the point cloud contained in the fourth point cloud data onto a horizontal plane; Discretize the projected horizontal plane into multiple grids; The corresponding height value is stored in each grid to generate the original elevation map.

4. The method according to claim 2, characterized in that, The step of obtaining the fourth point cloud data from the third point cloud data includes: Clustering the third point cloud data based on spatial distance yields at least one first point cloud cluster. Filter out the first point cloud cluster whose centroid height is greater than the first threshold, and obtain at least one second point cloud cluster; Second point cloud clusters are filtered out by removing those whose angle between the normal vector and the vertical direction is greater than a second threshold, resulting in at least one third point cloud cluster; wherein, the fourth point cloud data includes the at least one third point cloud cluster.

5. The method according to claim 1, characterized in that, The determination of the real-time ground contact distance of the bucket based on the precise pose of the bucket, the preset 3D model of the bucket, and the ground elevation map includes: Based on the precise pose of the bucket and the preset three-dimensional model of the bucket, the first three-dimensional coordinates of at least one bottom plate feature point of the bucket are obtained. Based on the first three-dimensional coordinates, obtain the grid to which each base plate feature point belongs in the ground elevation map; Based on the height coordinates in the first three-dimensional coordinate system and the height values ​​stored in the grid, the distance between each base plate feature point and the ground is determined. The preset statistical value in the distance is determined as the real-time ground contact distance.

6. The method according to claim 5, characterized in that, Determining the preset statistical value in the distance as the real-time ground contact distance includes: Select the minimum value from the distances; The minimum value is corrected based on the thickness compensation value of the preset three-dimensional model of the bucket; The corrected minimum value is determined as the real-time ground contact distance.

7. The method according to claim 1, characterized in that, The step of controlling the bucket's contact with the ground based on the deviation between the real-time ground contact distance and the target distance threshold includes: The control rate for the bucket is obtained based on the deviation using a PID algorithm. The bucket is ground-hugging controlled based on the control rate.

8. The method according to claim 7, characterized in that, The control of the bucket's ground contact based on the control rate includes: In response to the real-time ground contact distance being greater than the target distance threshold, the control rate is determined as the descent rate of the bucket to control the descent of the bucket; In response to the real-time ground contact distance being less than the target distance threshold, the control rate is determined as the lifting rate for the bucket to control the bucket to rise.

9. The method according to claim 1, characterized in that, The step of obtaining second point cloud data from the first point cloud data based on the initial estimated pose information of the bucket includes: Based on the motion parameters of the bucket, the initial estimated pose information of the bucket is obtained; Based on the size information of the bucket, the cutting range is obtained; Using the initial estimated pose information as the location, and based on the interception range, the second point cloud data is intercepted from the first point cloud data.

10. The method according to claim 9, characterized in that, The process of obtaining the cut-off range based on the bucket size information includes: Based on the bucket's size information, determine the first dimension of the bucket in the three coordinate axes; The first dimension of the bucket in the negative direction of a specified coordinate axis among the three coordinate axes is expanded into a second dimension to obtain the interception range; The second dimension is larger than the first dimension.

11. The method according to claim 1, characterized in that, The process of registering the preset 3D model based on the bucket with the second point cloud data to obtain the precise pose of the bucket includes: The constrained iterative nearest point algorithm is used to register the second point cloud data with the preset 3D model to obtain the six-degree-of-freedom pose of the bucket. Based on the six-degree-of-freedom pose, the precise pose is obtained.

12. A bucket control device, characterized in that, For working equipment with a bucket, the device includes: The first acquisition module is used to acquire first point cloud data, which is used to characterize the three-dimensional environmental point cloud within a first preset range of the operating equipment. The second acquisition module is used to acquire second point cloud data from the first point cloud data based on the initial estimated pose information of the bucket; The pose acquisition module is used to register the bucket with the second point cloud data based on the preset three-dimensional model of the bucket to obtain the precise pose of the bucket. An elevation construction module is used to construct a ground elevation map based on third point cloud data, wherein the third point cloud data is used to characterize other point cloud data in the first point cloud data other than the second point cloud data. The distance acquisition module is used to determine the real-time ground contact distance of the bucket based on the precise pose of the bucket, the preset three-dimensional model of the bucket, the second point cloud data and the ground elevation map; The bucket control module controls the bucket's contact with the ground based on the deviation between the real-time ground contact distance and the target distance threshold.

13. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the bucket control method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the bucket control method according to any one of claims 1 to 11.

15. A computer program product, characterized in that, It includes computer instructions for causing a computer to perform the bucket control method according to any one of claims 1 to 11.

Images