Wet spraying mechanical arm control method and system, wet spraying trolley, storage medium and program product

Abstract

The invention relates to a wet spraying mechanical arm control method and system, a wet spraying trolley, a storage medium and a program product. The method comprises the steps that the three-dimensional arch frame position where an arch frame in a to-be-sprayed face is located is obtained; according to the three-dimensional arch center position and the arch center point cloud sample, a target operation path matched with the to-be-sprayed face is determined from guniting paths corresponding to the arch center point cloud sample, and the target operation path comprises a plurality of ordered to-be-sprayed face operation path points under an arch center coordinate system; generating a target nozzle pose parameter corresponding to each to-be-sprayed surface operation route point by adopting a spraying pose prediction model; and the target nozzle pose parameters are converted into corresponding mechanical arm joint positions, and a wet spraying mechanical arm is controlled to conduct spraying operation on the to-be-sprayed face along the target operation path according to the mechanical arm joint positions. By the adoption of the method, the arch center position and the guniting path can be combined, rapid reuse of the historical guniting path is achieved, and high guniting consistency is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel construction, and in particular to a wet spraying robot arm control method, system, wet spraying trolley, computer-readable storage medium and computer program product. Background Art

[0002] The wet spraying trolley is a large machine used in the spraying process. The operator can stand near the working surface of the wet spraying trolley to observe the position and status of the working surface of the wet spraying trolley. According to the judgment results of the position and status of the working surface based on personal experience, the remote control is operated to control the movement of the mechanical arm of the wet spraying trolley to complete the spraying operation. However, the spraying quality obtained by the above-mentioned manual operation of the wet spraying trolley spraying depends on the personal experience of the operator, and it is easy to have the problem of poor consistency of the spraying. Summary of the invention

[0003] Based on this, it is necessary to provide a wet spraying robot arm control method, system, wet spraying trolley, computer-readable storage medium and computer program product that can improve the consistency of spraying in response to the above-mentioned technical problems.

[0004] In a first aspect, the present application provides a wet spraying robot arm control method, comprising:

[0005] Obtain the three-dimensional arch frame position of the arch frame in the surface to be sprayed;

[0006] According to the three-dimensional arch position and the arch point cloud sample, a target operation path matching the to-be-sprayed surface is determined from the shotcrete path corresponding to the arch point cloud sample, wherein the target operation path includes a plurality of ordered operation route points of the to-be-sprayed surface in the arch coordinate system;

[0007] A spray posture prediction model is used to generate target nozzle posture parameters corresponding to each working route point of the surface to be sprayed, wherein the spray posture prediction model is trained based on nozzle posture samples and samples of the points to be sprayed corresponding to the nozzle posture samples;

[0008] The target nozzle posture parameters are converted into corresponding robot arm joint positions, and the wet spraying robot arm is controlled according to the robot arm joint positions to perform spraying operations on the surface to be sprayed along the target operation path.

[0009] In one embodiment, the method for generating the spraying path includes:

[0010] Acquire an arch point cloud sample of a surface sample to be sprayed, a shotcrete point cloud sample of the surface sample to be sprayed, and joint motion data for the surface sample to be sprayed;

[0011] Perform three-dimensional rendering of the process of the wet spraying mechanical arm performing the spraying operation on the sample of the surface to be sprayed according to the arch point cloud sample, the spraying point cloud sample and the joint motion data, and generate spraying process data and spraying effect data corresponding to the sample of the surface to be sprayed;

[0012] The spraying path that meets the preset conditions is obtained by screening the spraying process data according to the spraying effect data.

[0013] In one embodiment, the step of selecting a spraying path that meets preset conditions from the spraying process data according to the spraying effect data includes:

[0014] Sending the shotcrete process data and the shotcrete effect data to a client for display;

[0015] In response to the selection operation of the client, a spraying path in which the spraying effect data satisfies the preset condition is determined.

[0016] In one embodiment, the training method of the injection posture prediction model includes:

[0017] Determine the corresponding nozzle posture sample according to the joint motion data, and determine the to-be-sprayed point position sample corresponding to the nozzle posture sample from the spraying path according to the joint motion data;

[0018] Using the samples of the points to be sprayed as training data, and inputting the nozzle posture samples corresponding to the samples of the points to be sprayed as training labels into an initial prediction model, wherein the initial prediction model includes a plurality of decision trees;

[0019] Generate a posture prediction result corresponding to the to-be-sprayed point sample through each decision tree in the initial prediction model;

[0020] Determining a target prediction result from the posture prediction results according to the voting results of the posture prediction results generated by each decision tree by the initial prediction model;

[0021] When the loss value between the target prediction result and the nozzle posture sample meets a preset training threshold, the initial prediction model is used as the injection posture prediction model.

[0022] In one of the embodiments, before obtaining the three-dimensional arch position of the arch in the surface to be sprayed, the method further includes:

[0023] Obtaining current inclinometer parameters of the wet spraying robotic arm;

[0024] Calibrating the wet spraying mechanical arm according to the inclinometer parameters until the wet spraying mechanical arm is in a leveling state;

[0025] In the working environment where the wet spraying robot arm in the leveling state is located, the three-dimensional position information of multiple preset arch points is scanned;

[0026] According to the three-dimensional position information of each preset arch point, the three-dimensional point cloud position of the current wet spraying mechanical arm in the arch coordinate system is located.

[0027] In one embodiment, the method further comprises:

[0028] Obtaining real-time joint positions of different parts of the wet spraying robot arm;

[0029] When the real-time joint positions of any two parts are less than a preset distance threshold, or the distance between the real-time joint position of any part and the surface to be sprayed is less than the preset distance threshold, a distance alarm message corresponding to the wet spraying robot arm is generated, and the movement speed of the wet spraying robot arm is controlled to decrease.

[0030] In a second aspect, the present application also provides a wet spraying robot arm control system, comprising:

[0031] An arch positioning module is used to obtain the three-dimensional arch position of the arch in the surface to be sprayed;

[0032] A path determination module is used to determine a target operation path matching the surface to be sprayed from the spraying path corresponding to the arch point cloud sample according to the three-dimensional arch position and the arch point cloud sample, wherein the target operation path includes a plurality of ordered operation route points of the surface to be sprayed in the arch coordinate system;

[0033] A posture prediction module, used to generate target nozzle posture parameters corresponding to each working route point of the to-be-sprayed surface by using a spray posture prediction model, wherein the spray posture prediction model is obtained by training based on nozzle posture samples and to-be-sprayed point samples corresponding to the nozzle posture samples;

[0034] The motion control module is used to convert the target nozzle posture parameters into corresponding robot arm joint positions, and control the wet spraying robot arm to perform spraying operations on the surface to be sprayed along the target operation path according to the robot arm joint positions.

[0035] In a third aspect, the present application also provides a wet spraying trolley, including a wet spraying mechanical arm. The wet spraying trolley also includes a three-dimensional sensing device for obtaining a three-dimensional arch position of an arch in a spraying surface;

[0036] A path planning control device is used to determine a target operation path matching the surface to be sprayed from the spraying path corresponding to the arch point cloud sample according to the three-dimensional arch position and the arch point cloud sample, wherein the target operation path includes a plurality of ordered operation route points of the surface to be sprayed in the arch coordinate system;

[0037] An injection posture prediction module is used to generate a target nozzle posture parameter corresponding to each of the working route points on the surface to be sprayed using an injection posture prediction model, wherein the injection posture prediction model is obtained by training based on nozzle posture samples and samples of the points to be sprayed corresponding to the nozzle posture samples;

[0038] A nozzle position and direction control device, used to convert the target nozzle posture parameters into corresponding robot arm joint positions;

[0039] A robot arm joint position control device is used to control the wet spraying robot arm to perform spraying operation on the surface to be sprayed along the target operation path according to the robot arm joint position.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the wet spraying robot arm control method described in any one of the embodiments of the first aspect is implemented.

[0041] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the wet spraying robot arm control method described in any one of the embodiments of the first aspect is implemented.

[0042] The wet spraying robotic arm control method, system, wet spraying trolley, computer-readable storage medium and computer program product obtain the three-dimensional arch frame position of the arch frame in the surface to be sprayed, determine the target operation path matching the surface to be sprayed from the spraying path corresponding to the arch frame point cloud sample according to the three-dimensional arch frame position and the arch frame point cloud sample, use the spraying posture prediction model to generate target nozzle posture parameters corresponding to each operation route point of the surface to be sprayed in the target operation path, convert the target nozzle posture parameters into the corresponding robotic arm joint position, and control the wet spraying robotic arm to spray the surface to be sprayed along the target operation path according to the robotic arm joint position, and can combine the arch frame position with the spraying path, and use the similarity between the three-dimensional arch frame position in the current surface to be sprayed and the arch frame point cloud sample in the historical spraying operation to quickly select the target operation path that meets the current spraying operation scene from the spraying path used in the historical spraying operation, which not only realizes the rapid reuse of the historical spraying path and ensures a high spraying consistency, but also simplifies the data processing amount of the target operation path and improves the control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 1. is an application environment diagram of a wet spraying robot arm control method in one embodiment;

[0045] Figure 2 A schematic diagram of a flow chart of a wet spraying robot arm control method in one embodiment;

[0046] Figure 3 A schematic flow chart of a shotcrete path generation step in one embodiment;

[0047] Figure 4 A flowchart of a prediction model training step in one embodiment;

[0048] Figure 5 A schematic diagram of a flow chart of a leveling and positioning step in one embodiment;

[0049] Figure 6 is a structural block diagram of a wet spraying trolley 600 in one embodiment;

[0050] Figure 7 It is a structural block diagram of a wet spraying trolley 700 in another embodiment;

[0051] Figure 8 is a schematic diagram of a spraying path in one embodiment;

[0052] Fig. 9 1 is a structural block diagram of a wet spraying robot control system 900 in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0055] The wet spraying robot arm control method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the robot arm control device 102 can be installed in the same wet spraying trolley as the wet spraying robot arm 104, or can communicate with the wet spraying robot arm 104 through a network or a bus.

[0056] Specifically, the robot control device 102 can obtain the three-dimensional arch position of the arch in the surface to be sprayed where the wet spray robot 104 currently needs to perform spraying operation. The robot control device 102 can determine the target operation path that matches the current surface to be sprayed from the spraying path corresponding to the arch point cloud sample based on the three-dimensional arch position and the arch point cloud sample pre-stored in the database or obtained from the network. Among them, the target operation path includes a number of ordered operation route points of the surface to be sprayed in the arch coordinate system. The robot control device 102 can use the spraying posture prediction model to generate the target nozzle posture parameters corresponding to each operation route point of the surface to be sprayed. Among them, the spraying posture prediction model can be obtained by training based on the nozzle posture sample and the sample of the point to be sprayed corresponding to the nozzle posture sample. The robot control device 102 can convert the target nozzle posture parameter into the corresponding robot joint position, and control the wet spray robot 104 to spray the surface to be sprayed along the target operation path according to the robot joint position.

[0057] The robot arm control device 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. IoT devices may be smart TVs, smart car-mounted devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices may be terminal devices such as virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, or independent physical servers, server clusters or distributed systems consisting of multiple physical servers, cloud servers providing cloud computing services, or systems consisting of terminals and servers.

[0058] In an exemplary embodiment, Figure 2 As shown, a wet spraying robot arm control method is provided, and the method is applied to Figure 1 The robot arm control device 102 in FIG. 1 is taken as an example to illustrate the method, which includes the following steps S202 to S208. Among them:

[0059] Step S202, obtaining the three-dimensional arch position of the arch in the surface to be sprayed.

[0060] The surface to be sprayed can be used to indicate the working area where the wet spraying robot arm needs to perform spraying operations, such as the exposed rock wall in a tunnel.

[0061] Arches can be used to characterize a type of support structure in a tunnel.

[0062] For example, the robot control device can communicate with the wet spray robot arm through a three-dimensional sensing device such as a laser radar and an ultrasonic sensor to obtain the three-dimensional point cloud data of the spray surface to be sprayed by the wet spray robot arm. Target detection is performed on the three-dimensional point cloud data of the spray surface to be sprayed, so as to obtain the three-dimensional arch position where the arch point cloud data matching the arch features (such as shape features, grayscale features, etc.) is located.

[0063] Step S204, according to the three-dimensional arch position and the arch point cloud sample, determine the target operation path matching the surface to be sprayed from the shotcrete path corresponding to the arch point cloud sample, and the target operation path includes a plurality of ordered operation route points of the surface to be sprayed in the arch coordinate system.

[0064] Among them, the arch point cloud sample can be used to represent the arch point cloud data collected in the working scene of the historical shotcrete operation performed before the current moment.

[0065] The shotcrete path can be used to characterize the motion path of the wet shotcrete manipulator when performing historical shotcrete operations on the arch point cloud sample. The shotcrete path can include a series of operation route points discretized by the wet shotcrete manipulator in the arch coordinate system.

[0066] The arch coordinate system can be used to represent a three-dimensional space coordinate system with the arch as a reference (for example, with the end point or midpoint of the arch as the coordinate origin).

[0067] The ordered working route points of the surface to be sprayed can be used to represent the discrete points that the wet spraying robot arm passes through in the execution of the spraying operation.

[0068] Exemplarily, the robot arm control device may store several arch frame point cloud samples in different shotcrete operation scenarios and the shotcrete path for each arch frame point cloud sample in the local database in advance. The robot arm control device may compare or match the three-dimensional arch frame position of the current surface to be shotcrete and the arch frame point cloud samples in the historical shotcrete operation scenarios. According to the similarity or matching degree between the three-dimensional arch frame position and the arch frame point cloud sample, the arch frame point cloud sample corresponding to the current three-dimensional arch frame position is determined. Then, the shotcrete path that matches the corresponding arch frame point cloud sample is selected from the shotcrete path as the target operation path of the current surface to be shotcrete.

[0069] Step S206, using the injection posture prediction model to generate target nozzle posture parameters corresponding to each working route point on the surface to be sprayed, the injection posture prediction model is trained based on the nozzle posture samples and the samples of the points to be sprayed corresponding to the nozzle posture samples.

[0070] Among them, the injection posture prediction module can be used to characterize a pre-trained neural network model.

[0071] The target nozzle posture parameters may include but are not limited to any one or more of the parameters such as the position of the wet spray robot arm nozzle and the direction of the nozzle.

[0072] The nozzle posture samples may include but are not limited to sample data such as nozzle positions and nozzle directions used in historical shotcrete operations.

[0073] The sample of the point position to be sprayed can be used to represent the position to be sprayed corresponding to the nozzle posture sample in the historical spraying operation.

[0074] Exemplarily, the robot arm control device may be deployed with an injection posture prediction module pre-trained using nozzle posture samples and samples of points to be sprayed corresponding to the nozzle posture samples. The currently determined working route points of the surface to be sprayed corresponding to the surface to be sprayed are input into the injection posture prediction model to obtain target nozzle posture parameters corresponding to each current working route point of the surface to be sprayed, which are predicted and generated by the injection posture prediction model based on the prior knowledge learned in the pre-training stage.

[0075] Step S208, converting the target nozzle posture parameters into corresponding robot arm joint positions, and controlling the wet spraying robot arm to perform spraying operations on the spraying surface along the target operation path according to the robot arm joint positions.

[0076] Exemplarily, a robot arm kinematics algorithm may be stored in the robot arm control device. The robot arm kinematics algorithm is used to calculate and process the target nozzle posture parameters to obtain the robot arm joint positions corresponding to the target nozzle posture parameters. A control instruction carrying the robot arm joint position is generated, and the control instruction is sent to the wet spraying robot arm to control the wet spraying robot arm to perform the spraying operation on the spraying surface according to the movement sequence of the robot arm joint positions corresponding to the target operation path.

[0077] In the above-mentioned wet spraying robot arm control method, by obtaining the three-dimensional arch frame position where the arch frame is located in the surface to be sprayed, the target operation path matching the surface to be sprayed is determined from the spraying path corresponding to the arch frame point cloud sample according to the three-dimensional arch frame position and the arch frame point cloud sample, and the spraying posture prediction model is used to generate the target nozzle posture parameters corresponding to each operation route point of the surface to be sprayed in the target operation path, and the target nozzle posture parameters are converted into the corresponding robot arm joint position, and the wet spraying robot arm is controlled to spray the surface to be sprayed along the target operation path according to the robot arm joint position. The arch frame position can be combined with the spraying path, and the similarity between the three-dimensional arch frame position in the current surface to be sprayed and the arch frame point cloud sample in the historical spraying operation can be used to quickly select the target operation path that meets the current spraying operation scene from the spraying path used in the historical spraying operation, and the required joint position is reversed from the target operation path for motion control, which not only realizes the rapid reuse of the historical spraying path and ensures a high spraying consistency, but also simplifies the data processing amount of the target operation path and improves the control efficiency.

[0078] In an exemplary embodiment, Figure 3 As shown, a method for generating a spraying path is also provided, including the following steps S302 to S306. Among them:

[0079] Step S302, obtaining the arch point cloud sample of the surface sample to be sprayed, the shotcrete point cloud sample of the surface sample to be sprayed, and the joint motion data for the surface sample to be sprayed.

[0080] Step S304, three-dimensionally render the process of the wet spraying robot arm performing spraying operation on the sample of the surface to be sprayed according to the arch point cloud sample, the spraying point cloud sample and the joint motion data, and generate spraying process data and spraying effect data corresponding to the sample of the surface to be sprayed.

[0081] The arch point cloud sample can be used to characterize the point cloud sample corresponding to the arch before the spraying of the surface sample to be sprayed. The spraying point cloud data can be used to characterize the point cloud sample after the spraying operation of the surface sample to be sprayed is completed.

[0082] The joint motion data can be used to characterize the movement direction, movement position, movement speed and other data of the joints of the wet spraying robot arm during the execution of historical wet spraying operations.

[0083] The shotcrete process data may include but is not limited to the motion path of the wet shotcrete robot arm, the three-dimensional point cloud model of the sample to be shotcrete before and after the shotcrete operation, etc.

[0084] The shotcrete effect data can be used to characterize the shotcrete speed, the surface quality of the surface to be shotcrete after shotcrete, the amount of material used for shotcrete and other data.

[0085] Exemplarily, the robotic arm control device can read the arch point cloud sample of the surface sample to be sprayed, the spraying point cloud sample of the surface sample to be sprayed, and the joint motion data of the wet spraying robotic arm for the surface sample to be sprayed after the historical spraying operation is completed. The arch point cloud sample is used for three-dimensional rendering to obtain a three-dimensional point cloud model of the surface to be sprayed before the spraying operation. The joint motion data of the wet spraying robotic arm for the surface sample to be sprayed is used for three-dimensional rendering to obtain the motion trajectory of the wet spraying robotic arm performing the spraying operation on the surface sample to be sprayed. The spraying point cloud data is used for three-dimensional rendering to obtain a three-dimensional point cloud model of the surface to be sprayed after the spraying operation. By integrating the three-dimensional point cloud data of the surface sample to be sprayed before the spraying operation, the motion trajectory of the wet spraying robotic arm, and the three-dimensional point cloud data of the surface sample to be sprayed after the spraying operation, the spraying process data of the wet spraying robotic arm performing the spraying operation on the surface sample to be sprayed can be formed. According to the difference between the arch point cloud sample and the shotcrete point cloud sample of the surface sample to be sprayed, the movement speed corresponding to the joint movement data and other parameters, combined with the preset scoring strategy, the shotcrete effect data of the wet spraying robot arm can be generated.

[0086] Step S306, screening the spraying path that meets the preset conditions from the spraying process data according to the spraying effect data.

[0087] For example, the robot arm control device can obtain the spraying process data and spraying effect data corresponding to each spraying operation after the operator manipulates the wet spraying robot arm to repeatedly perform multiple spraying operations. Priority is sorted according to the spraying process data corresponding to the spraying effect data. The robot arm motion path that meets the preset conditions in the priority sorting is used as the spraying path corresponding to the arch point cloud sample.

[0088] Optionally, in some embodiments, the preset conditions may be that the spraying speed is fast and the spraying quality of the surface sample to be sprayed is high (the surface smoothness of the surface sample to be sprayed after spraying is high and the material loss of the surface sample to be sprayed during the spraying operation is low).

[0089] In this embodiment, the process of the wet spraying robot performing the spraying operation on the sample of the surface to be sprayed is three-dimensionally rendered according to the arch point cloud sample, the spraying point cloud data and the joint motion data, and the spraying path is selected from the spraying process data according to the spraying effect data obtained by the three-dimensional rendering, so as to improve the spraying quality of the spraying path.

[0090] In an exemplary embodiment, the above step S306 may further include:

[0091] The spraying process data and the spraying effect data are sent to the client for display, and in response to the client's selection operation, a spraying path whose spraying effect data meets preset conditions is determined.

[0092] For example, the robot arm control device can send the shotcrete process data and shotcrete effect data obtained by three-dimensional rendering to the client for display, so as to realize the three-dimensional reproduction of the shotcrete operation. The shotcrete process data and shotcrete effect data displayed on the client are used to assist the user in deciding the best shotcrete path.

[0093] The robot arm control device can respond to the client's selection operation on the spraying process data based on the spraying effect data, and use the robot arm movement path in the spraying process data selected by the client as the spraying path whose spraying effect data meets the preset conditions.

[0094] In this embodiment, by sending the spraying process data and the spraying effect data to the client for display, in response to the client's selection operation, the spraying path that meets the preset conditions as the spraying effect data will be selected, and a visual display of the spraying operation can be achieved, thereby facilitating the user to select the spraying path more quickly and improving the efficiency of determining the spraying path.

[0095] In an exemplary embodiment, Figure 4 As shown, a method for training an injection posture prediction model is also provided, including the following steps S402 to S410. Among them:

[0096] Step S402, determining the corresponding nozzle posture sample according to the joint motion data, and determining the to-be-sprayed point position sample corresponding to the nozzle posture sample from the spraying path according to the joint motion data.

[0097] Exemplarily, the robot arm control device may store a robot arm motion model. According to the joint motion data and the robot arm motion model, a nozzle posture sample corresponding to the joint motion data may be calculated. According to the joint motion data, the joint motion position at each moment during the process of the wet spraying robot arm performing the spraying operation is determined. According to the arch point cloud sample within a preset distance range from the joint motion position, the to-be-sprayed point position sample corresponding to the nozzle posture sample corresponding to the joint motion data may be determined.

[0098] Step S404, using samples of points to be sprayed as training data, and inputting nozzle posture samples corresponding to the samples of points to be sprayed as training labels into an initial prediction model, wherein the initial prediction model includes a plurality of decision trees.

[0099] For example, the robot arm control device can use the samples of the points to be sprayed as training data, and the nozzle posture samples corresponding to the samples of the points to be sprayed as training labels to form a training data set. The training data set is divided into multiple training subsets. Each training subset is used to train each decision tree in the initial prediction model.

[0100] Step S406, generating posture prediction results corresponding to the to-be-printed point samples through each decision tree in the initial prediction model.

[0101] Step S408, determining a target prediction result from the pose prediction results according to the voting results of the pose prediction results generated by each decision tree through the initial prediction model.

[0102] Exemplarily, the robot arm control device can process the sample of the point to be sprayed based on its own model parameters through each decision tree in the initial prediction model to obtain the pose prediction result corresponding to the sample of the point to be sprayed generated by each decision tree. The pose prediction result generated by each decision tree is voted through the initial prediction model, and the pose prediction result with the highest vote is used as the target prediction result finally output by the initial prediction model.

[0103] Step S410, when the loss value between the target prediction result and the nozzle posture sample meets the preset training threshold, the initial prediction model is used as the injection posture prediction model.

[0104] Exemplarily, the robot arm control device can perform calculations based on the target prediction result corresponding to the sample of the point to be sprayed generated by the initial prediction model and the nozzle posture sample corresponding to the sample of the point to be sprayed, to obtain the loss value of the initial prediction model. The initial prediction model is iteratively trained according to the loss value until the target prediction result output by the trained initial prediction model and the loss value of the actual nozzle posture sample meet the preset training threshold, and the injection posture prediction model is obtained, which can avoid overfitting of the injection posture prediction model, thereby helping to improve the accuracy of the target nozzle posture parameters obtained by the subsequent use of the injection posture prediction model.

[0105] In an exemplary embodiment, Figure 5 As shown, before the above step S202, the following steps S502 to S508 may also be included. Among them:

[0106] Step S502, obtaining the current inclinometer parameters of the wet spraying robot arm.

[0107] Step S504, calibrating the wet spraying robot arm according to the inclinometer parameters until the wet spraying robot arm is in a leveling state.

[0108] Among them, the inclinometer parameters can be used to characterize the current tilt angle of the wet spraying robot arm.

[0109] For example, before starting the spraying operation, the robot arm control device can obtain the current tilt angle of the wet spraying robot arm by installing an inclinometer in the wet spraying trolley. The inclinometer parameters of the wet spraying robot arm at the current position are read. The wet spraying robot arm is calibrated according to the inclinometer parameters. For example, when the inclinometer parameters are three degrees to the left, the wet spraying robot arm can be adjusted three degrees to the right to calibrate the wet spraying robot arm to a leveling state in which the inclinometer parameters are zero.

[0110] Step S506, in the working environment where the wet spraying robot arm in the leveling state is located, scan and obtain the three-dimensional position information of a plurality of preset arch points.

[0111] Step S508, according to the three-dimensional position information of each preset arch point, locate and obtain the three-dimensional point cloud position of the current wet spraying robot arm in the arch coordinate system.

[0112] Exemplarily, after leveling, the robot control device can obtain the three-dimensional position information of multiple preset arch points in the working environment where the wet spraying robot is located. Among them, the preset arch point can be a point in the tunnel arch that is within a preset working range from the wet spraying robot. Using the three-dimensional position information of each preset arch point and the posture relationship between the wet spraying robot and the scanning device of the three-dimensional position information, the position information of the current wet spraying robot relative to the preset arch point can be located, that is, the three-dimensional point cloud position in the arch coordinate system.

[0113] Optionally, in some embodiments, the number of preset arch points may be two or more.

[0114] In this embodiment, by performing leveling, calibration and positioning on the wet spraying robot arm, the control accuracy of the wet spraying robot arm in the leveled state in subsequent use can be improved.

[0115] In an exemplary embodiment, an early warning method is also provided, including: obtaining the real-time joint positions of different parts in the wet spraying robot arm; when the real-time joint positions of any two parts are less than a preset distance threshold, or the distance between the real-time joint position of any part and the surface to be sprayed is less than the preset distance threshold, generating distance alarm information corresponding to the wet spraying robot arm, and controlling the movement speed of the wet spraying robot arm to decrease.

[0116] Exemplarily, after the robot arm control device controls the wet spraying robot arm to start the spraying operation, it can obtain the real-time joint positions of the three different parts of the wet spraying robot arm, namely the upper arm, the lower arm and the spray gun. Detect the distance between the real-time joint positions of any two parts, or the distance between the real-time joint position of any part and the surface to be sprayed. When the detected distance is less than the preset distance threshold, a distance alarm message corresponding to the real-time joint position corresponding to the distance can be generated, and the movement speed of the wet spraying robot arm can be automatically controlled to decrease.

[0117] In this embodiment, by detecting the real-time joint positions and issuing safety warnings based on the distance between the real-time joint positions or the distance between the real-time joint positions and the surface to be sprayed, the control safety of the robot arm control method can be improved and collisions between different parts of the robot arm can be avoided.

[0118] In an exemplary embodiment, Figure 6As shown, a wet spraying trolley 600 is provided, comprising:

[0119] The three-dimensional sensing device 610 is used to obtain the three-dimensional arch position of the arch in the surface to be sprayed.

[0120] The path planning control device 620 is used to determine the target operation path matching the surface to be sprayed from the spraying path corresponding to the arch point cloud sample according to the three-dimensional arch position and the arch point cloud sample. The target operation path includes a number of ordered operation route points of the surface to be sprayed in the arch coordinate system.

[0121] The injection posture prediction module 630 is used to generate target nozzle posture parameters corresponding to each working route point of the surface to be sprayed using an injection posture prediction model. The injection posture prediction model is trained based on nozzle posture samples and the samples of the points to be sprayed corresponding to the nozzle posture samples.

[0122] The nozzle position and direction control device 640 is used to convert the target nozzle posture parameters into the corresponding robot arm joint positions.

[0123] The robot arm joint position control device 650 is used to control the wet spraying robot arm to perform spraying operations on the spraying surface along the target operation path according to the robot arm joint position.

[0124] In an exemplary embodiment, the three-dimensional sensing device 610 is also used to obtain the arch point cloud samples of the surface sample to be sprayed, the spraying point cloud samples of the surface sample to be sprayed, and the joint motion data for the surface sample to be sprayed; based on the arch point cloud samples, the spraying point cloud samples, and the joint motion data, the process of the wet spraying robot arm performing spraying operations on the surface sample to be sprayed is three-dimensionally rendered to generate spraying process data and spraying effect data corresponding to the surface sample to be sprayed; based on the spraying effect data, a spraying path that meets preset conditions is screened from the spraying process data.

[0125] In an exemplary embodiment, the three-dimensional sensing device 610 is also used to send the spraying process data and the spraying effect data to the client for display; in response to the client's selection operation, determine the spraying path in which the spraying effect data meets the preset conditions.

[0126] In an exemplary embodiment, the wet spraying trolley 600 also includes wet spraying auxiliary design software 660, which is used to determine the corresponding nozzle posture samples according to the joint motion data, and determine the point samples to be sprayed corresponding to the nozzle posture samples from the spraying path according to the joint motion data; the point samples to be sprayed are used as training data, and the nozzle posture samples corresponding to the point samples to be sprayed are input into the initial prediction model as training labels, and the initial prediction model includes multiple decision trees; each decision tree in the initial prediction model generates a posture prediction result corresponding to the point sample to be sprayed; the initial prediction model determines the target prediction result from the posture prediction results according to the voting results of the posture prediction results generated by each decision tree; when the loss value of the target prediction result and the nozzle posture sample meets the preset training threshold, the initial prediction model is used as the injection posture prediction model.

[0127] In an exemplary embodiment, the wet spraying trolley 600 also includes a dual-axis inclinometer 670 for collecting inclinometer parameters, and the three-dimensional sensing device 610 is also used to scan and obtain the three-dimensional position information of multiple preset arch frame points, and locate the three-dimensional point cloud position of the current wet spraying robotic arm in the arch frame coordinate system according to the three-dimensional position information of each preset arch frame point.

[0128] In an exemplary embodiment, the wet spraying trolley 600 also includes a robotic arm joint position monitoring device 680 for obtaining the real-time joint positions of different parts in the wet spraying robotic arm; the collision warning module 690 is used to generate distance alarm information corresponding to the wet spraying robotic arm when the real-time joint positions of any two parts are less than a preset distance threshold, or the distance between the real-time joint position of any part and the surface to be sprayed is less than the preset distance threshold, and control the movement speed of the wet spraying robotic arm to decrease.

[0129] In an exemplary embodiment, Figure 7 As shown, a wet spraying trolley 700 and an arch frame 720 are also provided, including: a robotic arm body 701, a trolley walking system 702, a three-dimensional sensing device 703, a path planning control device 704, a dual-axis inclinometer 705, a spraying posture prediction module 706, a collision warning device 707, a nozzle position and direction control device 708, a robotic arm joint position monitoring device 709, a robotic arm joint position control device 710, a human-computer interaction device 711, a data generating device 712, and a wet spraying auxiliary design software 713.

[0130] During the big data generation and artificial intelligence model training stage of the shotcrete operation: the wet shotcrete trolley 700 can receive the operator's operating instructions through the human-machine interaction device 711, and control the trolley walking system 702 to make the wet shotcrete trolley 700 walk to the vicinity of the surface to be shotcrete. The wet shotcrete trolley 700 can be parked at any position, and the reading of the dual-axis inclinometer 705 (inclinometer parameters) can be checked to level the wet shotcrete trolley 700 according to the inclinometer parameters. The three-dimensional sensing device 703 realizes the positioning of the trolley by scanning two known points (preset arch points) on the tunnel. The three-dimensional sensing device 703 scans the surface to be shotcrete to form point cloud data before wet shotcrete (arch point cloud sample). The remote control of the data generating device 712 receives the operator's control of the mechanical arm to complete the tunnel shotcrete operation (with arch). The data generating device 712 synchronously records the motion data of each joint of the mechanical arm; after the shotcrete operation is completed, the three-dimensional sensing device 703 scans the working surface again to form point cloud data after wet shotcrete (shotcrete point cloud sample). The motion data of each joint of the robot arm and the point cloud data before and after wet spraying are imported into the wet spraying auxiliary design software 713 to reproduce the wet spraying process and effect in a three-dimensional dynamic display. The spraying path with high spraying quality and short operation time selected by professionals is received through the human-computer interaction device 711 (with the arch frame as a reference, a discrete operation route point of the surface to be sprayed in the arch frame coordinate system is formed). The wet spraying auxiliary design software 713 has a built-in robot arm model, and the nozzle position and direction data are obtained from the motion data of each joint of the robot arm, and the corresponding point data to be sprayed (relative to the arch frame) is obtained by combining the point cloud data; the spraying posture prediction module 706 is trained by the point data to be sprayed and the nozzle position and direction data using the random forest algorithm.

[0131] Intelligent control stage: The wet spraying trolley 700 is moved to the vicinity of the surface to be sprayed through the trolley walking system 702, and the trolley can be parked at any position. The trolley is adjusted by checking the reading of the dual-axis inclinometer 705; the three-dimensional sensing device 703 realizes the positioning of the trolley by scanning two known points on the tunnel. The three-dimensional sensing device 703 scans the surface to be sprayed to form point cloud data before wet spraying. The path planning control device 704 recommends the optimal spraying path according to the arch position in the point cloud data (a set of discrete working route points of the surface to be sprayed with the arch as a reference). The spraying posture prediction module 706 predicts the corresponding nozzle position and direction (x, y, z of the spray gun head and x, y, z of the spray gun tail) for each working route point of the surface to be sprayed (arch coordinate system, x, y, z). The nozzle position and direction control device 708 has a built-in robot arm kinematics algorithm to convert the nozzle position and direction into joint position and send it to the robot arm joint position control device 710. The robot arm joint position control device 710 has a built-in PID algorithm (proportional integral differential adjustment algorithm) to realize closed-loop control of each joint, so that the robot arm moves to the expected state. Figure 8 The shotcrete operation is carried out according to the shotcrete path shown.

[0132] Collision warning module 707: Built-in robot arm model and tunnel design outline. During the arm movement, the robot arm state is obtained from the robot arm joint position monitoring device 709 in real time, and the robot arm is divided into three parts: the upper arm, the lower arm and the spray gun. When the distance between the two parts of the robot arm or any part of the robot arm and the tunnel rock wall is less than the safe distance, an alarm is issued, and the robot arm joint position control device 710 reduces the joint movement speed.

[0133] In this embodiment, the wet spraying trolley does not require on-site operation by the operator, which can improve the work safety of the operator. At the same time, since the wet spraying trolley has learned the spraying path information during the training stage, the experience requirement for the operator of the subsequent spraying operation is relatively low, and automatic control can be achieved.

[0134] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the indications of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless clearly stated herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the steps or stages in other steps.

[0135] Based on the same inventive concept, the embodiment of the present application also provides a wet spraying robot arm control system for implementing the wet spraying robot arm control method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more wet spraying robot arm control system embodiments provided below can refer to the limitations of the wet spraying robot arm control method above, and will not be repeated here.

[0136] In an exemplary embodiment, Fig. 9 As shown, a wet spraying robot arm control system 900 is provided, including: an arch positioning module 902, a path determination module 904, a posture prediction module 906 and a motion control module 908, wherein:

[0137] The arch positioning module 902 is used to obtain the three-dimensional arch position of the arch in the surface to be sprayed;

[0138] A path determination module 904 is used to determine a target operation path matching the surface to be sprayed from the spraying path corresponding to the arch point cloud sample according to the three-dimensional arch position and the arch point cloud sample, wherein the target operation path includes a plurality of ordered operation route points of the surface to be sprayed in the arch coordinate system;

[0139] A posture prediction module 906 is used to generate a target nozzle posture parameter corresponding to each of the working route points on the surface to be sprayed using a spray posture prediction model, wherein the spray posture prediction model is trained based on nozzle posture samples and samples of the points to be sprayed corresponding to the nozzle posture samples;

[0140] The motion control module 908 is used to convert the target nozzle posture parameters into corresponding robot arm joint positions, and control the wet spraying robot arm to perform spraying operations on the surface to be sprayed along the target operation path according to the robot arm joint positions.

[0141] In an exemplary embodiment, the wet spraying robot control system 900 also includes: a path generation module, which is used to obtain the arch point cloud sample of the surface sample to be sprayed, the spraying point cloud sample of the surface sample to be sprayed, and the joint motion data for the surface sample to be sprayed; three-dimensionally render the process of the wet spraying robot performing spraying operation on the surface sample to be sprayed according to the arch point cloud sample, the spraying point cloud sample and the joint motion data, and generate spraying process data and spraying effect data corresponding to the surface sample to be sprayed; and filter the spraying path that meets the preset conditions from the spraying process data according to the spraying effect data.

[0142] In an exemplary embodiment, the path generation module is further used to: send the spraying process data and the spraying effect data to the client for display; and determine the spraying path whose spraying effect data meets preset conditions in response to the client's selection operation.

[0143] In an exemplary embodiment, the wet spraying robot control system 900 also includes: a model training module, which is used to determine the corresponding nozzle posture samples according to the joint motion data, and determine the point samples to be sprayed corresponding to the nozzle posture samples from the spraying path according to the joint motion data; using the point samples to be sprayed as training data, and inputting the nozzle posture samples corresponding to the point samples to be sprayed as training labels into the initial prediction model, and the initial prediction model includes multiple decision trees; generating posture prediction results corresponding to the point samples to be sprayed through each decision tree in the initial prediction model; determining the target prediction result from the posture prediction results according to the voting results of the posture prediction results generated by each decision tree through the initial prediction model; when the loss value of the target prediction result and the nozzle posture sample meets the preset training threshold, the initial prediction model is used as the injection posture prediction model.

[0144] In an exemplary embodiment, the wet spraying robot control system 900 also includes: a leveling and positioning module, which is used to obtain the current inclinometer parameters of the wet spraying robot; calibrate the wet spraying robot according to the inclinometer parameters until the wet spraying robot is in a leveling state; in the working environment where the wet spraying robot is in the leveling state, scan and obtain the three-dimensional position information of multiple preset arch frame points; based on the three-dimensional position information of each preset arch frame point, locate and obtain the three-dimensional point cloud position of the current wet spraying robot in the arch frame coordinate system.

[0145] In an exemplary embodiment, the wet spraying robot control system 900 also includes: a distance warning module, which is used to obtain the real-time joint positions of different parts in the wet spraying robot; when the real-time joint positions of any two parts are less than a preset distance threshold, or the distance between the real-time joint position of any part and the surface to be sprayed is less than the preset distance threshold, a distance alarm information corresponding to the wet spraying robot is generated, and the movement speed of the wet spraying robot is controlled to decrease.

[0146] Each module in the wet spraying robot control system 900 can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0147] Those skilled in the art will understand that the structures shown in the drawings of the specification are merely block diagrams of partial structures related to the scheme of the present application, and do not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the drawings, or combine certain components, or have a different arrangement of components.

[0148] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0149] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0150] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0151] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0152] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0153] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A wet spraying robot arm control method, characterized in that: The method comprises: Obtain the three-dimensional arch frame position of the arch frame in the surface to be sprayed; According to the three-dimensional arch position and the arch point cloud sample, a target operation path matching the to-be-sprayed surface is determined from the shotcrete path corresponding to the arch point cloud sample, wherein the target operation path includes a plurality of ordered operation route points of the to-be-sprayed surface in the arch coordinate system; A spray posture prediction model is used to generate target nozzle posture parameters corresponding to each working route point of the surface to be sprayed, wherein the spray posture prediction model is trained based on nozzle posture samples and samples of the points to be sprayed corresponding to the nozzle posture samples; The target nozzle posture parameters are converted into corresponding robot arm joint positions, and the wet spraying robot arm is controlled according to the robot arm joint positions to perform spraying operations on the surface to be sprayed along the target operation path.

2. The method according to claim 1, characterized in that The generation method of the shotcrete path includes: Acquire an arch point cloud sample of a surface sample to be sprayed, a shotcrete point cloud sample of the surface sample to be sprayed, and joint motion data for the surface sample to be sprayed; Perform three-dimensional rendering of the process of the wet spraying mechanical arm performing the spraying operation on the sample of the surface to be sprayed according to the arch point cloud sample, the spraying point cloud sample and the joint motion data, and generate spraying process data and spraying effect data corresponding to the sample of the surface to be sprayed; The spraying path that meets the preset conditions is obtained by screening the spraying process data according to the spraying effect data.

3. The method according to claim 2, characterized in that The step of selecting a spraying path that meets preset conditions from the spraying process data according to the spraying effect data includes: Sending the shotcrete process data and the shotcrete effect data to a client for display; In response to the selection operation of the client, a spraying path in which the spraying effect data satisfies the preset condition is determined.

4. The method according to claim 2, characterized in that: The training method of the injection posture prediction model includes: Determine the corresponding nozzle posture sample according to the joint motion data, and determine the to-be-sprayed point position sample corresponding to the nozzle posture sample from the spraying path according to the joint motion data; Using the samples of the points to be sprayed as training data, and inputting the nozzle posture samples corresponding to the samples of the points to be sprayed as training labels into an initial prediction model, wherein the initial prediction model includes a plurality of decision trees; Generate a posture prediction result corresponding to the to-be-sprayed point sample through each decision tree in the initial prediction model; Determining a target prediction result from the posture prediction results according to the voting results of the posture prediction results generated by each decision tree by the initial prediction model; When the loss value between the target prediction result and the nozzle posture sample meets a preset training threshold, the initial prediction model is used as the injection posture prediction model.

5. The method according to claim 1, characterized in that: Before obtaining the three-dimensional arch frame position of the arch frame in the surface to be sprayed, the method further includes: Obtaining current inclinometer parameters of the wet spraying robotic arm; Calibrating the wet spraying mechanical arm according to the inclinometer parameters until the wet spraying mechanical arm is in a leveling state; In the working environment where the wet spraying robot arm in the leveling state is located, the three-dimensional position information of multiple preset arch points is scanned; According to the three-dimensional position information of each preset arch point, the three-dimensional point cloud position of the current wet spraying mechanical arm in the arch coordinate system is located.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining real-time joint positions of different parts of the wet spraying robot arm; When the real-time joint positions of any two parts are less than a preset distance threshold, or the distance between the real-time joint position of any part and the surface to be sprayed is less than the preset distance threshold, a distance alarm message corresponding to the wet spraying robot arm is generated, and the movement speed of the wet spraying robot arm is controlled to decrease.

7. A wet spraying robot arm control system, characterized in that: The system comprises: An arch positioning module is used to obtain the three-dimensional arch position of the arch in the surface to be sprayed; A path determination module is used to determine a target operation path matching the surface to be sprayed from the spraying path corresponding to the arch point cloud sample according to the three-dimensional arch position and the arch point cloud sample, wherein the target operation path includes a plurality of ordered operation route points of the surface to be sprayed in the arch coordinate system; A posture prediction module, used to generate target nozzle posture parameters corresponding to each working route point of the to-be-sprayed surface by using a spray posture prediction model, wherein the spray posture prediction model is obtained by training based on nozzle posture samples and to-be-sprayed point samples corresponding to the nozzle posture samples; The motion control module is used to convert the target nozzle posture parameters into corresponding robot arm joint positions, and control the wet spraying robot arm to perform spraying operations on the surface to be sprayed along the target operation path according to the robot arm joint positions.

8. A wet spraying trolley, comprising a wet spraying mechanical arm, characterized in that: The wet spraying trolley also includes: A three-dimensional sensing device is used to obtain the three-dimensional arch frame position of the arch frame in the surface to be sprayed; A path planning control device is used to determine a target operation path matching the surface to be sprayed from the spraying path corresponding to the arch point cloud sample according to the three-dimensional arch position and the arch point cloud sample, wherein the target operation path includes a plurality of ordered operation route points of the surface to be sprayed in the arch coordinate system; An injection posture prediction module is used to generate a target nozzle posture parameter corresponding to each of the working route points on the surface to be sprayed using an injection posture prediction model, wherein the injection posture prediction model is obtained by training based on nozzle posture samples and samples of the points to be sprayed corresponding to the nozzle posture samples; A nozzle position and direction control device, used to convert the target nozzle posture parameters into corresponding robot arm joint positions; A robot arm joint position control device is used to control the wet spraying robot arm to perform spraying operation on the surface to be sprayed along the target operation path according to the robot arm joint position.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the wet spraying robot arm control method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the wet spraying robot arm control method described in any one of claims 1 to 6 is implemented.

Images