Control method and device of assembly robot

Abstract

The invention relates to a control method and device for an assembly robot. The method comprises the steps that according to visual sensing information and laser displacement sensing information of an assembly robot, multi-level self-calibration is conducted on the assembly pose, and assembly robot pose determination information is obtained; according to the multi-point microspur scanning information of the assembly robot, the part position and the part angle in the assembly robot pose determination information are positioned, and assembly robot part determination information is obtained; according to the assembly robot part determination information and the space three-dimensional information corresponding to the assembly robot, an assembly moving path is planned; according to the assembly robot part determination information and the assembly moving path, the assembly robot is controlled to move, and robot micro-force feedback control information is obtained; and according to the robot micro-force feedback control information, the assembly moving path and the assembly robot part determination information are adjusted, and assembly scene application information is determined. By adopting the method, the assembly efficiency and the assembly quality can meet preset standards.

Description

Technical Field

[0001] The present application relates to the field of automatic control technology, and in particular to a control method and device for an assembly robot. Background Art

[0002] With the continuous advancement of automation and intelligent manufacturing, assembly robots have gradually replaced traditional manual operations and become an indispensable production equipment on the assembly line. Traditional control methods mostly rely on pre-programmed trajectory planning and simple command responses. However, traditional assembly robot control methods have limitations in dealing with complex production needs and high-precision requirements, making it difficult for assembly efficiency and assembly quality to meet preset standards. Summary of the invention

[0003] Based on this, it is necessary to provide a control method, device, computer equipment, computer-readable storage medium and computer program product for an assembly robot that can ensure that the assembly efficiency and assembly quality meet preset standards in order to address the above technical problems.

[0004] In a first aspect, the present application provides a control method for an assembly robot, comprising:

[0005] Performing multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and the laser displacement sensing information of the assembly robot to obtain the assembly robot posture determination information;

[0006] Positioning the part position and part angle in the assembly robot posture determination information according to the multi-point macro scanning information of the assembly robot to obtain the assembly robot part determination information;

[0007] Planning an assembly movement path of the assembly robot according to the assembly robot part determination information and the spatial three-dimensional information corresponding to the assembly robot;

[0008] According to the assembly robot part determination information and the assembly movement path, the assembly robot is controlled to move, and the robot micro-force feedback control information is obtained;

[0009] According to the robot micro-force feedback control information, the assembly movement path and the assembly robot part determination information are adjusted to determine the assembly scene application information of the assembly robot.

[0010] In a second aspect, the present application also provides a control device for an assembly robot, comprising:

[0011] A robot self-calibration module, used to perform multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and laser displacement sensing information of the assembly robot, so as to obtain the assembly robot posture determination information;

[0012] A part posture adjustment module is used to locate the part position and part angle in the assembly robot posture determination information according to the multi-point macro scanning information of the assembly robot to obtain the assembly robot part determination information;

[0013] A moving path planning module, used to plan the assembly moving path of the assembly robot according to the part determination information of the assembly robot and the spatial three-dimensional information corresponding to the assembly robot;

[0014] A feedback information obtaining module, used to control the assembly robot to move according to the assembly robot part determination information and the assembly movement path, and obtain the robot micro-force feedback control information;

[0015] The assembly information optimization module is used to adjust the assembly movement path and the assembly robot part determination information according to the robot micro-force feedback control information, and determine the assembly scene application information of the assembly robot.

[0016] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0017] Performing multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and the laser displacement sensing information of the assembly robot to obtain the assembly robot posture determination information;

[0018] Positioning the part position and part angle in the assembly robot posture determination information according to the multi-point macro scanning information of the assembly robot to obtain the assembly robot part determination information;

[0019] Planning an assembly movement path of the assembly robot according to the assembly robot part determination information and the spatial three-dimensional information corresponding to the assembly robot;

[0020] According to the assembly robot part determination information and the assembly movement path, the assembly robot is controlled to move, and the robot micro-force feedback control information is obtained;

[0021] According to the robot micro-force feedback control information, the assembly movement path and the assembly robot part determination information are adjusted to determine the assembly scene application information of the assembly robot.

[0022] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0023] Performing multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and the laser displacement sensing information of the assembly robot to obtain the assembly robot posture determination information;

[0024] Positioning the part position and part angle in the assembly robot posture determination information according to the multi-point macro scanning information of the assembly robot to obtain the assembly robot part determination information;

[0025] Planning an assembly movement path of the assembly robot according to the assembly robot part determination information and the spatial three-dimensional information corresponding to the assembly robot;

[0026] According to the assembly robot part determination information and the assembly movement path, the assembly robot is controlled to move, and the robot micro-force feedback control information is obtained;

[0027] According to the robot micro-force feedback control information, the assembly movement path and the assembly robot part determination information are adjusted to determine the assembly scene application information of the assembly robot.

[0028] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0029] Performing multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and the laser displacement sensing information of the assembly robot to obtain the assembly robot posture determination information;

[0030] Positioning the part position and part angle in the assembly robot posture determination information according to the multi-point macro scanning information of the assembly robot to obtain the assembly robot part determination information;

[0031] Planning an assembly movement path of the assembly robot according to the assembly robot part determination information and the spatial three-dimensional information corresponding to the assembly robot;

[0032] According to the assembly robot part determination information and the assembly movement path, the assembly robot is controlled to move, and the robot micro-force feedback control information is obtained;

[0033] According to the robot micro-force feedback control information, the assembly movement path and the assembly robot part determination information are adjusted to determine the assembly scene application information of the assembly robot.

[0034] The above-mentioned control method, device, computer equipment, storage medium and computer program product of an assembly robot perform multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and laser displacement sensing information of the assembly robot to obtain the posture determination information of the assembly robot; locate the part position and part angle in the posture determination information of the assembly robot according to the multi-point macro scanning information of the assembly robot to obtain the part determination information of the assembly robot; plan the assembly movement path of the assembly robot according to the part determination information of the assembly robot and the spatial three-dimensional information corresponding to the assembly robot; control the assembly robot to move according to the part determination information of the assembly robot and the assembly movement path to obtain the robot micro-force feedback control information; adjust the assembly movement path and the part determination information of the assembly robot according to the micro-force feedback control information of the robot to determine the assembly scene application information of the assembly robot.

[0035] By integrating multi-level perception technologies such as visual sensing, laser displacement, and multi-point macro scanning, highly accurate posture self-calibration is achieved, enabling the assembly robot to accurately obtain part position and angle information, thereby ensuring that each step in the assembly process is completed within the error range of the micron level. At the same time, based on the real-time micro-force feedback control system, the assembly path and part positioning information can be dynamically adjusted, allowing the robot to adapt to small errors and environmental changes in complex assembly scenarios. This series of precise control and dynamic optimization processes has improved the stability and intelligence level of robot assembly. It can not only cope with complex production needs and high-precision requirements, and achieve assembly efficiency and assembly quality that meet preset standards, but also greatly improve assembly efficiency. It also effectively reduces rework and material loss caused by assembly deviations, thereby achieving high-quality, low-cost intelligent assembly. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A diagram of an application environment of a control method for an assembly robot in one embodiment;

[0038] Figure 2 A schematic flow chart of a control method for an assembly robot in one embodiment;

[0039] Figure 3 It is a flowchart of a method for determining assembly scenario application information in one embodiment;

[0040] Figure 4 It is a flowchart of a method for determining assembly scenario application information in another embodiment;

[0041] Figure 5 A schematic diagram of a flow chart of a method for acquiring micro-force feedback control information of a robot in one embodiment;

[0042] Figure 6 A schematic diagram of a process for calculating physical parameters of initial assembly in one embodiment;

[0043] Figure 7 A schematic diagram of a flow chart of a method for calculating physical parameters of initial assembly in another embodiment;

[0044] Figure 8 A schematic diagram of a flow chart of a method for obtaining position and posture determination information of an assembly robot in one embodiment;

[0045] Fig. 9 A schematic flow chart of a method for obtaining position and posture determination information of an assembly robot in another embodiment;

[0046] Fig.10 A structural block diagram of a control device for assembling a robot in one embodiment;

[0047] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0048] 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.

[0049] The control method of an assembly robot provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 performs multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and laser displacement sensing information obtained by the assembly robot from the terminal 102, and obtains the assembly robot posture determination information; according to the multi-point macro scanning information of the assembly robot, the part position and part angle in the assembly robot posture determination information are located to obtain the assembly robot part determination information; according to the assembly robot part determination information and the spatial three-dimensional information corresponding to the assembly robot, the assembly movement path of the assembly robot is planned; according to the assembly robot part determination information and the assembly movement path, the assembly robot is controlled to move, and the robot micro-force feedback control information is obtained; according to the robot micro-force feedback control information, the assembly movement path and the assembly robot part determination information are adjusted to determine the assembly scene application information of the assembly robot. Among them, the server 104 can be implemented with an independent server or a server cluster composed of multiple servers.

[0050] In an exemplary embodiment, Figure 2 As shown, a control method for an assembly robot is provided, and the method is applied to Figure 1 The server in the example is used to illustrate, including the following steps 202 to 210. Among them:

[0051] Step 202 , performing multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and the laser displacement sensing information of the assembly robot, and obtaining the assembly robot posture determination information.

[0052] The visual sensing information may be images or video data collected by the robot's camera device, which is used to identify and analyze the appearance features, spatial position and relative posture of the assembly object.

[0053] The laser displacement sensing information may be distance measurement data generated by a laser displacement sensor, which is used to accurately measure the relative position and shape details between the robot and the assembly object.

[0054] Among them, multi-level self-calibration can be the process of adjusting the robot's posture and position in a layer-by-layer manner to reduce operational errors.

[0055] The assembly posture can be the precise position and posture that the robot needs to maintain before assembly in order to correctly operate the assembly parts.

[0056] The position and posture determination information of the assembly robot may be accurate posture data after multi-level self-calibration, including the position and orientation of the robot in the assembly area.

[0057] Specifically, at the initial stage of the assembly process, the system obtains image data of the overall assembly area through the visual sensor of the assembly robot, identifies the assembly object and its spatial layout. Subsequently, the laser displacement sensor performs high-precision three-dimensional measurement of the details of the assembly object to obtain its surface morphology, spatial position, and relative distance between assembly components. By fusing these two types of sensor information, the system constructs a detailed posture model. In the multi-level calibration, the system will repeatedly compare and adjust the model to eliminate posture errors and correct the posture deviation of the robot body, and finally obtain the posture determination information of the assembly robot, laying a stable spatial foundation for assembly operations.

[0058] Step 204 , based on the multi-point macro scanning information of the assembly robot, locate the part position and part angle in the position determination information of the assembly robot to obtain the part determination information of the assembly robot.

[0059] The multi-point macro scanning information may be high-precision position and angle data obtained by performing multi-point scanning on the surface of the assembly part by a macro scanning device.

[0060] The assembly robot part determination information may be detailed data generated based on multi-point macro scanning and calibration information, including the precise position and posture of the part in space.

[0061] Specifically, after the assembly robot posture determination information is established, the system uses multi-point macro scanning technology to accurately locate the position and angle of the parts in the assembly posture. Macro scanning detects the microscopic structure of the part surface point by point, captures small geometric features, and feeds back the position information of each scanning point to the system for high-precision angle and position measurement. The system uses a three-dimensional feature matching algorithm to compare the scanning results with the established part features in the model to eliminate positioning errors caused by small part offsets, thereby generating assembly robot part determination information and providing specific position and posture data for subsequent path planning.

[0062] Step 206 , planning the assembly movement path of the assembly robot according to the assembly robot part determination information and the spatial three-dimensional information corresponding to the assembly robot.

[0063] The assembly movement path may be a movement route planned by the robot when performing an assembly task, and defines the movement trajectory of the robot between different assembly positions.

[0064] Specifically, after obtaining the confirmed information of the assembly robot parts, the system performs path planning based on the current posture information of the assembly robot, the spatial position of the parts, and the three-dimensional information of the overall assembly environment. The planning process designs an efficient and safe motion path by analyzing the range of motion of the robot joints, the gaps between the parts, and the obstacles that need to be avoided during the assembly process. The path planning algorithm dynamically adjusts the assembly speed and acceleration curve according to the dynamic capabilities of the robot joints and the obstacle avoidance requirements in space to ensure that each movement is smooth and natural, and can maintain accurate positioning of the parts during the assembly process, and obtain an assembly movement path including trajectory, speed, and acceleration, minimizing assembly errors caused by path deviations.

[0065] Step 208 , according to the information of the assembly robot parts and the assembly movement path, the assembly robot is controlled to move, and the robot micro-force feedback control information is obtained.

[0066] Among them, the robot micro-force feedback control information can be the contact force and force feedback data obtained by the robot during the assembly process, which is used to monitor the force balance between parts during the assembly process in real time.

[0067] Specifically, based on the information on the assembly robot parts and the assembly movement path, the system starts the movement control of the assembly robot, gradually guides it to the assembly position, and monitors the force feedback information during the assembly process in real time. During the contact and fixation phase of the parts, the system's micro-force sensors accurately detect the contact pressure, sliding friction, and strain of the parts, thereby controlling the assembly force to avoid assembly failure due to excessive or insufficient force. Through the feedback mechanism, the system can detect slight deviations in the assembly position and make adjustments to keep the robot stable during the assembly process, ensuring that parts assembly is completed safely and effectively in complex scenarios.

[0068] Step 210 , adjusting the assembly movement path and the assembly robot part determination information according to the robot micro-force feedback control information, and determining the assembly scene application information of the assembly robot.

[0069] Among them, the assembly scenario application information can be an optimization parameter set comprehensively derived based on the actual assembly situation, including adjustment information such as posture, path, part position, force feedback, etc.

[0070] Specifically, during the assembly process of the assembly robot, the system will continuously receive the robot's micro-force feedback control information to determine whether the actual assembly effect is consistent with the expected path and position. If the system detects deviations caused by abnormal force feedback or position errors, it will automatically fine-tune the path and part positioning information, and use the real-time updated path optimization algorithm to recalculate the robot's movement path, adjust the assembly force, change the assembly mode, adjust the assembly angle, etc., until the assembly force and position information reach the ideal state. Through this dynamic adjustment mechanism, the system realizes intelligent adaptation to the assembly scene, enabling the robot to always maintain high-precision assembly effects under different environments and assembly requirements, and finally generates assembly scene application information that adapts to the assembly scene.

[0071] In the above-mentioned control method for an assembly robot, the assembly posture of the assembly robot is self-calibrated at multiple levels according to the visual sensing information and laser displacement sensing information of the assembly robot to obtain the posture determination information of the assembly robot; the part position and part angle in the posture determination information of the assembly robot are located according to the multi-point macro scanning information of the assembly robot to obtain the part determination information of the assembly robot; the assembly movement path of the assembly robot is planned according to the part determination information of the assembly robot and the spatial three-dimensional information corresponding to the assembly robot; the assembly robot is controlled to move according to the part determination information of the assembly robot and the assembly movement path to obtain the micro-force feedback control information of the robot; the assembly movement path and the part determination information of the assembly robot are adjusted according to the micro-force feedback control information of the robot to determine the assembly scene application information of the assembly robot.

[0072] By integrating multi-level perception technologies such as visual sensing, laser displacement, and multi-point macro scanning, highly accurate posture self-calibration is achieved, enabling the assembly robot to accurately obtain part position and angle information, thereby ensuring that each step in the assembly process is completed within the error range of the micron level. At the same time, based on the real-time micro-force feedback control system, the assembly path and part positioning information can be dynamically adjusted, allowing the robot to adapt to small errors and environmental changes in complex assembly scenarios. This series of precise control and dynamic optimization processes has improved the stability and intelligence level of robot assembly. It can not only cope with complex production needs and high-precision requirements, and achieve assembly efficiency and assembly quality that meet preset standards, but also greatly improve assembly efficiency. It also effectively reduces rework and material loss caused by assembly deviations, thereby achieving high-quality, low-cost intelligent assembly.

[0073] In an exemplary embodiment, Figure 3 As shown, according to the robot micro-force feedback control information, the assembly movement path and the assembly robot part determination information are adjusted to determine the assembly scene application information of the assembly robot, including steps 302 to 306. Among them:

[0074] Step 302 : determining an assembly mode of the robot assembly process of the assembly robot according to the robot micro-force feedback control information.

[0075] Among them, the assembly mode of the robot assembly process can be an operation mode automatically selected by the system based on micro-force feedback data and assembly requirements during the assembly task. Different assembly modes (such as flexible mode and precision mode) correspond to different force control and motion accuracy, which are suitable for various situations in the assembly process.

[0076] Specifically, the system uses the micro-force feedback control information of the assembly robot to analyze the subtle mechanical changes in the assembly process in real time, and combines the amplitude, direction, duration and other characteristics of the force data to identify whether the assembly state is stable or abnormal. According to the fluctuation of the assembly force, the system determines the assembly difficulty and precision requirements, and automatically selects the appropriate robot assembly process assembly mode, such as flexible mode or precision mode, to cope with different assembly conditions. The flexible mode is usually used for assemblies that require a large tolerance, while the precision mode is suitable for high-precision and high-rigidity operating environments. The system determines the timing of mode switching based on the characteristics of the feedback data to ensure that the assembly robot operates in the optimal mode throughout the process.

[0077] Step 304 , fine-tune the assembly force and assembly error of the assembly robot parts according to the robot micro-force feedback control information and the assembly mode of the robot assembly process, and obtain robot assembly fine-tuning information.

[0078] Among them, the robot assembly fine-tuning information can be a set of parameters for fine-tuning the position, angle and force of parts during the assembly process. By dynamically correcting the feedback mechanical and position data, the system continuously optimizes the accuracy of the assembly operation to achieve the ideal assembly state.

[0079] Specifically, the system combines the robot's micro-force feedback control information with the robot's assembly process assembly mode. By adjusting the force output and direction of the robot's end to accurately correct the force during the assembly process for the tiny force errors and position deviations detected during the assembly process, as well as the deviations in the assembly force, the system can ensure that the parts are in firm contact without damage. At this time, the system uses closed-loop control to compare the feedback force signal with the expected value, continuously fine-tune the contact force and position offset of the robot's end, and gradually eliminate small assembly errors. At the same time, through the error evaluation algorithm, the system confirms that all assembly parameters meet the standard requirements, generates robot assembly fine-tuning information, and records the precise mechanical parameters and position of the current assembly.

[0080] Step 306 , perform multi-level precision calibration on the robot assembly fine-tuning information to obtain assembly scene application information.

[0081] Among them, multi-level precision calibration can be a process of gradually improving assembly accuracy. Through the three-stage calibration operations of coarse, medium and fine, the assembly error is gradually reduced. The initial calibration greatly corrects the position and posture, the mid-term calibration further optimizes the details, and the final fine calibration uses high-precision data to ensure that the assembly reaches extremely high accuracy.

[0082] Specifically, the system performs multi-level precision calibration on the generated robot assembly fine-tuning information, from coarse adjustment to fine adjustment in sequence, to ensure that the final assembly accuracy meets the requirements. In the initial calibration stage, the system first adjusts the posture and force with larger errors, and gradually reduces the error range. In the mid-term calibration stage, by integrating the calibration data of multiple micro-force feedbacks, the assembly parameters are further optimized to ensure that the error is within an acceptable range. In the final fine calibration stage, the system uses the feedback information of high-precision sensors to minimize the residual error, and through a multi-level data fusion algorithm, the final calibration of posture and force is achieved to obtain assembly scenario application information.

[0083] In this embodiment, by utilizing the robot's micro-force feedback control information, the system can judge the mechanical state in the assembly process in real time and dynamically select the most appropriate assembly mode. This adaptive assembly mode helps the robot to accurately control the force in complex assembly tasks, and fine-tune the force and error according to the feedback during the assembly process to generate robot assembly fine-tuning information. Finally, the assembly accuracy and stability are further optimized through multi-level precision calibration. The system ensures the precise execution of each assembly step and significantly reduces deviations and assembly defects. This adaptive adjustment mechanism based on real-time feedback greatly improves assembly efficiency and finished product quality, reduces the possibility of rework and material loss, and realizes efficient and reliable intelligent assembly.

[0084] In an exemplary embodiment, Figure 4 As shown, multi-level precision calibration is performed on the robot assembly fine-tuning information to obtain assembly scene application information, including steps 402 to 406. Among them:

[0085] Step 402 , performing reference point positioning calibration on the reference point information of the robot assembly fine-tuning information to obtain robot assembly reference point calibration information.

[0086] Among them, the reference point positioning calibration can be carried out by accurately measuring and adjusting the reference positions in the assembly area through high-precision sensing equipment to ensure that the assembly robot can accurately identify and align these key positions as the starting reference for the assembly action.

[0087] Among them, the robot assembly reference point calibration information can be the precise position and posture data obtained by the assembly robot after the reference point positioning and calibration, which is used to define the spatial coordinates of each reference point in the assembly task.

[0088] Specifically, in the first step of multi-level precision calibration, the system accurately locates and calibrates the reference point data in the robot assembly fine-tuning information. The reference point is the core reference position for all operations in the assembly task, which determines the initial posture and direction of the assembly action. The system uses high-precision displacement sensors and multi-angle imaging devices to gradually scan and identify the positions of the reference points in the assembly area to ensure that these points are strictly aligned with the preset standard coordinates. Through real-time comparison and feedback adjustment, the system enables the robot to locate the reference point within a sub-millimeter error range, thereby generating accurate robot assembly reference point calibration information, ensuring that the entire assembly process starts from a precise reference position, and providing a stable starting point for subsequent force calibration and space calibration.

[0089] Step 404 , performing contact force balance calibration on the contact force information of the robot assembly reference point calibration information to obtain the robot assembly contact force calibration information.

[0090] Among them, the contact force information can be the force data applied by the robot on the parts or contact surfaces during the assembly process, including details such as the magnitude, direction and distribution of the force.

[0091] Among them, contact force balance calibration can be a detailed adjustment of the force applied by the assembly robot based on the contact force information to ensure that the force is evenly and reasonably distributed, avoiding the impact of excessive or insufficient local force on the assembly quality.

[0092] Among them, the robot assembly contact force calibration information can be the adjustment data after the contact force balance calibration, including optimized force distribution and force application parameters, which is used to guide the mechanical control of the robot during the assembly process to ensure that each contact point in the assembly is in an ideal force balance state.

[0093] Specifically, in the second step of the multi-level precision calibration, the system performs a balanced calibration on the contact force parameters in the assembly reference point calibration information to ensure that the contact force applied by the robot during the assembly process is evenly distributed. This process uses contact force sensors to monitor the force applied by the robot when assembling parts in real time, and compares the mechanical data with the standard values ​​required for assembly, finds unbalanced areas and automatically adjusts them. The system will carefully adjust the robot's force output to form a balanced and moderate pressure on the contact surface to avoid offset, wear or damage to assembly parts caused by uneven force distribution. The calibration process generates robot assembly contact force calibration information through multiple fine-tuning until the contact force distribution meets the standard, providing a stable mechanical basis for subsequent spatial calibration.

[0094] Step 406 , performing multi-vector calibration on the three-dimensional space of the robot assembly contact force calibration information to obtain assembly scene application information.

[0095] Among them, multi-vector calibration can be a fine adjustment of the multi-directional motion trajectory and angle of the assembly robot in three-dimensional space to eliminate the remaining motion errors.

[0096] Specifically, in the third step of the multi-level precision calibration, this stage analyzes the various motion vectors of the assembly robot in three-dimensional space to make final precision fine-tuning of the assembly path and angle. Specifically, the system detects the displacement and rotation accuracy of the robot in all directions based on spatial vector analysis, and gradually optimizes the synchronization and coordination of each motion axis so that each vector conforms to the ideal spatial orientation. The calibration system will use multiple repeated tests and feedback adjustments to further optimize the robot's motion path and motion parameters so that its movements in three-dimensional space are free of any deviations and error accumulation. After this stage of multi-vector calibration, the system generates the final assembly scene application information to ensure that the robot can perform complex assembly tasks with high precision and achieve optimal assembly accuracy and stability in three-dimensional space.

[0097] In this embodiment, by positioning the reference points of the robot assembly fine-tuning information, balancing the contact force, and calibrating the three-dimensional multi-vector, the system can achieve multi-level and refined calibration during the assembly process. The reference point positioning calibration ensures that the robot is accurately aligned at key positions in space, the contact force balancing calibration makes the force distribution more uniform, thereby avoiding part damage or assembly deviation, and the three-dimensional multi-vector calibration further optimizes the robot's precision control in different directions. This complete calibration process enables assembly operations to achieve higher accuracy and stability, greatly improves assembly quality, and effectively reduces assembly problems caused by uneven force distribution or posture deviation, realizing efficient and reliable intelligent assembly applications.

[0098] In an exemplary embodiment, Figure 5 As shown, according to the information of the assembly robot parts and the assembly movement path, the assembly robot is controlled to move, and the robot micro-force feedback control information is obtained, including steps 502 to 506. Among them:

[0099] Step 502, determining the robot assembly start-up assembly mode according to the assembly robot part determination information and the assembly movement path.

[0100] Among them, the robot assembly startup assembly mode can be an initial operation mode determined according to the requirements of the assembly task, part characteristics and assembly path, and defines the operation strategy of the robot when it starts to perform the assembly task.

[0101] Specifically, the system conducts a comprehensive analysis of the assembly task requirements based on the information of the assembly robot parts and the preset assembly movement path, and determines the geometric shape, material, and spatial limitations of the parts in the assembly area. By analyzing the assembly accuracy requirements, task difficulty, and environmental conditions, the system selects the most suitable robot assembly startup assembly mode, such as flexible mode (suitable for small, fragile parts) and precision mode (for high-precision assembly). The mode selection takes into account the flexibility and stability of the robot's movement, so that it can respond to different assembly scenarios in the most appropriate way at the beginning of assembly, ensuring the smoothness and efficiency of the entire assembly process.

[0102] Step 504 , calculating initial assembly physical parameters according to the robot assembly startup assembly mode and assembly robot part determination information.

[0103] Among them, the initial assembly physical parameters can be key physical data set when the assembly is started, including the force, direction, speed and acceleration required by the robot when contacting the parts.

[0104] Specifically, after the robot assembly startup assembly mode is determined, the system will perform a detailed calculation of the physical parameters of the assembly based on this mode to ensure that the mechanical conditions of each assembly action meet the process requirements. Specifically, the system will comprehensively consider the size of the assembly parts, the distance of the assembly path, the posture of the robot end, and other information to calculate the initial physical parameters, including the magnitude, direction, contact speed, and acceleration of the applied force. This calculation takes into account the balance between force and speed, and prevents both loose assembly caused by insufficient force and damage to parts caused by excessive force. The system inputs these physical parameters into the robot controller as guidance data when the assembly is started to ensure that the initial operation is in the best state.

[0105] Step 506 , controlling the assembly robot to move according to the initial assembly physical parameters, and obtaining the robot micro-force feedback control information.

[0106] Specifically, based on the initial assembly physical parameters, the system instructs the assembly robot to move along the assembly path to accurately contact and position the assembly parts. During the movement, the robot monitors its contact force with the parts in real time, and obtains tiny displacement and contact force feedback data through micro-force sensors. These robot micro-force feedback control information provides the system with real-time mechanical feedback of the assembly operation, which is used to evaluate the actual assembly effect. If the feedback information shows that the assembly force, angle or position deviates, the system will automatically adjust the assembly path or force and perform real-time fine-tuning to ensure that the accuracy of the assembly process meets the predetermined standards. Through this feedback mechanism, the system continuously optimizes the assembly operation, enabling the robot to complete tasks stably and efficiently under different assembly conditions.

[0107] In this embodiment, by determining information and movement paths based on the assembly robot parts, the system can select the assembly startup mode that best suits the current task, thereby realizing an adaptive assembly strategy. Combining the assembly mode and part characteristics, the system further calculates the initial assembly physical parameters to ensure that the robot has the appropriate force, direction, and speed at startup, thereby avoiding assembly deviations caused by improper operation. Subsequently, the system controls the movement of the robot and obtains micro-force feedback control information in real time to achieve accurate monitoring and dynamic adjustment of the assembly process. This process makes the assembly process more flexible and efficient, significantly improves assembly accuracy and quality, and reduces assembly defects caused by mechanical deviations or speed mismatches, laying the foundation for realizing intelligent and reliable assembly operations.

[0108] In an exemplary embodiment, Figure 6 As shown, according to the robot assembly startup assembly mode and the assembly robot part determination information, the initial assembly physical parameters are calculated, including steps 602 to 606.

[0109] in:

[0110] Step 602: Calculate the movement posture adjustment information of the assembly robot according to the robot assembly start-up assembly mode and the assembly movement path.

[0111] The mobile posture adjustment information may be the detailed adjustment data of the joint angle, actuator position and movement direction calculated by the system to ensure that the robot maintains the best posture along the assembly path during the assembly task.

[0112] Specifically, the system analyzes the posture adjustment requirements of each key point based on the geometric characteristics of the assembly movement path (such as curvature, angle, slope, etc.) and the requirements of the robot assembly start-up assembly mode. The posture adjustment information includes the robot's joint angles, the attitude angle of the end effector, and the direction of movement to ensure that the contact with the parts remains stable during the movement process, and the mobile posture adjustment information of the assembly robot is calculated. Through the mobile posture adjustment information of the assembly robot, the system can fine-tune the robot's joints to ensure that the robot runs in the best posture at every step on the path, avoiding the influence of posture deviation on assembly accuracy.

[0113] Step 604 , dynamically adjust the assembly robot part determination information according to the movement posture adjustment information to obtain the assembly robot movement dynamic parameter information.

[0114] Among them, dynamic adjustment can be a continuous optimization based on real-time data during the assembly process. The system makes instant adjustments to the robot's operating parameters (such as position, posture, force, etc.) to adapt to instantaneous changes in the environment or different characteristics of the assembly path.

[0115] The dynamic parameter information of the assembly robot movement may be the operation data dynamically generated by the robot during the assembly process, including information such as the adjusted posture, speed, and contact angle.

[0116] Specifically, based on the mobile posture adjustment information, the system further dynamically updates the assembly robot part determination information to meet the needs of different path segments. In this process, the system comprehensively analyzes the real-time position, angle changes, and path characteristics of the parts, and dynamically fine-tunes the robot's grasping and manipulation of the parts. For example, when the path undergoes a large turn or angle change, the system will recalculate the contact force and contact angle to ensure that the robot's control of the parts is accurate and stable in different postures, thereby determining the dynamic parameter information of the assembly robot's movement. This dynamic parameter information enables the robot to smoothly transition between different path segments, ensuring precise part control in complex environments.

[0117] Step 606 , introducing historical error feedback compensation information of the assembly robot, performing nonlinear adjustment on the movement dynamic parameter information of the assembly robot, and obtaining initial assembly physical parameters.

[0118] Among them, the historical error feedback compensation information can be the correction information generated by the system based on the deviation data accumulated in the robot's previous assembly process, which records the amplitude, direction and trend of common errors.

[0119] Among them, nonlinear adjustment can be a high-precision optimization method applied by the system to address the irregularities of errors in the assembly process, dynamically correcting mechanical and posture parameters through complex algorithms.

[0120] Specifically, the system introduces historical error feedback compensation information of robot assembly, uses the deviation pattern recorded in the historical error data, and optimizes parameters such as force, direction, and speed through a nonlinear compensation algorithm to eliminate the cumulative error or path deviation caused by repeated motion in the dynamic parameter information of the assembly robot. In the adjustment process, the nonlinear adjustment gradually adjusts the mechanical conditions in the dynamic parameter information of the assembly robot according to the fluctuation trend of the historical error to obtain parameter output that meets the assembly accuracy. Finally, the initial assembly physical parameters after compensation and nonlinear optimization are obtained, ensuring that the robot can enter the assembly operation with the best force, direction, and posture, significantly improving the assembly accuracy and stability.

[0121] In this embodiment, by calculating the robot's mobile posture adjustment information based on the assembly startup mode and the mobile path, the system can achieve real-time and precise adjustment during the assembly process. By dynamically optimizing the positioning parameters of the parts using the posture adjustment information, the system can flexibly adapt to different operating requirements in the assembly path to ensure the accuracy of each step. At the same time, the introduction of historical error feedback compensation information for nonlinear adjustment allows the system to correct minor deviations caused by repeated operations or environmental changes, thereby generating optimized initial assembly physical parameters. This process significantly improves the stability and accuracy of assembly operations, reduces the impact of cumulative errors, lays a solid foundation for high-quality and reliable assembly, and improves the overall efficiency and accuracy of intelligent assembly.

[0122] In an exemplary embodiment, Figure 7 As shown, the historical error feedback compensation information of the assembly robot is introduced to perform nonlinear adjustment on the dynamic parameter information of the assembly robot movement to obtain the initial assembly physical parameters, including steps 702 to 704. Among them:

[0123] Step 702, starting the assembly mode according to the robot assembly, and defining the assembly mode adaptation factor.

[0124] The assembly mode adaptation factor can be a set of adjustment coefficients defined for different assembly task requirements, which are used to adjust the flexibility, accuracy and force output of the robot's operation when it performs assembly tasks. The factor is set according to the characteristics of the assembly mode (such as flexible assembly mode or precision assembly mode) to ensure that the robot can automatically adapt to the operation requirements when performing different tasks.

[0125] Specifically, the assembly mode adaptation factor is defined according to the robot assembly startup assembly mode (such as flexible assembly or precision assembly) to quantify and adapt the requirements of the specific mode for operational flexibility, precision and force output. The assembly mode adaptation factor is a set of adjustment coefficients used to adjust the adaptability of parameters in the nonlinear optimization process. For example, in the flexible mode, the adaptation factor will relax the tolerance of force control, allowing the robot to be more adaptable when encountering slight deviations; while in the precision mode, the adaptation factor will enhance the sensitivity to position and force to ensure that each step of the operation is accurate. By analyzing the operational requirements and precision level of the task, the system automatically sets the various parameters of the adaptation factor, thereby accurately introducing the characteristics of different assembly modes into the subsequent nonlinear adjustment process, so that the robot can adapt to the current assembly environment after startup.

[0126] Step 704 , nonlinearly adjust the fused data of the assembly robot movement dynamic parameter information, the assembly mode adaptation factor, and the historical error feedback compensation information to obtain initial assembly physical parameters.

[0127] Specifically, the nonlinear adjustment uses the assembly mode adaptation factor as the weight, making the parameter adjustment more flexible and adapting to the mechanical requirements of the current mode; at the same time, the system analyzes the historical error feedback compensation information, uses the frequency, amplitude and trend of the error to compensate the dynamic parameters, and gradually eliminates the accumulated error. During the adjustment process, the system applies a nonlinear optimization algorithm to minimize the residual deviation in the dynamic parameter information of the assembly robot through iterative calculation, especially in the details of the mechanical output and motion path, to ensure that the final generated initial assembly physical parameters meet the precise standards of force, angle and position required for the task. The data set finally output by this process puts the robot in the most ideal mechanical and geometric state when the assembly starts, so as to achieve high-precision and stable assembly.

[0128] Among them, the fusion data of the assembly robot's moving dynamic parameter information, the assembly mode adaptation factor, and the historical error feedback compensation information are nonlinearly adjusted to obtain the expression corresponding to the initial assembly physical parameters:

[0129] P 调整 =F 非线性 ·(M 因子 ·V 动态 +E 反馈 )+P 初始

[0130]

[0131] Among them, α f is the adaptation factor of the force, α v is the speed adaptation factor, α θ is the adaptation factor of the attitude angle, β f is the force history error compensation coefficient, β v is the speed history error compensation coefficient, β θ is the historical error compensation coefficient of attitude angle, is the accumulated error of the force in the past n operations, is the accumulated error of speed in the past n operations, is the cumulative error of the posture angle in the past n operations, tan h(k·x) is the nonlinear adjustment function, k is the sensitivity coefficient, x is the input value of the nonlinear adjustment function, P 装配 Determine information for assembly robot parts, Δ x , Δ y and Δ z They are the position deviations in the x, y, and z directions during dynamic adjustment.

[0132] In this embodiment, by defining the assembly mode adaptation factor according to the robot assembly startup mode, the system can adapt to the needs of different assembly tasks and flexibly adjust the accuracy and mechanical characteristics of the robot operation. Combining the comprehensive data of the assembly mode adaptation factor, mobile dynamic parameter information and historical error feedback compensation information, the system performs nonlinear adjustment and generates optimized initial assembly physical parameters. This fusion adjustment method enables the system to accurately respond to environmental changes and accumulated errors in the task, ensuring that each assembly operation meets the requirements in terms of force, angle and position, thereby significantly improving the accuracy, stability and adaptability of the assembly, ensuring high-quality assembly results and effectively reducing the rework rate.

[0133] In an exemplary embodiment, Figure 8 As shown, according to the visual sensing information and laser displacement sensing information of the assembly robot, the assembly posture of the assembly robot is calibrated at multiple levels to obtain the assembly robot posture determination information, including steps 802 to 806. Wherein:

[0134] Step 802, adjusting the actual three-dimensional coordinates of the assembly robot to the reference three-dimensional coordinates according to the visual sensing information and the laser displacement sensing information, and obtaining the macro calibration information of the assembly robot.

[0135] The reference three-dimensional coordinates can be the spatial reference points of the pre-set standard position and posture in the assembly task, defining the ideal starting position and orientation of the robot in the assembly area.

[0136] Among them, the assembly robot macro calibration information can be the overall position adjustment data generated based on vision and laser displacement sensor data, which includes the alignment information of the robot with the reference coordinates in three-dimensional space.

[0137] Specifically, the system uses visual sensors to obtain an overall image of the assembly area and locate the relative position of the robot and its surroundings. At the same time, the laser displacement sensor collects actual three-dimensional coordinate data, accurately identifies the robot's current position deviation, and makes the first adjustment. Combining visual sensing information and laser displacement data, the system compares the robot's actual three-dimensional coordinates with the preset reference three-dimensional coordinates to analyze the differences in position and posture. Based on the comparison results, the system calculates the adjustment amount for each joint and instructs the robot to gradually adjust its position until its overall three-dimensional coordinates are accurately aligned with the reference coordinates. This process generates macro calibration information for the assembly robot, providing the robot with an accurate initial positioning so that it can achieve optimal alignment with the assembly environment on a macro scale.

[0138] Step 804 , fine-tuning the macroscopic calibration information of the assembly robot according to the laser marking information of the assembly robot to obtain the microscopic calibration information of the assembly robot.

[0139] The laser marking information may be high-precision position data obtained by a laser displacement sensor, which is used to detect and adjust slight deviations between the robot and a reference position.

[0140] Among them, the micro-calibration information of the assembly robot can be the fine calibration data achieved through laser calibration on the basis of macro-calibration, which records the position adjustment results of the robot on a micro scale.

[0141] Specifically, the system further uses laser displacement sensors for fine adjustments, improving positioning accuracy by detecting subtle displacement differences between the reference point and the robot. The errors detected by the laser sensor are usually at the sub-millimeter level, and the system uses this data for more precise fine-tuning operations, calculating correction values ​​for each key point to eliminate residual minor deviations. This fine-tuning operation ensures the precise alignment of the robot with the reference point by adjusting the joint position and the end tool posture, generating micro-calibration information for the assembly robot. After micro-calibration, the robot achieves extremely high accuracy in position and posture, laying a solid foundation for performing more sophisticated assembly tasks.

[0142] Step 806, adjusting the robot arm position and posture information in the assembly robot micro-calibration information to obtain assembly robot position and posture determination information.

[0143] Among them, the robot arm posture information can be the specific position and angle data of the robot arm in three-dimensional space, including the angle of each joint and the position direction of the end tool.

[0144] Specifically, based on the assembly robot's microscopic calibration information, the system makes final adjustments to the end-of-line posture of the robot arm to ensure that the position and angle of the assembly tool in space fully meet the operational requirements. The system first calculates the final angle and position of each joint after fine-tuning, so that the end tool is in the optimal position required for the task. Subsequently, the system refines the motion path of each joint and ensures the dynamic stability of the robot arm in space through real-time sensor data. The final generated assembly robot posture determination information covers the precise positioning and posture of each joint, allowing the robot to perform assembly tasks without error and achieve target accuracy and operational stability.

[0145] In this embodiment, by integrating visual sensing information and laser displacement sensing information, the system can accurately adjust the actual three-dimensional coordinates of the assembly robot to the reference three-dimensional coordinates, complete macro calibration, and ensure the accurate positioning of the robot in the assembly area. Then, the macro calibration data is fine-tuned using laser alignment information to achieve sub-millimeter micro calibration, so that the position and posture of the robot can reach extremely high precision. Finally, the position and posture information of the robot arm after micro calibration is adjusted to obtain the optimal position and posture determination information. This multi-level calibration process greatly improves the positioning accuracy and posture stability of the robot, ensures the precise execution of each operation step in the assembly process, reduces error accumulation and assembly deviation, and achieves reliable, stable and high-quality assembly.

[0146] In an exemplary embodiment, Fig. 9 As shown, the robot arm position information in the assembly robot microscopic calibration information is adjusted to obtain the assembly robot position determination information, including steps 902 to 906. Among them:

[0147] Step 902, locking the six-axis degrees of freedom of the end manipulator of the assembly robot according to the microscopic calibration information of the assembly robot.

[0148] Among them, the six-axis degrees of freedom can be the six independently movable directions of the assembly robot's end manipulator in three-dimensional space, including linear movement along the three coordinate axes of X, Y, and Z (position freedom), and rotation around the X, Y, and Z axes (attitude freedom).

[0149] Specifically, the end position data of the end manipulator of the assembly robot in the microscopic calibration information of the assembly robot is analyzed, and the six degrees of freedom of the end manipulator (including the X, Y, and Z position coordinates in three-dimensional space and the rotation angles around the X, Y, and Z axes) are locked. This locking operation ensures that the end tool does not shift in position or posture during the assembly process and maintains its accuracy. The system forms a fixed reference point by locking the six-axis degrees of freedom of the end, so that the end is always in the reference position and angle when adjusting the remaining manipulator joints. This operation lays a stable spatial reference for subsequent steps, ensuring the accuracy and reliability of the final assembly.

[0150] Step 904 , based on the locked six-axis degrees of freedom and according to the current pose information of the remaining robotic arms of the assembly robot microscopic calibration information, calculate the optimized pose information of the remaining robotic arms.

[0151] Among them, the remaining robotic arms can be other joints and connecting rod parts of the assembly robot except the end robotic arm, and these joints support the precise operation of the end through mutual coordination.

[0152] Among them, the optimized posture information can be the ideal posture data calculated according to the end locking and robot arm position requirements, including the optimal position and angle required for each joint under the premise of meeting the task requirements.

[0153] Specifically, based on the locking of the six-axis degrees of freedom of the end robot, the system uses kinematic models and inverse algorithms to analyze the distribution of the remaining robot joints (i.e., all joints except the end) in the current position. The system calculates the optimal position and angle required for each joint while keeping the end position unchanged, so as to minimize the stress and load of the robot and ensure the balance of the entire arm structure. The system further considers the mutual influence between the joints, and through multiple iterative optimizations, obtains the optimized posture information that enables the robot to have the optimal operating posture, providing support for the smooth and efficient movement of the robot.

[0154] Step 906: adjust the posture of each of the remaining robot arms according to the optimized posture information to obtain the assembly robot posture determination information.

[0155] Specifically, the system gradually adjusts the posture of each remaining robot arm, and adjusts the remaining joints of the robot arm according to the optimization calculation results to achieve the best balance and force state. The adjustment of each joint strictly follows the optimized angle and position settings, and the adjustment is accurate through real-time feedback and sensor monitoring. The final generated assembly robot posture determination information covers the adjustment results of all joints, defines the best posture of the robot in the entire assembly process, enables it to perform tasks efficiently and stably, and ensures mechanical stability and assembly accuracy during operation.

[0156] In this embodiment, through the precise positioning of the micro-calibration information, the system first locks the six-axis degrees of freedom of the end manipulator of the assembly robot to ensure that its position and posture remain stable during the assembly process. Next, based on this locked six-axis degree of freedom, the system analyzes the current posture information of the remaining manipulator joints and calculates the optimal posture adjustment scheme to reduce the joint load and improve overall coordination. Finally, the system adjusts the remaining manipulator joints according to the optimized posture information to generate the assembly robot posture determination information. This process greatly improves the positioning accuracy and mechanical stability of the robot during assembly, ensures the high reliability and consistency of the terminal assembly operation, and thus achieves more accurate and efficient assembly operations.

[0157] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments 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 carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0158] Based on the same inventive concept, the embodiment of the present application also provides a control device for an assembly robot for implementing the control method of the assembly robot involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the control device for one or more assembly robots provided below can refer to the limitations of the control method for an assembly robot above, and will not be repeated here.

[0159] In an exemplary embodiment, Fig.10 As shown, a control device for an assembly robot is provided, comprising: a robot self-calibration module 1002, a part posture adjustment module 1004, a movement path planning module 1006 and a feedback information obtaining module 1008, wherein:

[0160] The robot self-calibration module 1002 is used to perform multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and laser displacement sensing information of the assembly robot to obtain the assembly robot posture determination information;

[0161] The part posture adjustment module 1004 is used to locate the part position and part angle in the assembly robot posture determination information according to the multi-point macro scanning information of the assembly robot, so as to obtain the assembly robot part determination information;

[0162] A moving path planning module 1006 is used to plan the assembly moving path of the assembly robot according to the part determination information of the assembly robot and the spatial three-dimensional information corresponding to the assembly robot;

[0163] The feedback information obtaining module 1008 is used to control the assembly robot to move according to the assembly robot part determination information and the assembly movement path, and obtain the robot micro-force feedback control information;

[0164] The assembly information optimization module 1010 is used to adjust the assembly movement path and the assembly robot part determination information according to the robot micro-force feedback control information, and determine the assembly scene application information of the assembly robot.

[0165] In one embodiment, the assembly information optimization module 1010 is also used to determine the assembly mode of the robot assembly process of the assembly robot based on the robot micro-force feedback control information; fine-tune the assembly force and assembly error of the assembly robot parts determined by the robot micro-force feedback control information and the assembly mode of the robot assembly process to obtain robot assembly fine-tuning information; perform multi-level precision calibration on the robot assembly fine-tuning information to obtain assembly scene application information.

[0166] In one embodiment, the assembly information optimization module 1010 is also used to perform reference point positioning calibration on the reference point information of the robot assembly fine-tuning information to obtain the robot assembly reference point calibration information; perform contact force balance calibration on the contact force information of the robot assembly reference point calibration information to obtain the robot assembly contact force calibration information; perform multi-vector calibration on the three-dimensional space of the robot assembly contact force calibration information to obtain assembly scene application information.

[0167] In one embodiment, the feedback information obtaining module 1008 is also used to determine the robot assembly start-up assembly mode based on the assembly robot parts determination information and the assembly movement path; calculate the initial assembly physical parameters based on the robot assembly start-up assembly mode and the assembly robot parts determination information; control the assembly robot to move based on the initial assembly physical parameters, and obtain the robot micro-force feedback control information.

[0168] In one embodiment, the feedback information obtaining module 1008 is also used to calculate the mobile posture adjustment information of the assembly robot according to the robot assembly startup assembly mode and the assembly movement path; dynamically adjust the assembly robot part determination information according to the mobile posture adjustment information to obtain the assembly robot movement dynamic parameter information; introduce the historical error feedback compensation information of the assembly robot, perform nonlinear adjustment on the assembly robot movement dynamic parameter information, and obtain the initial assembly physical parameters.

[0169] In one embodiment, the feedback information obtaining module 1008 is also used to define the assembly mode adaptation factor according to the robot assembly startup assembly mode; perform nonlinear adjustment on the fusion data of the assembly robot movement dynamic parameter information, the assembly mode adaptation factor and the historical error feedback compensation information to obtain the initial assembly physical parameters.

[0170] In one embodiment, the robot self-calibration module 1002 is also used to fine-tune the macro calibration information of the assembly robot according to the laser marking information of the assembly robot to obtain the micro calibration information of the assembly robot; and adjust the robot arm posture information in the micro calibration information of the assembly robot to obtain the posture determination information of the assembly robot.

[0171] In one embodiment, the robot self-calibration module 1002 is also used to lock the six-axis degrees of freedom of the end robotic arm of the assembly robot according to the microscopic calibration information of the assembly robot; based on the locked six-axis degrees of freedom, calculate the optimized posture information of each remaining robotic arm according to the current posture information of each remaining robotic arm according to the microscopic calibration information of the assembly robot; adjust the posture of each remaining robotic arm according to the optimized posture information to obtain the posture determination information of the assembly robot.

[0172] Each module in the control device of the assembly robot 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 the computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0173] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a control method for an assembly robot is implemented.

[0174] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0175] In one embodiment, a computer device is further 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 method embodiments when executing the computer program.

[0176] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0177] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0178] 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.

[0179] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods 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 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), magnetoresistive 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, etc., but are not limited to this.

[0180] 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 specification.

[0181] 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 control method for an assembly robot, characterized in that: The method comprises: Performing multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and the laser displacement sensing information of the assembly robot to obtain the assembly robot posture determination information; Positioning the part position and part angle in the assembly robot posture determination information according to the multi-point macro scanning information of the assembly robot to obtain the assembly robot part determination information; Planning an assembly movement path of the assembly robot according to the assembly robot part determination information and the spatial three-dimensional information corresponding to the assembly robot; According to the assembly robot part determination information and the assembly movement path, the assembly robot is controlled to move, and the robot micro-force feedback control information is obtained; According to the robot micro-force feedback control information, the assembly movement path and the assembly robot part determination information are adjusted to determine the assembly scene application information of the assembly robot.

2. The method according to claim 1, characterized in that The step of adjusting the assembly movement path and the assembly robot part determination information according to the robot micro-force feedback control information to determine the assembly scene application information of the assembly robot includes: determining an assembly mode of a robot assembly process of the assembly robot according to the robot micro-force feedback control information; According to the robot micro-force feedback control information and the robot assembly process assembly mode, fine-tune the assembly force and assembly error of the assembly robot part determination information to obtain robot assembly fine-tuning information; The robot assembly fine-tuning information is calibrated at multiple levels of accuracy to obtain the assembly scene application information.

3. The method according to claim 2, characterized in that The multi-level precision calibration of the robot assembly fine-tuning information to obtain the assembly scene application information includes: Performing reference point positioning calibration on the reference point information of the robot assembly fine-tuning information to obtain robot assembly reference point calibration information; Performing contact force balance calibration on the contact force information of the robot assembly reference point calibration information to obtain robot assembly contact force calibration information; Multi-vector calibration is performed on the three-dimensional space of the robot assembly contact force calibration information to obtain the assembly scene application information.

4. The method according to claim 1, characterized in that The step of controlling the assembly robot to move according to the assembly robot part determination information and the assembly movement path, and obtaining the robot micro-force feedback control information, comprises: Determine a robot assembly start-up assembly mode according to the assembly robot part determination information and the assembly movement path; Calculating initial assembly physical parameters according to the robot assembly startup assembly mode and the assembly robot part determination information; According to the initial assembly physical parameters, the assembly robot is controlled to move, and micro-force feedback control information of the robot is obtained.

5. The method according to claim 4, characterized in that The calculating of initial assembly physical parameters according to the robot assembly startup assembly mode and the assembly robot part determination information includes: Calculating the movement posture adjustment information of the assembly robot according to the robot assembly start assembly mode and the assembly movement path; According to the mobile posture adjustment information, dynamically adjust the assembly robot part determination information to obtain the assembly robot movement dynamic parameter information; The historical error feedback compensation information of the assembly robot is introduced to perform nonlinear adjustment on the movement dynamic parameter information of the assembly robot to obtain the initial assembly physical parameters.

6. The method according to claim 5, characterized in that The introducing of the historical error feedback compensation information of the assembly robot and the nonlinear adjustment of the movement dynamic parameter information of the assembly robot to obtain the initial assembly physical parameters include: According to the robot assembly start assembly mode, defining an assembly mode adaptation factor; Nonlinear adjustment is performed on the fusion data of the assembly robot movement dynamic parameter information, the assembly mode adaptation factor and the historical error feedback compensation information to obtain the initial assembly physical parameters.

7. The method according to claim 6, characterized in that The nonlinear adjustment is performed on the fusion data of the assembly robot movement dynamic parameter information, the assembly mode adaptation factor and the historical error feedback compensation information to obtain the expression corresponding to the initial assembly physical parameter: P 调整 =F 非线性 ·(M 因子 ·V 动态 +E 反馈 )+P 初始 Among them, α f is the adaptation factor of the force, α v is the speed adaptation factor, α θ is the adaptation factor of the attitude angle, β f is the force history error compensation coefficient, β v is the speed history error compensation coefficient, β θ is the historical error compensation coefficient of attitude angle, is the accumulated error of the force in the past n operations, is the accumulated error of speed in the past n operations, is the cumulative error of the posture angle in the past n operations, tan h(k·x) is the nonlinear adjustment function, k is the sensitivity coefficient, x is the input value of the nonlinear adjustment function, P 装配 Determine information for assembly robot parts, Δ x , Δ y and Δ z They are the position deviations in the x, y, and z directions during dynamic adjustment.

8. The method according to claim 1, characterized in that The method of performing multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and the laser displacement sensing information of the assembly robot to obtain the assembly robot posture determination information includes: According to the visual sensing information and the laser displacement sensing information, adjusting the actual three-dimensional coordinates of the assembly robot to the reference three-dimensional coordinates to obtain macroscopic calibration information of the assembly robot; According to the laser marking information of the assembly robot, fine-tuning the macroscopic calibration information of the assembly robot is performed to obtain the microscopic calibration information of the assembly robot; The robot arm position and posture information in the assembly robot micro-calibration information is adjusted to obtain the assembly robot position and posture determination information.

9. The method according to claim 8, characterized in that The step of adjusting the robot arm posture information in the microscopic calibration information of the assembly robot to obtain the assembly robot posture determination information includes: According to the microscopic calibration information of the assembly robot, locking the six-axis degrees of freedom of the end manipulator of the assembly robot; Based on the locked six-axis degrees of freedom, and according to the current pose information of the remaining mechanical arms of the assembly robot microscopic calibration information, the optimized pose information of the remaining mechanical arms is calculated; The posture of each of the remaining robotic arms is adjusted according to the optimized posture information to obtain the posture determination information of the assembly robot.

10. A control device for an assembly robot, characterized in that: The device comprises: A robot self-calibration module, used to perform multi-level self-calibration on the assembly posture of the assembly robot according to the visual sensing information and laser displacement sensing information of the assembly robot, so as to obtain the assembly robot posture determination information; A part posture adjustment module is used to locate the part position and part angle in the assembly robot posture determination information according to the multi-point macro scanning information of the assembly robot to obtain the assembly robot part determination information; A moving path planning module, used to plan the assembly moving path of the assembly robot according to the part determination information of the assembly robot and the spatial three-dimensional information corresponding to the assembly robot; A feedback information obtaining module, used to control the assembly robot to move according to the assembly robot part determination information and the assembly movement path, and obtain the robot micro-force feedback control information; The assembly information optimization module is used to adjust the assembly movement path and the assembly robot part determination information according to the robot micro-force feedback control information, and determine the assembly scene application information of the assembly robot.

Images