Robot machining method, device and system for curved-surface workpiece and storage medium

Abstract

The invention relates to the technical field of industrial robots, and discloses a robot machining method, device and system for a curved-surface workpiece and a storage medium. The method comprises the steps that positioning targets are arranged at the tail end of a robot and a machining platform respectively, and a first conversion matrix between a binocular camera coordinate system and a robot base coordinate system and a second conversion matrix between a laser three-dimensional scanner coordinate system and the binocular camera coordinate system are obtained; on the basis of the first conversion matrix and the second conversion matrix, point cloud information of the to-be-machined surface of the to-be-machined workpiece in a robot-based coordinate system is obtained; and the to-be-machined surface is machined through the robot based on the point cloud information of the robot-based coordinate system. According to the scheme of the embodiment, the position information collected by the binocular camera and the laser three-dimensional scanner can be unified into the robot base coordinate system through target point registration, calibration of the workpiece coordinate system of the workpiece with the free-form surface can be achieved, and high-precision machining of the workpiece with the free-form surface can be achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial robots, and particularly relates to a robot machining method, device, system and storage medium for curved workpieces. BACKGROUND

[0002] With the rapid development of robot technology, its application scenarios are more and more extensive, and the working conditions are more and more complex. Especially in the face of free-form surface machining, the requirements for machining efficiency and machining quality are extremely high.

[0003] At present, the machining of workpieces by industrial robots can meet the requirements for machining efficiency and machining quality, and the core of robot machining is the planning of machining trajectories. Usually, when solving robot machining trajectories, the trajectory solving needs to rely on the design model of the machining object, but for a free-form surface with small rigidity, there are often some differences between the actual shape and the design model, resulting in that the original design model cannot generate correct machining trajectories. In addition, when facing the machining of non-standard parts that cannot obtain the design model, the difficulty of machining trajectory planning is further increased. Therefore, it is difficult to meet the high-precision machining requirements of free-form surface workpieces. SUMMARY

[0004] The present application provides a robot machining method, device, system and storage medium for curved workpieces, which can realize high-precision machining of free-form surface workpieces.

[0005] According to an aspect of the present application, a robot machining method for curved workpieces is provided, comprising:

[0006] A conversion matrix acquisition module is configured to acquire a first conversion matrix between a binocular camera coordinate system and a robot base coordinate system and a second conversion matrix between a laser three-dimensional scanner coordinate system and the binocular camera coordinate system by setting positioning targets on the robot end and the machining platform respectively;

[0007] Based on the first conversion matrix and the second conversion matrix, point cloud information of a to-be-machined surface of a to-be-machined workpiece on the machining platform in the robot base coordinate system is acquired;

[0008] The robot performs machining on the to-be-machined surface based on the point cloud information of the robot base coordinate system.

[0009] According to another aspect of the present application, a robot machining device for curved workpieces is provided, comprising:

[0010] A conversion matrix acquisition module is configured to acquire a first conversion matrix between a binocular camera coordinate system and a robot base coordinate system and a second conversion matrix between a laser three-dimensional scanner coordinate system and the binocular camera coordinate system by setting positioning targets on the robot end and the machining platform respectively;

[0011] a point cloud information obtaining module, configured to obtain point cloud information of a to-be-processed surface of a to-be-processed workpiece on the processing platform in the robot base coordinate system based on the first conversion matrix and the second conversion matrix;

[0012] a surface processing module, configured to process the to-be-processed surface based on the point cloud information of the robot base coordinate system by the robot.

[0013] According to another aspect of the present application, a robot processing system for a curved workpiece is provided, comprising:

[0014] a laser three-dimensional scanner in communication connection with the controller, configured to collect three-dimensional position information of a positioning target on the processing platform in the laser three-dimensional scanner coordinate system, and send the three-dimensional position information of the positioning target on the processing platform in the laser three-dimensional scanner coordinate system to the controller, and collect point cloud information of a to-be-processed surface of a to-be-processed workpiece on the processing platform in the laser three-dimensional scanner coordinate system, and send the point cloud information of the to-be-processed surface in the laser three-dimensional scanner coordinate system to the controller;

[0015] a binocular camera in communication connection with the controller, configured to collect three-dimensional position information of a positioning target on the robot end in the binocular camera coordinate system, and send the three-dimensional position information of the positioning target on the robot end in the binocular camera coordinate system to the controller;

[0016] the controller in communication connection with the robot, configured to execute the robot processing method for a curved workpiece according to any one of the embodiments of the present application, and generate a control instruction and send the control instruction to the robot;

[0017] the robot, configured to move and process the to-be-processed surface according to the control instruction.

[0018] According to another aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium stores a computer program, the computer program is used to make a processor execute to realize the robot processing method for a curved workpiece according to any one of the embodiments of the present application.

[0019] The technical scheme of the embodiment of the present application is characterized in that: the positioning targets are arranged on the robot end and the machining platform respectively, the first conversion matrix between the binocular camera coordinate system and the robot base coordinate system and the second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system are obtained, the point cloud information of the to-be-machined surface of the to-be-machined workpiece on the machining platform in the robot base coordinate system is obtained based on the first conversion matrix and the second conversion matrix, the robot processes the to-be-machined surface based on the point cloud information of the robot base coordinate system, the position information collected by the binocular camera and the laser three-dimensional scanner is unified to the robot base coordinate system through target point registration, the calibration of the workpiece coordinate system of the workpiece with a free curved surface can be realized, and thus the high-precision machining of the workpiece with a free curved surface can be realized.

[0020] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a flow chart of a robot machining method for a curved surface workpiece according to the first embodiment of the present application;

[0023] Figure 2 is a coordinate system conversion schematic diagram according to the first embodiment of the present application;

[0024] Figure 3 is a structural schematic diagram of a robot machining device for a curved surface workpiece according to the second embodiment of the present application;

[0025] Figure 4 is a structural schematic diagram of a robot machining system for a curved surface workpiece according to the third embodiment of the present application;

[0026] Figure 5 is a structural schematic diagram of a robot end according to the third embodiment of the present application;

[0027] Figure 6 is a structural schematic diagram of another robot machining system for a curved surface workpiece according to the third embodiment of the present application. DETAILED DESCRIPTION

[0028] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort should belong to the protection scope of the present application.

[0029] It should be noted that the terms "first", "second", "target" and the like in the description, claims, and drawings of the present application are intended to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in other sequences than those illustrated or described herein. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0030] Embodiment one

[0031] Figure 1 A flowchart of a robot machining method for a curved workpiece is provided for the first embodiment of the present application. The present embodiment can be applied to the case where an industrial robot is used to machine a workpiece with a free-form surface. The method can be executed by a robot machining device for a curved workpiece, which can be implemented in the form of hardware and / or software. The method can be applied to the controller 32 of the robot machining system 30 for a curved workpiece provided in the third embodiment of the present application. As shown in the figure, the method comprises: Figure 1

[0032] S110, by setting positioning targets on the robot end and the machining platform respectively, obtaining a first conversion matrix between the binocular camera coordinate system and the robot base coordinate system, and a second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system.

[0033] In the present embodiment, the robot machining system 30 for a curved workpiece can be composed of a laser three-dimensional scanner 31, a binocular camera 33, a robot 34, and a controller 32. The robot 34 can be an industrial robot, and the type of the industrial robot can not be specifically limited in the present embodiment.

[0034] ​Before the workpiece is processed, the workpiece to be processed can be first fixed on the processing platform, and positioning targets are pasted on the end of the robot 34 and the processing platform respectively, the positioning targets are provided with irregular target points for providing position information of the end of the robot 34 and the workpiece to be processed, and the binocular camera 33 and the laser three-dimensional scanner 31 are erected near the processing platform. Then, the three-dimensional position information (three-dimensional coordinates) of the positioning target on the end of the robot 34 in the binocular camera coordinate system can be measured based on the binocular camera 33, the three-dimensional position information of the positioning target in the robot base coordinate system can be obtained based on the robot 34, and the first conversion matrix between the binocular camera coordinate system and the robot base coordinate system can be calculated based on the three-dimensional position information of each target point in the two coordinate systems.

[0035] Similarly, the three-dimensional position information of each target point of the positioning target on the processing platform in the laser three-dimensional scanner coordinate system and the binocular camera coordinate system can be measured based on the binocular camera 33 and the laser three-dimensional scanner 31 respectively, and the second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system can be calculated based on the three-dimensional position information of each target point in the two coordinate systems.

[0036] Optionally, the first conversion matrix between the binocular camera coordinate system and the robot base coordinate system and the second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system can be obtained by respectively setting the positioning targets on the end of the robot 34 and the processing platform.

[0037] The robot 34 is controlled to move along the set trajectory, and the three-dimensional position information of the positioning target on the end of the robot 34 in the binocular camera coordinate system is collected during the movement;

[0038] The first conversion matrix between the binocular camera coordinate system and the robot base coordinate system is obtained according to the three-dimensional position information of the binocular camera coordinate system and the set trajectory;

[0039] The second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system is obtained according to the three-dimensional position information of the positioning target on the processing platform in the laser three-dimensional scanner coordinate system and the binocular camera coordinate system.

[0040] The set trajectory can be a set of coordinate points in the robot base coordinate system. In this embodiment, when the first conversion matrix between the binocular camera coordinate system and the robot base coordinate system is determined, the robot 34 can be controlled to move along the set trajectory, and the positioning target can be measured in real time by the binocular camera 33 during the movement to obtain the three-dimensional position information of the positioning target in the binocular camera coordinate system. At the same time, based on the set trajectory, the three-dimensional position information of the positioning target in the robot base coordinate system can be determined. Thus, based on the three-dimensional position information of the positioning target in the two coordinate systems, the first conversion matrix can be calculated.

[0041] For example, assuming that the first conversion matrix from the binocular camera coordinate system to the robot base coordinate system is The coordinate P in the binocular camera coordinate system Cam can be converted to the coordinate P in the robot base coordinate system by the formula . Rob When the three-dimensional position information of the same position point in the two coordinate systems is obtained, the first conversion matrix can be solved based on the formula.

[0042] Secondly, assuming that the second conversion matrix from the laser three-dimensional scanner coordinate system to the binocular camera coordinate system is The coordinate P in the laser three-dimensional scanner coordinate system San can be converted to the coordinate P in the binocular camera coordinate system by the formula . Cam Similarly, based on the formula, the second conversion matrix can be solved according to the three-dimensional position information of the same position point in the laser three-dimensional scanner coordinate system and the binocular camera coordinate system.

[0043] S120, based on the first conversion matrix and the second conversion matrix, obtaining point cloud information of a to-be-processed surface of a to-be-processed workpiece on the processing platform in the robot base coordinate system.

[0044] The to-be-processed surface can be a free-form surface. The type of the to-be-processed surface in this embodiment can not be specifically limited.

[0045] Specifically, after the first conversion matrix and the second conversion matrix are determined, the three-dimensional position information of each position point on the to-be-processed surface in the laser three-dimensional scanner coordinate system can be converted to the three-dimensional position information in the robot base coordinate system based on the first conversion matrix and the second conversion matrix, so as to form the point cloud information. The point cloud information can be a set of multiple three-dimensional position information.

[0046] In a specific example, the coordinate system conversion can be as follows Figure 2As shown, based on the corresponding conversion matrix, the mutual conversion of coordinates between the laser three-dimensional scanner coordinate system, the binocular camera coordinate system and the robot base coordinate system can be realized.

[0047] Optionally, based on the first conversion matrix and the second conversion matrix, the point cloud information of the to-be-processed surface of the to-be-processed workpiece on the processing platform in the robot base coordinate system can comprise:

[0048] Obtaining the point cloud information of the to-be-processed surface of the to-be-processed workpiece on the processing platform in the laser three-dimensional scanner coordinate system;

[0049] According to the point cloud information of the to-be-processed surface in the laser three-dimensional scanner coordinate system and the first conversion matrix and the second conversion matrix, the point cloud information of the to-be-processed surface in the robot base coordinate system is obtained.

[0050] Specifically, the laser three-dimensional scanner 31 can be used to scan the to-be-processed workpiece fixed on the processing platform to obtain the point cloud information of the to-be-processed surface in the laser three-dimensional scanner coordinate system, and the point cloud information in the laser three-dimensional scanner coordinate system can be sent to the controller 32. Then, the controller 32 can use the formula Convert the point cloud information to the point cloud information in the robot base coordinate system.

[0051] S130, the robot processes the to-be-processed surface based on the point cloud information in the robot base coordinate system.

[0052] Specifically, after determining the point cloud information of the to-be-processed surface in the robot base coordinate system, the controller 32 can combine the existing process parameters, such as the technical parameters of the robot 34, the current position information of the processing end, the parameter information of the to-be-processed workpiece, etc., to plan the processing trajectory, generate the control instruction of the robot 34 based on the processing trajectory, and send the control instruction to the robot 34. The robot 34 can move and process the to-be-processed surface according to the control instruction. It should be noted that during the entire processing process, the controller 32 can collect the point cloud information of the to-be-processed surface in real time, and determine whether the preset processing target (such as the set removal amount, the set surface processing quality, etc.) is met. When it is determined that the processing target is not reached, the robot 34 can be controlled to process the workpiece for multiple times, and the control instruction can be adjusted in real time.

[0053] The technical solution of the embodiment of the present invention is to obtain a first conversion matrix between the binocular camera coordinate system and the robot base coordinate system, and a second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system by respectively setting positioning targets on the end of the robot 34 and the processing platform; based on the first conversion matrix and the second conversion matrix, the point cloud information of the to-be-processed surface of the workpiece to be processed on the processing platform in the robot base coordinate system is obtained; the to-be-processed surface is processed by the robot 34 based on the point cloud information of the robot base coordinate system; by using target point alignment, the position information collected by the binocular camera 33 and the laser three-dimensional scanner 31 can be unified into the robot base coordinate system, and the workpiece coordinate system of the workpiece with a free-form surface can be calibrated, thereby achieving high-precision processing of the free-form surface workpiece.

[0054] In an optional implementation of this embodiment, processing the surface to be processed by the robot 34 based on the point cloud information of the robot base coordinate system may include:

[0055] Generate a machining motion instruction based on the current point cloud information of the robot base coordinate system, and control the robot 34 to machine the surface to be machined according to the machining motion instruction;

[0056] After completing the current processing, obtaining updated point cloud information of the processed surface in the robot base coordinate system;

[0057] According to the current point cloud information and the updated point cloud information, it is determined whether a preset processing completion detection condition is met. If so, it is determined that the processing of the surface to be processed is completed.

[0058] Among them, the preset processing completion detection conditions can be pre-set condition information that needs to be met for the processing of the surface to be processed to be completed. For example, the total removal amount can reach the set value, or the quality of the surface to be processed after processing (for example, flatness, etc.) meets the set requirements.

[0059] In this embodiment, after the previous round of workpiece processing, if it is determined that the preset processing completion detection conditions have not yet been met, the controller 32 can generate processing motion instructions for the current round based on the current point cloud information of the robot base coordinate system and send the processing motion instructions to the robot 34. The robot 34 can then perform the current round of processing on the surface to be processed according to the processing motion instructions. After the current processing is completed, the binocular camera 33 and the laser 3D scanner 31 can obtain updated point cloud information of the processed surface in the robot base coordinate system. Furthermore, based on the current point cloud information and the updated point cloud information, if it is determined that the preset processing completion detection conditions have been met, it can be determined that the processing of the surface to be processed is complete.

[0060] Optionally, after determining whether the preset machining completion detection condition is satisfied according to the current point cloud information and the updated point cloud information, the method can further include:

[0061] If not, the machining motion instruction is generated again based on the updated point cloud information, and the robot 34 is controlled to machine the surface to be machined again according to the machining motion instruction until it is determined that the preset machining completion detection condition is satisfied according to the current point cloud information after machining and the point cloud information after the previous machining.

[0062] In another case, after the current round of machining, if it is determined that the preset machining completion detection condition is still not satisfied, the robot 34 can be controlled to continue the next round of machining on the surface to be machined. Specifically, the controller 32 can generate a new machining motion instruction based on the updated point cloud information obtained after the current round of machining, and control the robot 34 to machine the surface to be machined according to the machining motion instruction. After completing the next round of machining, if it is determined that the preset machining completion detection condition is satisfied according to the current point cloud information after machining and the point cloud information after the previous machining, the machining of the surface to be machined can be ended. If it is detected that the preset machining completion detection condition is still not satisfied, the above steps can be repeated to continue the next round of machining until it is detected that the preset machining completion detection condition is satisfied.

[0063] Optionally, determining whether the preset machining completion detection condition is satisfied according to the current point cloud information and the updated point cloud information can include:

[0064] The current machining removal amount is obtained according to the current point cloud information and the updated point cloud information, and the cumulative machining removal amount is calculated according to the current machining removal amount.

[0065] The difference between the target machining removal amount and the cumulative machining removal amount is calculated, and it is determined whether the difference is less than or equal to a preset threshold. If it is determined that the difference is less than or equal to the preset threshold, it is determined that the preset machining completion detection condition is satisfied, and if it is determined that the difference is greater than the preset threshold, it is determined that the preset machining completion detection condition is not satisfied.

[0066] The target machining removal amount can be a preset expected distance of removing the surface to be machined. In this embodiment, the normal distance between the current point cloud information and the updated point cloud information can be calculated as the machining removal amount. For example, for a position point on the surface to be machined, the corresponding current three-dimensional coordinates can be determined according to the current point cloud information, and the corresponding updated three-dimensional coordinates can be determined according to the updated point cloud information, and then the normal distance between the current three-dimensional coordinates and the updated three-dimensional coordinates can be calculated to obtain the machining removal amount corresponding to the position point.

[0067] In one specific example, the preset machining completion detection condition can be that a difference between the total machining removal amount of the surface to be machined and the target machining removal amount is less than or equal to a preset threshold. Specifically, after machining of the workpiece is completed in each round, the machining removal amount of each round can be obtained according to the point cloud information before machining and the point cloud information after machining; then, the machining removal amount of the current round can be added to the machining removal amounts of the previous rounds, and the sum is taken as the cumulative machining removal amount. Further, the difference between the target machining removal amount and the cumulative machining removal amount can be calculated, and it is determined whether the difference is less than or equal to the preset threshold. If yes, it is considered that the preset machining completion detection condition is met, and if no, it is considered that the preset machining completion detection condition is not met.

[0068] It should be noted that different target machining removal amounts can be set for different position points or different regions on the surface to be machined. Thus, the cumulative machining removal amount corresponding to each position point can be counted and detected by the difference from the corresponding target machining removal amount until each position point meets the preset machining completion detection condition, and it is determined that the machining of the workpiece is completed.

[0069] The above setting has the advantages of improving the flexibility of free-form surface machining and expanding the application range of free-form surface machining.

[0070] Optionally, obtaining the current machining removal amount according to the current point cloud information and the updated point cloud information can include:

[0071] fitting a current three-dimensional model of the workpiece to be machined based on the current point cloud information;

[0072] calculating the distance between the updated point cloud information and the surface of the current three-dimensional model to obtain the current machining removal amount.

[0073] In one specific example, the point cloud information before machining can be fitted into a three-dimensional model of the surface to be machined of the workpiece to be machined, such as a CAD model, and the distance between the updated point cloud information after machining and the surface of the three-dimensional model can be calculated to obtain the removal amount distribution of this machining, i.e., the current machining removal amount.

[0074] In an optional implementation of the embodiment, after the workpiece processing of the current round is completed, the current processing removal amount can be obtained according to the current point cloud information and the updated point cloud information, and it can be judged whether the current processing removal amount is equal to the preset removal amount, if not, it can be determined that the preset processing completion detection condition is not met; further, the preset removal amount can be subtracted by the current processing removal amount, and the difference value can be taken as a new preset removal amount; then, the workpiece processing of the next round can be carried out, and it can be judged whether the processing removal amount of the next round is equal to the new preset removal amount. Repeat the above steps until the processing removal amount of a certain round is equal to the corresponding preset removal amount, it can be determined that the processing is completed.

[0075] The technical scheme of the embodiment of the application, by using the laser three-dimensional scanner 31 to express the workpiece coordinate system, relative to the existing calibration method, does not depend on the reference features on the surface of the workpiece, and can realize the calibration of the free-form surface workpiece; moreover, by using the laser three-dimensional scanner 31 to obtain the real-time geometric appearance of the workpiece to be processed under the robot base coordinate system, with the aid of the appearance, not only the geometric features and position information of the workpiece can be obtained, but also the processing quality can be evaluated after the processing is completed; secondly, by using the laser three-dimensional scanner 31 to obtain the point cloud information of the workpiece, the processing track can be directly generated according to the workpiece point cloud, without the CAD file of the workpiece and without additional coordinate system conversion.

[0076] Embodiment two

[0077] Figure 3 A structural schematic diagram of a robot processing device for a curved surface workpiece provided by the embodiment two of the application. As shown in the figure, Figure 3 The device comprises a conversion matrix acquisition module 210, a point cloud information acquisition module 220 and a surface processing module 230; wherein,

[0078] The conversion matrix acquisition module 210 is used for acquiring the first conversion matrix between the binocular camera coordinate system and the robot base coordinate system and the second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system by setting positioning targets on the robot 34 end and the processing platform respectively;

[0079] The point cloud information acquisition module 220 is used for acquiring the point cloud information of the to-be-processed surface of the workpiece to be processed on the processing platform in the robot base coordinate system based on the first conversion matrix and the second conversion matrix;

[0080] The surface processing module 230 is used for processing the to-be-processed surface based on the point cloud information of the robot base coordinate system by the robot 34.

[0081] The technical scheme of the embodiment of the application comprises the following steps: positioning targets are arranged at the end of the robot 34 and the machining platform respectively, a first conversion matrix between the binocular camera coordinate system and the robot base coordinate system is obtained, and a second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system is obtained; based on the first conversion matrix and the second conversion matrix, point cloud information of a to-be-machined surface of a to-be-machined workpiece on the machining platform in the robot base coordinate system is obtained; the robot 34 processes the to-be-machined surface based on the point cloud information in the robot base coordinate system; by using target point registration, the position information collected by the binocular camera 33 and the laser three-dimensional scanner 31 can be unified into the robot base coordinate system, the calibration of the workpiece coordinate system of the workpiece with a free-form surface can be realized, and therefore high-precision machining of the workpiece with a free-form surface can be realized.

[0082] Optionally, the surface machining module 230 is specifically used for generating machining motion instructions based on the current point cloud information in the robot base coordinate system, and controlling the robot 34 to process the to-be-machined surface according to the machining motion instructions.

[0083] After the current machining is completed, updated point cloud information of the machined to-be-machined surface in the robot base coordinate system is obtained.

[0084] According to the current point cloud information and the updated point cloud information, it is determined whether a preset machining completion detection condition is met, and if so, it is determined that the machining of the to-be-machined surface is completed.

[0085] Optionally, the surface machining module 230 is further used for if not, generating machining motion instructions again based on the updated point cloud information, and controlling the robot 34 to process the to-be-machined surface again according to the machining motion instructions, until it is determined that the preset machining completion detection condition is met according to the current point cloud information after the current machining and the point cloud information after the previous machining.

[0086] Optionally, the surface machining module 230 is specifically used for obtaining a current machining removal amount according to the current point cloud information and the updated point cloud information, and calculating a cumulative machining removal amount according to the current machining removal amount.

[0087] A difference between a target machining removal amount and the cumulative machining removal amount is calculated, and it is determined whether the difference is less than or equal to a preset threshold.

[0088] If it is determined that the difference is less than or equal to the preset threshold, it is determined that the preset machining completion detection condition is met, and if it is determined that the difference is greater than the preset threshold, it is determined that the preset machining completion detection condition is not met.

[0089] Optionally, the surface machining module 230 is specifically used for fitting a current three-dimensional model of the to-be-machined workpiece based on the current point cloud information.

[0090] Calculate the distance between the updated point cloud information and the current three-dimensional model surface to obtain the current machining removal amount.

[0091] Optionally, the conversion matrix acquisition module 210 is specifically configured to control the robot to move along the set trajectory, and acquire the three-dimensional position information of the positioning target on the robot end in the binocular camera coordinate system during the movement.

[0092] According to the three-dimensional position information of the binocular camera coordinate system and the set trajectory, a first conversion matrix between the binocular camera coordinate system and the robot base coordinate system is acquired.

[0093] According to the three-dimensional position information of the positioning target on the machining platform in the laser three-dimensional scanner coordinate system and the binocular camera coordinate system, a second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system is acquired.

[0094] Optionally, the point cloud information acquisition module 220 is specifically configured to acquire the point cloud information of the to-be-machined surface of the to-be-machined workpiece on the machining platform in the laser three-dimensional scanner coordinate system.

[0095] According to the point cloud information of the to-be-machined surface in the laser three-dimensional scanner coordinate system, and the first conversion matrix and the second conversion matrix, the point cloud information of the to-be-machined surface in the robot base coordinate system is acquired.

[0096] The robot machining device for curved surface workpieces provided by the embodiment of the application can execute the robot machining method for curved surface workpieces provided by any embodiment of the application, and has the corresponding function modules and beneficial effects of the execution method.

[0097] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0098] Embodiment three

[0099] Figure 4 A structural schematic diagram of a robot machining system for curved surface workpieces provided by embodiment three of the application. The robot machining system for curved surface workpieces 30 can include:

[0100] The laser 3D scanner 31 is in communication with the controller 32 and is used to collect 3D position information of a positioning target on the processing platform in the laser 3D scanner coordinate system, and send the 3D position information of the positioning target on the processing platform in the laser 3D scanner coordinate system to the controller 32, and collect point cloud information of a surface to be processed of a workpiece to be processed on the processing platform in the laser 3D scanner coordinate system, and send the point cloud information of the surface to be processed in the laser 3D scanner coordinate system to the controller 32;

[0101] The binocular camera 33 is in communication with the controller 32 and is used to collect the three-dimensional position information of the positioning target on the end of the robot 34 in the binocular camera coordinate system, and send the three-dimensional position information of the positioning target on the end of the robot 34 in the binocular camera coordinate system to the controller 32; for example, the structure of the end of the robot 34 can be as follows Figure 5 shown.

[0102] The controller 32 is in communication with the robot 34 and is configured to execute the robot processing method for a curved workpiece according to any embodiment of the present invention and to generate control instructions and send them to the robot 34 ;

[0103] The robot 34 is used to move according to the control instructions and process the surface to be processed.

[0104] The controller 32 may include a processor and a memory connected to the processor, such as a read-only memory (ROM) or a random access memory (RAM). The memory stores a computer program executable by the processor. The processor may perform various appropriate actions and processes based on the computer program stored in the ROM or loaded from a storage unit into the RAM. The RAM may also store various programs and data required for the operation of the controller 32.

[0105] The processor can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processors include, but are not limited to, central processing units, graphics processing units, various specialized artificial intelligence computing chips, various processors that run machine learning model algorithms, digital signal processors, and any suitable processor, microcontroller, etc. The processor executes the various methods and processes described above, such as the robotic machining method for curved workpieces.

[0106] In a specific example, the structure of the robot processing system 30 for curved workpieces can be as follows: Figure 6As shown. Among them, the laser three-dimensional scanner 31 can be deployed directly above the machining platform, the binocular camera 33 can be deployed above the side of the machining platform, and the robot 34 can be deployed on one side of the machining platform, and a positioning target can be preset on the machining platform, and the laser three-dimensional scanner 31, the binocular camera 33 and the robot 34 can be in wired or wireless communication connection with the controller 32.

[0107] In some embodiments, the robot machining method of the curved workpiece can be implemented as a computer program, which is tangibly contained in a computer readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program can be loaded and / or installed on the controller 32 via the ROM and / or the communication unit. When the computer program is loaded into the RAM and executed by the processor, one or more steps of the robot machining method of the curved workpiece described above can be performed. Alternatively, in other embodiments, the processor can be configured to perform the robot machining method of the curved workpiece by any other appropriate means (for example, by means of firmware).

[0108] The various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits, application specific standard products, chips, microprocessors, computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0109] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, and partially on a machine and partially on a remote machine or server.

[0110] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory or non-transitory format, a portable computer diskette, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disc read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0111] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or a combination of one or more such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network, a wide area network, a blockchain network, and the Internet.

[0112] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server is generally established by computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server.

[0113] It should be understood that various forms of flow shown above can be used, re-ordered, added to, or deleted from without departing from the spirit of the present application. For example, the steps recited in the present application can be performed in parallel, in series, or in a different order, without departing from the desired results of the technical solutions of the present application, and this is not limited herein.

[0114] The above detailed description does not constitute a limitation on the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A robot processing method for a curved workpiece, characterized in that: include: By setting positioning targets on the robot end and the processing platform respectively, the first conversion matrix between the binocular camera coordinate system and the robot base coordinate system, as well as the second conversion matrix between the laser 3D scanner coordinate system and the binocular camera coordinate system are obtained; Based on the first transformation matrix and the second transformation matrix, acquiring point cloud information of a to-be-machined surface of a workpiece to be machined on a machining platform in the robot base coordinate system; The surface to be processed is processed by the robot based on the point cloud information of the robot base coordinate system.

2. The method according to claim 1, characterized in that Processing the surface to be processed by the robot based on point cloud information of the robot base coordinate system, comprising: Generate a processing motion instruction based on the current point cloud information of the robot base coordinate system, and control the robot to process the surface to be processed according to the processing motion instruction; After completing the current processing, obtaining updated point cloud information of the processed surface in the robot base coordinate system; According to the current point cloud information and the updated point cloud information, it is determined whether a preset processing completion detection condition is met. If so, it is determined that the processing of the surface to be processed is completed.

3. The method according to claim 2, characterized in that After determining whether a preset processing completion detection condition is met based on the current point cloud information and the updated point cloud information, the method further includes: If not, the processing motion instructions are re-generated based on the updated point cloud information, and the robot is controlled to re-process the surface to be processed according to the processing motion instructions until it is detected that the preset processing completion detection conditions are met based on the current processed point cloud information and the previous processed point cloud information.

4. The method according to claim 2, characterized in that Determining whether a preset processing completion detection condition is met based on the current point cloud information and the updated point cloud information includes: Obtaining a current machining removal amount based on the current point cloud information and the updated point cloud information, and calculating a cumulative machining removal amount based on the current machining removal amount; Calculating a difference between a target machining removal amount and the cumulative machining removal amount, and determining whether the difference is less than or equal to a preset threshold; If it is determined that the difference is less than or equal to the preset threshold, it is determined that the preset processing completion detection condition is met; if it is determined that the difference is greater than the preset threshold, it is determined that the preset processing completion detection condition is not met.

5. The method according to claim 4, characterized in that Obtaining a current machining removal amount according to the current point cloud information and the updated point cloud information includes: Obtaining a current three-dimensional model of the workpiece to be processed based on the current point cloud information; The distance between the updated point cloud information and the surface of the current three-dimensional model is calculated to obtain the current machining removal amount.

6. The method according to claim 1, characterized in that By setting positioning targets on the robot end and the processing platform respectively, the first transformation matrix between the binocular camera coordinate system and the robot base coordinate system, and the second transformation matrix between the laser 3D scanner coordinate system and the binocular camera coordinate system are obtained, including: Control the robot to move along the set trajectory, and during the movement, collect the three-dimensional position information of the positioning target on the end of the robot in the binocular camera coordinate system; Obtaining a first transformation matrix between the binocular camera coordinate system and the robot base coordinate system according to the three-dimensional position information of the binocular camera coordinate system and the set trajectory; According to the three-dimensional position information of the positioning target on the processing platform in the laser three-dimensional scanner coordinate system and the binocular camera coordinate system, a second conversion matrix between the laser three-dimensional scanner coordinate system and the binocular camera coordinate system is obtained.

7. The method according to claim 1, characterized in that Acquiring point cloud information of a surface to be processed of a workpiece to be processed on a processing platform in the robot base coordinate system based on the first conversion matrix and the second conversion matrix includes: Obtaining point cloud information of the surface to be processed of the workpiece to be processed on the processing platform in the laser 3D scanner coordinate system; According to the point cloud information of the surface to be processed in the laser three-dimensional scanner coordinate system, as well as the first transformation matrix and the second transformation matrix, the point cloud information of the surface to be processed in the robot base coordinate system is acquired.

8. A robotic processing device for curved workpieces, characterized in that: include: The conversion matrix acquisition module is used to obtain the first conversion matrix between the binocular camera coordinate system and the robot base coordinate system, and the second conversion matrix between the laser 3D scanner coordinate system and the binocular camera coordinate system by setting positioning targets on the robot end and the processing platform respectively; A point cloud information acquisition module, configured to acquire point cloud information of a surface to be processed of a workpiece to be processed on a processing platform in the robot base coordinate system based on the first conversion matrix and the second conversion matrix; A surface processing module is used to process the surface to be processed by the robot based on the point cloud information of the robot base coordinate system.

9. A robotic machining system for curved workpieces, characterized in that: include: The laser 3D scanner is communicatively connected to the controller, and is used to collect 3D position information of a positioning target on the processing platform in a laser 3D scanner coordinate system, and send the 3D position information of the positioning target on the processing platform in the laser 3D scanner coordinate system to the controller, and collect point cloud information of a to-be-processed surface of a workpiece to be processed on the processing platform in the laser 3D scanner coordinate system, and send the point cloud information of the to-be-processed surface in the laser 3D scanner coordinate system to the controller; The binocular camera is communicatively connected to the controller and is used to collect three-dimensional position information of the positioning target on the end of the robot in the binocular camera coordinate system, and send the three-dimensional position information of the positioning target on the end of the robot in the binocular camera coordinate system to the controller; The controller is communicatively connected to the robot, and is used to execute the robot processing method for a curved workpiece according to any one of claims 1 to 7, and to generate control instructions and send them to the robot; The robot is used to move according to the control instructions and process the surface to be processed.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is used to enable a processor to implement the robot processing method for a curved workpiece according to any one of claims 1 to 7 when the computer program is executed.

Images