Shovel coordinate calibration method and apparatus, updating method and device, excavator

Abstract

The present disclosure relates to a bucket coordinate calibration method and device, an updating method and equipment, and a excavator. The bucket coordinate calibration method comprises: obtaining radar point cloud data and angle sensor data of a bucket; determining coordinates of a middle bucket tooth of the bucket in a radar coordinate system according to the radar point cloud data of the bucket; determining coordinates of the middle bucket tooth of the bucket in a excavator coordinate system according to the angle sensor data of the bucket; and determining a coordinate calibration matrix according to the coordinates of the middle bucket tooth of the bucket in the radar coordinate system and in the excavator coordinate system, wherein the coordinate calibration matrix is a coordinate calibration matrix for calibrating the coordinates of the middle bucket tooth of the bucket in the radar coordinate system to the excavator coordinate system. The present disclosure can calibrate the coordinates of the bucket by using a laser radar and a angle sensor of a excavator without increasing an external calibration equipment.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent construction machinery, and in particular to a bucket coordinate calibration method and device, updating method and equipment, and excavator. Background Technology

[0002] For excavators operating in bulk material excavation mode, it is hoped that sensing devices can detect the size of the material pile and the location of the target excavation point, and inform the excavator of the target location, so as to realize unmanned automatic excavation operation. Summary of the Invention

[0003] The inventors discovered through research that in excavator-operated bulk material excavation operations, a lidar system (LiDAR) is used to detect the size of the material pile and the location of the target excavation point. The lidar is mounted on the outside of the excavator. An angle sensor is used to detect the position of the bucket, which is mounted on the excavator. Automatic excavation towards the target excavation point is achieved through bucket trajectory planning and control. In this scenario, accurate measurement of the target excavation point is crucial for precise excavation. Precise measurement requires coordinate calibration, specifically, accurately transferring the coordinates of the bucket and the target excavation point from the radar coordinate system to the excavator coordinate system, thus unifying the bucket coordinates with the target excavation point coordinates within the excavator coordinate system.

[0004] Commonly used methods for coordinate calibration in related technologies include direct measurement, manual point selection, and scene feature analysis. However, these methods have the following drawbacks: direct measurement has low calibration accuracy, and both direct measurement and manual point selection often introduce various errors, including those caused by human error.

[0005] In view of at least one of the above technical problems, this disclosure provides a bucket coordinate calibration method and apparatus, an update method and device, and an excavator that can calibrate the bucket coordinates using lidar and excavator angle sensors without adding external calibration equipment.

[0006] According to one aspect of this disclosure, a method for calibrating bucket coordinates is provided, comprising:

[0007] Acquire radar point cloud data and angle sensor data of the bucket;

[0008] Based on the radar point cloud data of the bucket, determine the coordinates of the middle bucket tooth in the radar coordinate system;

[0009] Based on the angle sensor data of the bucket, determine the coordinates of the middle bucket tooth in the excavator coordinate system;

[0010] Based on the coordinates of the middle bucket teeth in the radar coordinate system and the excavator coordinate system, a coordinate calibration matrix is ​​determined, wherein the coordinate calibration matrix is ​​the coordinate calibration matrix from the radar coordinate system to the excavator coordinate system of the middle bucket teeth.

[0011] In some embodiments of this disclosure, acquiring radar point cloud data and angle sensor data of the bucket includes: collecting radar point cloud data and angle sensor data of the bucket when the bucket is in multiple different positions.

[0012] In some embodiments of this disclosure, determining the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data of the bucket includes: determining the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data collected at each spatial location of the bucket.

[0013] In some embodiments of this disclosure, determining the coordinates of the middle bucket tooth in the excavator coordinate system based on the bucket angle sensor data includes: determining the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data collected by the bucket at each spatial position.

[0014] In some embodiments of this disclosure, determining the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data collected at each spatial location of the bucket includes: determining the coordinates of the middle bucket tooth in the radar coordinate system based on the implicit shape model algorithm using the radar point cloud data collected at each spatial location of the bucket.

[0015] In some embodiments of this disclosure, determining the coordinates of the middle bucket tooth in the excavator coordinate system based on angle sensor data collected at each spatial position of the bucket includes: obtaining the forward kinematics solution of the excavator device based on the angle sensor data collected at each spatial position of the bucket, and determining the coordinates of the middle bucket tooth in the excavator coordinate system.

[0016] In some embodiments of this disclosure, determining the coordinate calibration matrix based on the coordinates of the bucket's intermediate teeth in the radar coordinate system and the excavator coordinate system includes:

[0017] Based on the coordinates of the middle bucket teeth in the radar coordinate system and the excavator coordinate system, data pairs of radar coordinate system coordinates and excavator coordinate system coordinates are constructed, and multiple data pairs are divided into training set and test set.

[0018] Determine the coordinate calibration matrix based on the training set data;

[0019] Use the test set to verify the coordinate calibration matrix.

[0020] In some embodiments of this disclosure, the coordinate calibration matrix is ​​a coordinate rotation and translation transformation matrix.

[0021] In some embodiments of this disclosure, determining the coordinate calibration matrix based on the training set data includes:

[0022] Initialize relevant parameters, including the number of iterations;

[0023] Randomly select a predetermined number of first data pairs;

[0024] Determine whether the first data pair is collinear;

[0025] In the case that the first data pairs are not collinear, a direct linear transformation is used to determine the coordinate calibration matrix.

[0026] In some embodiments of this disclosure, determining the coordinate calibration matrix based on the training set data further includes:

[0027] Using a coordinate calibration matrix, the radar coordinate system coordinates in the second data pair are transformed to obtain the excavator coordinate system coordinates. The second data pair consists of all other data pairs in the training set except for the first data pair.

[0028] Calculate the distance deviation between the excavator coordinate system coordinates obtained from the transformation and the actual excavator coordinate system coordinates;

[0029] Determine whether the distance deviation is less than a predetermined distance threshold;

[0030] Based on the number of iterations and a predetermined distance threshold, record the interior points that meet the conditions and update the coordinate calibration matrix;

[0031] Calculate the inlier probability and update the iteration count based on the inlier probability.

[0032] According to another aspect of this disclosure, a coordinate calibration update method is provided, comprising:

[0033] Determine whether the online error of the coordinate calibration matrix is ​​greater than the predetermined allowable error;

[0034] If the online error of the coordinate calibration matrix is ​​greater than the predetermined allowable error, then determine whether the number of collected location point data pairs has reached the predetermined number of location points.

[0035] When the number of collected location point data pairs is equal to the predetermined number of location points, a new coordinate calibration matrix is ​​determined using the bucket coordinate calibration method described in any of the above embodiments.

[0036] Update the coordinate calibration matrix.

[0037] In some embodiments of this disclosure, the coordinate calibration update method further includes:

[0038] If the number of location point data pairs collected is less than the predetermined number of location points, collect bucket radar point cloud data to determine one coordinate of the middle bucket tooth in the radar coordinate system.

[0039] Collect angle sensor data of the bucket to determine one coordinate of the middle bucket tooth in the excavator coordinate system;

[0040] The number of location point data pairs is accumulated, and then the step of determining whether the number of collected location point data pairs has reached the predetermined number of location points is executed again.

[0041] In some embodiments of this disclosure, determining one coordinate of the middle bucket tooth in the radar coordinate system includes: obtaining one coordinate of the middle bucket tooth in the radar coordinate system based on an implicit shape model algorithm; determining whether the model similarity is greater than a predetermined similarity; and using the one coordinate of the middle bucket tooth in the radar coordinate system if the model similarity is greater than the predetermined similarity.

[0042] In some embodiments of this disclosure, determining one coordinate of the middle bucket tooth in the excavator coordinate system includes: obtaining the forward kinematics of the excavator device based on angle sensor data, and determining one coordinate of the middle bucket tooth in the excavator coordinate system.

[0043] According to another aspect of this disclosure, a bucket coordinate calibration device is provided, comprising:

[0044] The data acquisition module is configured to acquire radar point cloud data and angle sensor data of the bucket;

[0045] The positioning module is configured to determine the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data of the bucket; and to determine the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data of the bucket.

[0046] The calibration module is configured to determine a coordinate calibration matrix based on the coordinates of the bucket's middle teeth in the radar coordinate system and the excavator coordinate system, wherein the coordinate calibration matrix is ​​the coordinate calibration matrix from the coordinates of the bucket's middle teeth in the radar system to the coordinate calibration matrix in the excavator coordinate system.

[0047] In some embodiments of this disclosure, the bucket coordinate calibration device is used to perform operations to implement the bucket coordinate calibration method as described in any of the above embodiments.

[0048] According to another aspect of this disclosure, a coordinate calibration update device is provided, comprising:

[0049] The judgment device is configured to determine whether the online error of the coordinate calibration matrix is ​​greater than a predetermined allowable error; if the online error of the coordinate calibration matrix is ​​greater than the predetermined allowable error, it determines whether the number of collected location point data pairs has reached a predetermined number of location points.

[0050] The bucket coordinate calibration device is configured to determine a new coordinate calibration matrix using the bucket coordinate calibration method when the number of collected location point data pairs is equal to the predetermined number of location points.

[0051] The updating device is configured to update the coordinate calibration matrix.

[0052] In some embodiments of this disclosure, the bucket coordinate calibration device is the bucket coordinate calibration device as described in any of the above embodiments.

[0053] In some embodiments of this disclosure, the coordinate calibration update device is used to perform operations that implement the coordinate calibration update method as described in any of the above embodiments.

[0054] According to another aspect of this disclosure, a computer apparatus is provided, comprising:

[0055] Memory, used to store instructions;

[0056] A processor is configured to execute the instructions, causing the computer device to perform operations implementing the bucket coordinate calibration method as described in any of the above embodiments, and / or to perform operations implementing the coordinate calibration update method as described in any of the above embodiments.

[0057] According to another aspect of this disclosure, a calibration system is provided, including a lidar and an angle sensor, and further including at least one of a computer device, a coordinate calibration update device, and a bucket coordinate calibration device, wherein the computer device is the computer device as described in any of the above embodiments, the coordinate calibration update device is the coordinate calibration update device as described in any of the above embodiments, and the bucket coordinate calibration device is the bucket coordinate calibration device as described in any of the above embodiments.

[0058] According to another aspect of this disclosure, an excavator is provided, including a lidar, and at least one of a computer device, a coordinate calibration and update device, and a bucket coordinate calibration device, wherein the computer device is the computer device as described in any of the above embodiments, the coordinate calibration and update device is the coordinate calibration and update device as described in any of the above embodiments, and the bucket coordinate calibration device is the bucket coordinate calibration device as described in any of the above embodiments.

[0059] According to another aspect of this disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions that, when executed by a processor, implement the bucket coordinate calibration method as described in any of the above embodiments, and / or implement the coordinate calibration update method as described in any of the above embodiments.

[0060] This disclosure allows for the calibration of bucket coordinates using lidar and excavator angle sensors without the need for additional external calibration equipment. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a schematic diagram illustrating the excavation operation of an excavator handling bulk materials according to some embodiments of this disclosure.

[0063] Figure 2 This is a schematic diagram of some embodiments of the bucket coordinate calibration method disclosed herein.

[0064] Figure 3 This is a schematic diagram of some other embodiments of the bucket coordinate calibration method disclosed herein.

[0065] Figure 4 The diagram illustrates some embodiments of the coordinate calibration and update method disclosed herein.

[0066] Figure 5 Schematic diagrams of other embodiments of the coordinate calibration and update method disclosed herein.

[0067] Figure 6 This is a schematic diagram of some embodiments of the bucket coordinate calibration device disclosed herein.

[0068] Figure 7 Schematic diagrams of some embodiments of the coordinate calibration update device of this disclosure.

[0069] Figure 8 This is a schematic diagram of the structure of some embodiments of the computer device disclosed herein. Detailed Implementation

[0070] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0071] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0072] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0073] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0074] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0075] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0076] The inventors discovered through research that related technologies such as direct measurement, manual point sampling, and scene feature analysis still have the following shortcomings:

[0077] 1) Manual sampling method is time-consuming and labor-intensive. Both direct testing and manual sampling require human intervention. If a large number of devices are calibrated, it will result in a large workload and make it difficult to achieve mass production of intelligent systems.

[0078] 2) The scene feature method requires the design of specific scenes for sensor calibration, and cannot achieve online calibration of sensors.

[0079] 3) None of the above methods have the function of verifying calibration errors online during operation, especially when the relative position of the excavator and the radar changes, the calibration cannot be updated online.

[0080] The related technology involves a sensor positioning system that can calculate the position of at least one or more autonomous vehicle sensors based on surface data. However, firstly, it requires multiple measurement conversions; secondly, it lacks error verification and online update functions.

[0081] The related technology also discloses a method for calibrating sensor devices installed on a machine, which can realize the calibration of sensors installed on the machine. However, firstly, it is necessary to collect terrain point clouds with multiple features and perform two registrations to calibrate the sensor devices installed on the machine; secondly, it cannot be calibrated online when the relative position of the sensor changes.

[0082] Another related technology can achieve offline calibration, but firstly, it requires specific calibration boards including a chessboard and an "L"-shaped joint calibration target; secondly, it cannot perform online calibration.

[0083] Another related technology enables offline calibration, but firstly, it requires a specific calibration board; secondly, obtaining the first coordinate values ​​of each feature point on the calibration board in the coordinate system of the machine's undercarriage requires manual measurement using measuring tools such as a tape measure, or automatic measurement by controlling the machine. However, manual measurement is cumbersome and difficult to be accurate, and how to perform automatic measurement is not explained; thirdly, online calibration is not possible.

[0084] In view of at least one of the above technical problems, this disclosure provides a bucket coordinate calibration method and apparatus, an updating method and equipment, and an excavator. The present disclosure will be described below through specific embodiments.

[0085] Figure 1 This is a schematic diagram illustrating the excavation operation of an excavator handling bulk materials, according to some embodiments of this disclosure. Figure 1 The operational scenario shown includes an excavator, the material to be excavated, a lidar sensing device, and a transport vehicle (not shown in the diagram, serving as an unloading point). The excavator is parked near the material to be excavated, and its excavation radius can cover the material area. In another scenario, when the total amount or location of the material changes during the excavation operation, the excavator can move accordingly.

[0086] In some embodiments of this disclosure, the lidar can be a lidar sensing device.

[0087] In some embodiments of this disclosure, such as Figure 1 As shown, the lidar sensing device is installed on the outside of the material to be excavated to collect the point cloud of the material in order to obtain a suitable target excavation point; at the same time, it is used to collect the point cloud of the bucket. When the middle bucket tooth is exposed outside the material, the point cloud containing the middle bucket tooth can be collected, and the coordinates PL of the middle bucket tooth in the radar coordinate system are obtained through the implicit shape model algorithm.

[0088] In some embodiments of this disclosure, such as Figure 1 As shown, an angle sensor is installed on the excavator to collect the excavator's angle information. The coordinates PW of the middle bucket tooth in the excavator coordinate system are calculated using the forward kinematics algorithm.

[0089] To achieve precise excavation, coordinate calibration is necessary. The above-described embodiments of this disclosure calibrate the coordinates of the middle bucket teeth in the radar system to the excavator coordinate system, thereby unifying the coordinates of the middle bucket teeth with the coordinates of the target excavation point in the excavator coordinate system.

[0090] Figure 2 The diagram illustrates some embodiments of the bucket coordinate calibration method disclosed herein. Preferably, this embodiment can be executed by the bucket coordinate calibration device, calibration system, computer device, or coordinate calibration update device disclosed herein. Figure 2 The method of the embodiment may include at least one of steps 21 to 24, wherein:

[0091] Step 21: Obtain radar point cloud data and angle sensor data of the bucket.

[0092] In some embodiments of this disclosure, step 21 may include: acquiring radar point cloud data and angle sensor data of the bucket when the bucket is in multiple different positions.

[0093] Step 22: Determine the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data of the bucket.

[0094] In some embodiments of this disclosure, step 22 may include: determining the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data collected at each spatial location of the bucket.

[0095] In some embodiments of this disclosure, step 22 may include: determining the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data collected at each spatial location of the bucket and an implicit shape model algorithm.

[0096] Step 23: Determine the coordinates of the middle bucket tooth in the excavator coordinate system based on the bucket angle sensor data.

[0097] In some embodiments of this disclosure, step 23 may include: determining the coordinates of the middle bucket tooth in the excavator coordinate system based on angle sensor data collected at each spatial location of the bucket.

[0098] In some embodiments of this disclosure, step 23 may include: obtaining the forward kinematics of the excavator device based on the angle sensor data collected by the bucket at each spatial position, and determining the coordinates of the middle bucket tooth in the excavator coordinate system.

[0099] Step 24: Determine the coordinate calibration matrix based on the coordinates of the middle bucket teeth in the radar coordinate system and the excavator coordinate system. The coordinate calibration matrix is ​​the coordinate calibration matrix from the radar coordinate system to the excavator coordinate system.

[0100] In some embodiments of this disclosure, the coordinate calibration matrix is ​​a coordinate rotation and translation transformation matrix.

[0101] In some embodiments of this disclosure, step 24 may include at least one of steps 241-243, wherein:

[0102] Step 241: Construct data pairs of radar coordinate system coordinates and excavator coordinate system coordinates based on the coordinates of the middle bucket teeth in the radar coordinate system and the excavator coordinate system, and divide multiple data pairs into training set and test set.

[0103] Step 242: Determine the coordinate calibration matrix based on the training set data.

[0104] Step 243: Verify the coordinate calibration matrix using the test set.

[0105] Figure 3 The diagram illustrates some other embodiments of the bucket coordinate calibration method disclosed herein. Preferably, this embodiment can be executed by the bucket coordinate calibration device, calibration system, computer device, or coordinate calibration update device of this disclosure. Figure 3 The method of the embodiment may include at least one of steps 31 to 36, wherein:

[0106] Step 31: Collect radar point cloud data and angle sensor data of the bucket at N different locations.

[0107] In some embodiments of this disclosure, N different positions refer to the bucket moving to N different spatial positions relative to the excavator coordinate system, where N is set in the program and its value is at least greater than 4. The bucket radar point cloud data is data collected based on the radar coordinate system. The angle sensor data is data collected based on the excavator coordinate system.

[0108] In some embodiments of this disclosure, when collecting data, the system can detect and control the N different spatial locations to make them significantly different, such as collecting data according to different slewing intervals, different bucket postures, and different boom angles. This avoids the collection locations being too concentrated, resulting in data correlation, which could lead to the problem of non-convergence when calculating the coordinate calibration matrix in subsequent steps.

[0109] In some embodiments of this disclosure, during data collection, the system can detect and control the bucket to be within the radar's field of view at N different spatial locations, enabling the radar to collect as many point clouds of the bucket as possible, ensuring the configuration accuracy of the subsequent implicit pattern algorithm and improving similarity.

[0110] In some embodiments of this disclosure, during the data acquisition and calibration process, the upper slewing system, excavator arm, and bucket can move freely, but the position of the excavator undercarriage and the radar should be kept relatively fixed. Otherwise, changes in the relative position of the excavator and the radar may lead to inaccurate calibration. Of course, the system can also be configured to recalibrate when a change in relative position is detected.

[0111] Step 32: Based on the implicit shape model algorithm, calculate the coordinates PL of the N bucket teeth in the radar coordinate system.

[0112] In some embodiments of this disclosure, step 32 may include: calculating the coordinates PL of the middle bucket tooth in the radar coordinate system based on the implicit shape model algorithm for the bucket radar point cloud collected at each spatial location.

[0113] Step 33: Based on the forward kinematics solution of the angle sensor, calculate the coordinates PW of the corresponding N bucket intermediate teeth in the excavator coordinate system;

[0114] In some embodiments of this disclosure, step 33 may include: obtaining the coordinates PW of the middle bucket tooth in the excavator coordinate system based on the kinematic forward kinematics of the angle sensor data collected at each spatial location of the bucket.

[0115] Step 34: Construct (PL, PW) data pairs and randomly divide them into training and test sets.

[0116] In some embodiments of this disclosure, step 34 may include: constructing (PL, PW) data pairs by matching the bucket tooth coordinates PL and PW obtained in the above steps one-to-one according to their corresponding positions, and randomly dividing the training set and the test set, wherein the division ratio can be set according to the number of points collected cumulatively.

[0117] Step 35: Use the RANSAC (RAndom Sampling Consensus) estimation algorithm to obtain the coordinate calibration matrix R|T from the training set data.

[0118] In some embodiments of this disclosure, step 35 may include: calculating the coordinate calibration matrix R|T using the RANSAC estimation algorithm on the training set data according to the coordinate calibration model PW = R*PL + T. This disclosure uses the RANSAC estimation algorithm to avoid interference from noisy data, ensuring accurate and reliable estimation of R|T.

[0119] In some embodiments of this disclosure, the purpose of coordinate calibration is to find a suitable R|T, transform the coordinates of the middle bucket teeth in the radar coordinate system to the excavator coordinate system, and calculate the error with the corresponding point, hoping that the mean square error of all data pairs is minimized, that is, to find the minimum value of formula (1).

[0120]

[0121] The inventors discovered through research that the relevant technology uses the least squares method, DLT (Direct Linear Transformation), to directly calculate the matrix. However, this method sometimes leads to unstable calculation results due to reasons such as numerical calculation of the matrix, inaccurate point correspondence, and especially the existence of outliers.

[0122] The above steps of this disclosed solution use an implicit shape model algorithm to calculate the bucket coordinates based on the bucket point cloud. The underlying method is to register the actual bucket point cloud with the model point cloud. The bucket point cloud collected on site and the model typically have a registration similarity. The higher the similarity, the higher the accuracy of the calculated bucket coordinates. That is, the accuracy of the bucket coordinates is affected by the model similarity. Therefore, this solution uses the RANSAC random sampling estimation algorithm to solve the coordinate calibration matrix R|T.

[0123] In some embodiments of this disclosure, Figure 2 Step 242 of the embodiment or Figure 3 Step 35 of the embodiment may include at least one of steps 351 to 359, wherein:

[0124] Step 351: Initialize relevant parameters, including parameters such as iteration count, threshold, maximum number of inliers, and inlier probability.

[0125] Steps 352 to 359 are iterative calculations.

[0126] Step 352: Randomly select a predetermined number of first data pairs, wherein the data pairs are point pairs.

[0127] In some embodiments of this disclosure, the predetermined quantity can be 4.

[0128] In some embodiments of this disclosure, step 352 may include: randomly selecting 4 point pairs.

[0129] Step 353: Determine if the first data pair is collinear. If they are collinear, return to step 351.

[0130] Step 354: In the case that the first data pairs are not collinear, the coordinate calibration matrix is ​​determined by direct linear transformation, that is, R|Ti is calculated using DLT.

[0131] Step 355: Using the coordinate calibration matrix R|Ti, the radar coordinate system coordinates PLi in the second data pair are transformed to obtain the excavator coordinate system coordinates PWi. The second data pair consists of the other data pairs in the training set excluding the first data pair.

[0132] Step 356: Calculate the distance deviation between the transformed excavator coordinate system coordinates and the actual excavator coordinate system coordinates.

[0133] Step 357: Determine whether the distance deviation is less than the predetermined distance threshold.

[0134] Step 358: Based on the number of iterations and the predetermined distance threshold, record the interior points that meet the conditions and update the coordinate calibration matrix R|T.

[0135] Step 359: Calculate the interior point probability and update the iteration count based on the interior point probability.

[0136] Verification has shown that the RANSAC estimation algorithm used in this disclosure can robustly estimate model parameters and can estimate parameters with high accuracy from datasets containing a large number of outliers.

[0137] Step 36: Verify the coordinate calibration matrix R|T using the test set.

[0138] This disclosure uses a test set to verify the coordinate calibration matrix R|T. If the error meets the usage requirements, the calibration is complete. In subsequent excavator operations, R|T is used to transform PW to the radar coordinate system for target point excavation and unloading at the unloading point.

[0139] The bucket coordinate calibration method of this disclosure will be described below through specific embodiments. Specific Implementation Example 1:

[0141] Following field testing, PL and PW were collected at N=8 different locations; among them...

[0142] The coordinates of the middle bucket tooth in the radar coordinate system, obtained through point cloud computing, are as follows:

[0143] PL={3.233 2.986 3.233 3.634 3.972 2.986 2.789 2.651

[0144] -0.415 -0.738 -0.888 -0.367 -0.662 -0.23 -0.52 -0.696

[0145] 0.057 -0.204 -0.38 -0.058 -0.266 -0.322 -0.074 0.253}

[0146] The coordinates of the middle bucket tooth in the excavator coordinate system are obtained by using the forward kinematics solution from the angle sensor.

[0147] PW={4.27 4.20 3.94 4.04 3.60 4.6 4.53 4.43 / / x

[0148] 0.74 1.13 1.07 0.50 0.45 0.80 1.12 1.33 / / y

[0149] 0.36 0.11 -0.07 0.24 0.01 0.01 0.24 0.58} / / z

[0150] The dataset was split in a 6:4 ratio to obtain the training set, as follows:

[0151] PL_train={3.233 2.986 3.233 3.634 3.972

[0152] -0.415 -0.738 -0.888 -0.367 -0.662

[0153] 0.057 -0.204 -0.38 -0.058 -0.266}

[0154] PW_train={4.27 4.20 3.94 4.04 3.603 0.74 1.13 1.07 0.50 0.45 0.80

[0156] 0.36 0.11 -0.07 0.24 0.01}

[0157] The test set is as follows:

[0158] PL_test = {2.986 2.789 2.651}

[0159] -0.23 -0.52 -0.696

[0160] -0.322 -0.074 0.253}

[0161] PW_test={4.6 4.53 4.43 0.80 1.12 1.33

[0163] 0.01 0.24 0.58}

[0164] The coordinate calibration matrix is ​​estimated using the RANSAC algorithm, resulting in R|T, where:

[0165] R = {-0.7098 0.7033 -0.0408}

[0166] -0.7028 -0.7109 -0.0273

[0167] -0.0482 0.0093 0.9988}

[0168] T = {6.8549} 2.7214

[0170] 0.4704}

[0171] Verification is performed using tests, where res = PW_test – (PL_test * R + T), yielding the deviation matrix. This matrix provides the error magnitude res for each point in the x, y, and z directions, and the mean squared error RE2, as shown below:

[0172] res = {-0.0131-0.0173 0.0435}

[0173] -0.0048 0.0131 0.0162

[0174] -0.0073 0.0172 0.0088}

[0175] RE2 = 0.0189

[0176] The maximum error is 4.35cm, and the mean square error is 1.89cm. This meets the requirements for bulk material excavation operations.

[0177] Figure 4 The diagram illustrates some embodiments of the coordinate calibration and update method of this disclosure. Preferably, this embodiment can be executed by the calibration system, computer device, or coordinate calibration and update device of this disclosure. Figure 4 The method of the embodiment may include at least one of steps 41 to 44, wherein:

[0178] Step 41: Determine whether the online error of the coordinate calibration matrix is ​​greater than the predetermined allowable error.

[0179] Step 42: If the online error of the coordinate calibration matrix is ​​greater than the predetermined allowable error, then determine whether the number of collected location point data pairs has reached the predetermined number of location points.

[0180] Step 43: When the number of collected location point data pairs is equal to the predetermined number of location points, adopt any of the above embodiments (e.g., Figure 2 or Figure 3 The bucket coordinate calibration method described in the embodiment determines a new coordinate calibration matrix.

[0181] Step 44: Update the coordinate calibration matrix.

[0182] Figure 5 The diagram illustrates some other embodiments of the coordinate calibration and update method of this disclosure. Preferably, this embodiment can be executed by the calibration system, computer device, or coordinate calibration and update device of this disclosure. Figure 5 The method of the embodiment may include at least one of steps S1 to S9, wherein:

[0183] Step S1: Set automatic calibration parameters: number of location points N, predetermined similarity A, division ratio B, and predetermined allowable error C.

[0184] In some embodiments of this disclosure, the number of position points N refers to the number of different spatial positions to which the bucket moves relative to the excavator coordinate system. N is set in the program and its value is at least greater than 4.

[0185] In some embodiments of this disclosure, the predetermined similarity A refers to the degree of registration similarity between the implicit shape model algorithm bucket point cloud and the model bucket point cloud.

[0186] In some embodiments of this disclosure, the partition ratio B refers to the partition ratio of the (PL, PW) training set to the test set.

[0187] In some embodiments of this disclosure, the predetermined allowable error C refers to the error required to meet usage requirements. The automatic calibration parameters can be set via a configuration file.

[0188] Step S2: Determine whether the online error is greater than the set predetermined allowable error C.

[0189] In some embodiments of this disclosure, the online error is calculated using the formula PW-R*PL+T. When the system is used for the first time, or when the relative position of the excavator and the radar changes, the online error will be greater than the set allowable error. At this time, the automatic calibration program will be entered, proceeding to step S3. After successful calibration, the calibration program will exit directly.

[0190] Step S3: Determine whether the number of collected point pairs (number of location point data pairs) is less than the set number of location points N. If the number of collected location point data pairs is less than the predetermined number of location points, proceed to step S4; if the number of collected location point data pairs is equal to the predetermined number of location points, proceed to step S8.

[0191] Step S4: Collect point cloud data of the bucket radar and determine one coordinate of the middle bucket tooth in the radar coordinate system.

[0192] In some embodiments of this disclosure, step S4 may include: collecting bucket radar point cloud data and obtaining the coordinates PL1 of the middle bucket tooth based on an implicit shape model algorithm.

[0193] In some embodiments of this disclosure, when collecting data, the bucket is collected within the appropriate visual angle range of the radar according to different positions of the bucket relative to the excavator, so as to collect reasonable bucket point clouds, increase the model registration success rate, and improve model similarity.

[0194] Step S5: Determine whether the model similarity is greater than the predetermined set value A.

[0195] In some embodiments of this disclosure, if the model similarity pair is greater than a predetermined set value A, then the coordinate PL1 of the middle bucket tooth is obtained based on the implicit shape model algorithm, and the process proceeds to step S6 to obtain the coordinate PW1 of the middle bucket tooth at that position in the excavator coordinate system.

[0196] Step S6: Collect angle sensor data of the bucket and determine one coordinate of the middle bucket tooth in the excavator coordinate system.

[0197] In some embodiments of this disclosure, step S6 may include: acquiring angle sensor data of the bucket and calculating the coordinate PW1 of the middle bucket tooth based on the forward kinematics of the angle sensor.

[0198] Step S7: Accumulate the number of location points.

[0199] In some embodiments of this disclosure, step S7 may include: counting the number of successfully paired (PL1, PW1) point pairs. When the data equals N, proceed to step S8.

[0200] Step S8: Use the calibration algorithm to calibrate the coordinate calibration matrix R|T.

[0201] In some embodiments of this disclosure, step S8 may include: when the number of collected location point data pairs is equal to the predetermined number of location points, employing any of the above embodiments (e.g., Figure 2 or Figure 3 The bucket coordinate calibration method described in the embodiment determines a new coordinate calibration matrix.

[0202] Step S9: Automatically update the coordinate calibration matrix R|T.

[0203] Once this public calibration is successful, the R|T can be automatically updated or the operator can be prompted to decide whether to use it.

[0204] To address the issues of low calibration accuracy, time-consuming and labor-intensive nature, requirement for special scenarios or dedicated calibration equipment, lack of online verification, and inability to calibrate online, such as direct measurement, manual point sampling, and scene feature methods, this disclosure provides a coordinate calibration method and automatic update method based on LiDAR and angle sensors:

[0205] First, this disclosure allows for calibration without requiring any additional calibration equipment on the existing system.

[0206] Secondly, this disclosure uses model similarity filtering and employs the RANSAC estimation algorithm to improve calibration accuracy.

[0207] Third, this disclosure provides an online verification function by randomly partitioning the dataset.

[0208] Fourth, this disclosure can automatically update the calibration when the relative position of the excavator and the radar changes, and when the coordinate calibration matrix produces drift errors.

[0209] Figure 6 These are schematic diagrams of some embodiments of the bucket coordinate calibration device disclosed herein. Figure 6 As shown, the bucket coordinate calibration device disclosed herein may include a data acquisition module 61, a positioning module 62, and a calibration module 63, wherein:

[0210] The data acquisition module 61 is configured to acquire radar point cloud data and angle sensor data of the bucket.

[0211] In some embodiments of this disclosure, the data acquisition module 61 is configured to collect radar point cloud data and angle sensor data of the bucket when the bucket is in multiple different positions.

[0212] The positioning module 62 is configured to determine the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data of the bucket; and to determine the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data of the bucket.

[0213] In some embodiments of this disclosure, the positioning module 62 is configured to determine the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data of the bucket at each spatial location, when the positioning module 62 determines the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data of the bucket.

[0214] In some embodiments of this disclosure, the positioning module 62, after determining the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data of the bucket, determines the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data collected at each spatial position of the bucket and an implicit shape model algorithm.

[0215] In some embodiments of this disclosure, the positioning module 62 is configured to determine the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data collected by the bucket at each spatial position, when the positioning module 62 determines the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data of the bucket.

[0216] In some embodiments of this disclosure, the positioning module 62, when determining the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data of the bucket, is configured to obtain the forward kinematics of the excavator device based on the angle sensor data collected at each spatial position of the bucket, and determine the coordinates of the middle bucket tooth in the excavator coordinate system.

[0217] The calibration module 63 is configured to determine a coordinate calibration matrix based on the coordinates of the bucket's middle teeth in the radar coordinate system and the excavator coordinate system, wherein the coordinate calibration matrix is ​​the coordinate calibration matrix from the coordinates of the bucket's middle teeth in the radar system to the coordinate calibration matrix in the excavator coordinate system.

[0218] In some embodiments of this disclosure, the coordinate calibration matrix is ​​a coordinate rotation and translation transformation matrix.

[0219] In some embodiments of this disclosure, the calibration module 63, when determining the coordinate calibration matrix based on the coordinates of the bucket's intermediate teeth in the radar coordinate system and the excavator coordinate system, is configured to construct data pairs of radar coordinate system coordinates and excavator coordinate system coordinates based on the coordinates of the bucket's intermediate teeth in the radar coordinate system and the excavator coordinate system, and divide multiple data pairs into training sets and test sets; determine the coordinate calibration matrix based on the training set data; and verify the coordinate calibration matrix using the test set data.

[0220] In some embodiments of this disclosure, the calibration module 63, after determining the coordinate calibration matrix based on the training set data, is configured to initialize relevant parameters, wherein the relevant parameters include the number of iterations; randomly select a predetermined number of first data pairs; determine whether the first data pairs are collinear; if the first data pairs are not collinear, determine the coordinate calibration matrix using a direct linear transformation; use the coordinate calibration matrix to transform the radar coordinate system coordinates in the second data pair to obtain the excavator coordinate system coordinates, wherein the second data pair is the other data pairs in the training set excluding the first data pair; calculate the distance deviation between the transformed excavator coordinate system coordinates and the actual excavator coordinate system coordinates; determine whether the distance deviation is less than a predetermined distance threshold; based on the number of iterations and the predetermined distance threshold, record the interior points that meet the conditions and update the coordinate calibration matrix; calculate the interior point probability and update the number of iterations based on the interior point probability.

[0221] In some embodiments of this disclosure, the bucket coordinate calibration device is used to perform any of the embodiments described above (e.g., Figure 2 or Figure 3 The operation of the bucket coordinate calibration method described in the embodiment)

[0222] Figure 7 These are schematic diagrams illustrating some embodiments of the coordinate calibration and update device disclosed herein. Figure 7 As shown, the coordinate calibration and update device disclosed herein may include a judgment device 71, a bucket coordinate calibration device 72, and an update device 73, wherein:

[0223] The judgment device 71 is configured to determine whether the online error of the coordinate calibration matrix is ​​greater than a predetermined allowable error; if the online error of the coordinate calibration matrix is ​​greater than the predetermined allowable error, it determines whether the number of collected location point data pairs has reached a predetermined number of location points.

[0224] The bucket coordinate calibration device 72 is configured to determine a new coordinate calibration matrix using a bucket coordinate calibration method when the number of collected location point data pairs is equal to the predetermined number of location points.

[0225] The updating device 73 is configured to update the coordinate calibration matrix.

[0226] In some embodiments of this disclosure, the bucket coordinate calibration device is as described in any of the above embodiments (e.g., Figure 6 The bucket coordinate calibration device described in the embodiment)

[0227] In some embodiments of this disclosure, the judging device 71 is further configured to, when the number of collected location point data pairs is less than the predetermined number of location points, collect bucket radar point cloud data to determine one coordinate of the middle bucket tooth in the radar coordinate system; collect bucket angle sensor data to determine one coordinate of the middle bucket tooth in the excavator coordinate system; accumulate the number of location point data pairs, and then perform the operation of judging whether the number of collected location point data pairs has reached the predetermined number of location points again.

[0228] In some embodiments of this disclosure, when determining a coordinate of the middle bucket tooth in the radar coordinate system, the determining device 71 is configured to obtain a coordinate of the middle bucket tooth in the radar coordinate system based on an implicit shape model algorithm; determine whether the model similarity is greater than a predetermined similarity; and if the model similarity is greater than the predetermined similarity, use the coordinate of the middle bucket tooth in the radar coordinate system.

[0229] In some embodiments of this disclosure, when determining a coordinate of the middle bucket tooth in the excavator coordinate system, the determining device 71 is configured to obtain the forward kinematics of the excavator device based on angle sensor data, and determine a coordinate of the middle bucket tooth in the excavator coordinate system.

[0230] In some embodiments of this disclosure, the coordinate calibration update device is used to perform any of the above embodiments (e.g. Figure 4 or Figure 5 The operation of the coordinate calibration and update method described in the embodiment)

[0231] The above embodiments of this disclosure provide a coordinate calibration device and an automatic update device based on lidar and angle sensor. By using lidar and excavator angle sensor, the bucket coordinates are calibrated and automatically updated without adding external calibration equipment, so as to realize the unification of bucket coordinates and target excavation point coordinates in the excavator coordinate system.

[0232] Figure 8 This is a schematic diagram illustrating the structure of some embodiments of the computer device disclosed herein. For example... Figure 8 As shown, the computer device includes a memory 81 and a processor 82.

[0233] Memory 81 is used to store instructions, and processor 82 is coupled to memory 81. Processor 82 is configured to execute instructions stored in memory to implement the above embodiments (e.g., Figures 2-5 The method involved in any embodiment.

[0234] like Figure 8As shown, the computer device also includes a communication interface 83 for exchanging information with other devices. Additionally, the computer device includes a bus 84, through which the processor 82, communication interface 83, and memory 81 communicate with each other.

[0235] The memory 81 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive. The memory 81 may also be a memory array. The memory 81 may also be divided into blocks, and these blocks may be combined into virtual volumes according to certain rules.

[0236] Furthermore, processor 82 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present disclosure.

[0237] According to another aspect of this disclosure, such as Figure 1 As shown, a calibration system is provided, including a lidar and an angle sensor, and further including at least one of a computer device, a coordinate calibration and update device, and a bucket coordinate calibration device, wherein the computer device is as described in any of the above embodiments (e.g., Figure 8 The computer apparatus described in the embodiment) wherein the coordinate calibration update device is as described in any of the above embodiments (e.g. Figure 7 The coordinate calibration and update device described in the embodiment is, for example, the bucket coordinate calibration device as described in any of the above embodiments (e.g., Figure 6 The bucket coordinate calibration device described in the embodiment)

[0238] According to another aspect of this disclosure, such as Figure 1 As shown, an excavator is provided, including a lidar system, and at least one of a computer device, a coordinate calibration and update device, and a bucket coordinate calibration device, wherein the computer device is as described in any of the above embodiments (e.g., Figure 8 The computer apparatus described in the embodiment) wherein the coordinate calibration update device is as described in any of the above embodiments (e.g. Figure 7 The coordinate calibration and update device described in the embodiment is, for example, the bucket coordinate calibration device as described in any of the above embodiments (e.g., Figure 6 The bucket coordinate calibration device described in the embodiment)

[0239] This disclosure provides a coordinate calibration method and automatic update system based on lidar and angle sensor. By using lidar and excavator angle sensor, the bucket coordinates are calibrated and automatically updated without adding external calibration equipment, which can realize the unification of bucket coordinates and target excavation point coordinates in the excavator coordinate system.

[0240] According to another aspect of this disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions that, when executed by a processor, implement any of the embodiments described above (e.g., Figure 2 or Figure 3 The bucket coordinate calibration method described in the embodiment, and / or the implementation of any of the above embodiments (e.g.) Figure 4 or Figure 5 The operation of the coordinate calibration and update method described in the embodiment)

[0241] In some embodiments of this disclosure, the computer-readable storage medium may be a non-transitory computer-readable storage medium.

[0242] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, apparatus, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0243] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. 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, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0244] 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.

[0245] 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.

[0246] The computer device, bucket coordinate calibration device, data acquisition module, positioning module, calibration module, coordinate calibration update device, judgment device, bucket coordinate calibration device and update device described above can be implemented as a general-purpose processor, programmable logic controller (PLC), digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component or any suitable combination thereof for performing the functions described in this application.

[0247] This concludes the detailed description of the present disclosure. To avoid obscuring the concept of the disclosure, some details known in the art have not been described. Those skilled in the art will fully understand how to implement the technical solutions disclosed herein based on the above description.

[0248] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program instructing the relevant hardware to implement them. The program can be stored in a non-transitory computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0249] The description in this disclosure is provided for illustrative and descriptive purposes only and is not intended to be exhaustive or to limit the disclosure to its forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of this disclosure and to enable those skilled in the art to understand this disclosure and to design various embodiments with various modifications suitable for a particular purpose.

Claims

1. A method for calibrating bucket coordinates, comprising: Acquiring radar point cloud data and angle sensor data of the bucket, wherein acquiring radar point cloud data and angle sensor data of the bucket includes: collecting radar point cloud data and angle sensor data of the bucket when the bucket is in multiple different positions; Based on the radar point cloud data of the bucket, determine the coordinates of the middle bucket tooth in the radar coordinate system; Based on the angle sensor data of the bucket, determine the coordinates of the middle bucket tooth in the excavator coordinate system; Based on the coordinates of the middle bucket teeth in the radar coordinate system and the excavator coordinate system, a coordinate calibration matrix is ​​determined, wherein the coordinate calibration matrix is ​​the coordinate calibration matrix from the radar coordinate system to the excavator coordinate system of the middle bucket teeth. The determination of the coordinate calibration matrix based on the coordinates of the middle bucket teeth in the radar coordinate system and the excavator coordinate system includes: Based on the coordinates of the middle bucket teeth in the radar coordinate system and the excavator coordinate system, data pairs of radar coordinate system coordinates and excavator coordinate system coordinates are constructed, and multiple data pairs are divided into training set and test set. Determine the coordinate calibration matrix based on the training set data; Verify the coordinate calibration matrix using a test set; The step of determining the coordinate calibration matrix based on the training set data includes: Initialize relevant parameters, including the number of iterations; Randomly select a predetermined number of first data pairs; Determine whether the first data pair is collinear; In the case that the first data pairs are not collinear, a direct linear transformation is used to determine the coordinate calibration matrix.

2. The bucket coordinate calibration method according to claim 1, wherein: The step of determining the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data of the bucket includes: determining the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data collected at each spatial position of the bucket. The step of determining the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data of the bucket includes: determining the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data collected at each spatial position of the bucket.

3. The bucket coordinate calibration method according to claim 2, wherein: The step of determining the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data collected at each spatial position of the bucket includes: determining the coordinates of the middle bucket tooth in the radar coordinate system based on the implicit shape model algorithm using the radar point cloud data collected at each spatial position of the bucket. The step of determining the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data collected by the bucket at each spatial position includes: obtaining the forward kinematics solution of the excavator device based on the angle sensor data collected by the bucket at each spatial position, and determining the coordinates of the middle bucket tooth in the excavator coordinate system.

4. The bucket coordinate calibration method according to any one of claims 1-3, wherein, The coordinate calibration matrix is ​​a coordinate rotation and translation transformation matrix.

5. The bucket coordinate calibration method according to any one of claims 1-3, wherein, The step of determining the coordinate calibration matrix based on the training set data also includes: Using a coordinate calibration matrix, the radar coordinate system coordinates in the second data pair are transformed to obtain the excavator coordinate system coordinates. The second data pair consists of all other data pairs in the training set except for the first data pair. Calculate the distance deviation between the excavator coordinate system coordinates obtained from the transformation and the actual excavator coordinate system coordinates; Determine whether the distance deviation is less than a predetermined distance threshold; Based on the number of iterations and a predetermined distance threshold, record the interior points that meet the conditions and update the coordinate calibration matrix; Calculate the inlier probability and update the iteration count based on the inlier probability.

6. A coordinate calibration update method, comprising: Determine whether the online error of the coordinate calibration matrix is ​​greater than the predetermined allowable error; If the online error of the coordinate calibration matrix is ​​greater than the predetermined allowable error, then determine whether the number of collected location point data pairs has reached the predetermined number of location points. When the number of collected location point data pairs is equal to the predetermined number of location points, a new coordinate calibration matrix is ​​determined using the bucket coordinate calibration method as described in any one of claims 1-5. Update the coordinate calibration matrix.

7. The coordinate calibration and update method according to claim 6 further includes: If the number of location point data pairs collected is less than the predetermined number of location points, collect bucket radar point cloud data to determine one coordinate of the middle bucket tooth in the radar coordinate system. Collect angle sensor data of the bucket to determine one coordinate of the middle bucket tooth in the excavator coordinate system; The number of location point data pairs is accumulated, and then the step of determining whether the number of collected location point data pairs has reached the predetermined number of location points is executed again.

8. The coordinate calibration and update method according to claim 7, wherein: The determination of one coordinate of the middle bucket tooth in the radar coordinate system includes: obtaining one coordinate of the middle bucket tooth in the radar coordinate system based on an implicit shape model algorithm; determining whether the model similarity is greater than a predetermined similarity; and using the one coordinate of the middle bucket tooth in the radar coordinate system if the model similarity is greater than the predetermined similarity. Determining one coordinate of the middle bucket tooth in the excavator coordinate system includes: obtaining the forward kinematics of the excavator device based on angle sensor data, and determining one coordinate of the middle bucket tooth in the excavator coordinate system.

9. A bucket coordinate calibration device, comprising: The data acquisition module is configured to acquire radar point cloud data and angle sensor data of the bucket. Specifically, the data acquisition module is configured to collect radar point cloud data and angle sensor data of the bucket when the bucket is in multiple different positions. The positioning module is configured to determine the coordinates of the middle bucket tooth in the radar coordinate system based on the radar point cloud data of the bucket; and to determine the coordinates of the middle bucket tooth in the excavator coordinate system based on the angle sensor data of the bucket. The calibration module is configured to determine a coordinate calibration matrix based on the coordinates of the middle bucket teeth in the radar coordinate system and the excavator coordinate system, wherein the coordinate calibration matrix is ​​the coordinate calibration matrix from the coordinates of the middle bucket teeth in the radar system to the coordinates of the excavator coordinate system. The calibration module, after determining the coordinate calibration matrix based on the coordinates of the bucket's center teeth in the radar coordinate system and the excavator coordinate system, is configured to construct data pairs of radar coordinate system coordinates and excavator coordinate system coordinates based on the coordinates of the bucket's center teeth in the radar coordinate system and the excavator coordinate system, and divide multiple data pairs into training sets and test sets; determine the coordinate calibration matrix based on the training set data; and verify the coordinate calibration matrix using the test set data. The calibration module, after determining the coordinate calibration matrix based on the training set data, is configured to initialize relevant parameters, including the number of iterations; randomly select a predetermined number of first data pairs; determine whether the first data pairs are collinear; and, if the first data pairs are not collinear, determine the coordinate calibration matrix using a direct linear transformation.

10. The bucket coordinate calibration device according to claim 9, wherein, The bucket coordinate calibration device is used to implement the bucket coordinate calibration method as described in any one of claims 2-5.

11. A coordinate calibration and update device, comprising: The judgment device is configured to determine whether the online error of the coordinate calibration matrix is ​​greater than a predetermined allowable error; If the online error of the coordinate calibration matrix is ​​greater than the predetermined allowable error, determine whether the number of collected location point data pairs has reached the predetermined number of location points. The bucket coordinate calibration device is configured to determine a new coordinate calibration matrix using the bucket coordinate calibration method when the number of collected location point data pairs is equal to the predetermined number of location points. The updating device is configured to update the coordinate calibration matrix; The bucket coordinate calibration device is the bucket coordinate calibration device as described in claim 9 or 10.

12. The coordinate calibration and update device according to claim 11, wherein, The coordinate calibration and update device is used to implement the coordinate calibration and update method as described in any one of claims 6-8.

13. A computer device comprising: Memory, used to store instructions; A processor is configured to execute the instructions, causing the computer device to implement the bucket coordinate calibration method as described in any one of claims 1-5, and / or to implement the coordinate calibration update method as described in any one of claims 6-8.

14. A calibration system, comprising a lidar and an angle sensor, and further comprising at least one of a computer device, a coordinate calibration and update device, and a bucket coordinate calibration device, wherein, The computer device is the computer device as described in claim 13, the coordinate calibration and update device is the coordinate calibration and update device as described in claim 11 or 12, and the bucket coordinate calibration device is the bucket coordinate calibration device as described in claim 9 or 10.

15. An excavator, comprising a lidar system, and further comprising at least one of a computer device, a coordinate calibration and updating device, and a bucket coordinate calibration device, wherein, The computer device is the computer device as described in claim 13, the coordinate calibration and update device is the coordinate calibration and update device as described in claim 11 or 12, and the bucket coordinate calibration device is the bucket coordinate calibration device as described in claim 9 or 10.

16. A computer-readable storage medium, wherein, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the bucket coordinate calibration method as described in any one of claims 1-5, and / or implement the coordinate calibration update method as described in any one of claims 6-8.

Images