Robot control method, control device, robot, and storage medium

Abstract

This application provides a robot control method, control device, robot, and storage medium. The method includes: acquiring a target operation task, the target operation task being used to instruct the robot to perform a target operation on the calibration object; controlling the robot to move to a first workstation near the calibration object based on the position information of the calibration object; acquiring feature data of the calibration object and identification data of the first workstation through the robot; controlling the robot at the first workstation to perform pose correction based on the feature data of the calibration object and the identification data of the first workstation; and controlling the pose-corrected robot to perform the target operation on the calibration object. This application enables precise control of the robot, thereby effectively improving the success rate of precise robot operations.

Description

Technical Field

[0001] This invention relates to the field of robotics, and more particularly to a robot control method, control device, robot, and storage medium. Background Technology

[0002] With the continuous development of robotics technology, robots have been widely used in various fields such as industrial manufacturing, logistics and transportation, and medical assistance. Most existing robot control methods are based on preset rules, fixed control models, or pre-set control strategies, which achieve automatic execution of tasks by programmatically controlling predetermined work processes.

[0003] However, in some work scenarios that require extremely high operational precision, such as assembly operations in precision manufacturing workshops, traditional robot control methods lack generalization ability and are difficult to control robots precisely, resulting in a low success rate of precise robot operations. Summary of the Invention

[0004] This application provides a robot control method, control device, robot, and storage medium, aiming to improve the success rate of precise robot operations.

[0005] In a first aspect, this application provides a robot control method, including: Obtain the target operation task, which is used to instruct the robot to perform a target operation on a calibrated object; Based on the location information of the calibrated object, the robot is controlled to move to the first workstation near the calibrated object; The robot acquires the feature data of the calibrated object and the identification data of the first workstation. Based on the feature data of the calibration object and the identification data of the first workstation, the robot on the first workstation is controlled to perform pose correction. After the robot has undergone pose correction, it performs the target operation on the calibrated object.

[0006] Secondly, this application also provides a control device, which includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, it implements the robot control method as described above.

[0007] Thirdly, this application also provides a robot, comprising: The robot itself; A mobile chassis is mounted on the robot body, and the robot changes position as the mobile chassis moves. An active mechanism is provided on the robot body, and the robot changes its posture as the active mechanism is adjusted; An end effector, mounted on the robot body or the movable mechanism, is used to perform a target operation; The control device described above is used to control the mobile chassis, the movable mechanism, and each of the end effectors.

[0008] Fourthly, this application also provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, which can be executed by one or more processors to implement any of the robot control methods provided in the embodiments of this application.

[0009] This application discloses a robot control method, control device, robot, and storage medium. The robot control method provided in the above embodiments acquires a target operation task, which instructs the robot to perform a target operation on a calibrated object. Based on the position information of the calibrated object, the robot is controlled to move to a first workstation near the calibrated object. The robot acquires feature data of the calibrated object and identification data of the first workstation. Based on the feature data of the calibrated object and the identification data of the first workstation, the robot at the first workstation is controlled to perform pose correction. The robot with the corrected pose then performs the target operation on the calibrated object. In this application, after guiding the robot to the first workstation, the pose correction at the first workstation is performed by combining the feature data of the calibrated object and the identification data of the first workstation. This enables the robot to accurately align with the calibrated object, avoiding target operation errors caused by inaccurate pose. Therefore, it achieves high-precision control of the robot to perform target operations on the calibrated object, thereby greatly improving the success rate of the robot's precision operations.

[0010] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A schematic flowchart illustrating the steps of a robot control method provided in one embodiment of this application; Figure 2 for Figure 1 A flowchart illustrating the sub-steps of the robot control method in the diagram; Figure 3 A schematic block diagram of a control device provided in an embodiment of this application; Figure 4 This is a schematic block diagram of a robot provided in an embodiment of this application. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0015] This application provides a robot control method, control device, robot, and storage medium. The robot control method can be applied to the control device, which can be installed on a robot or computer equipment. The robot can be, for example, a cleaning robot, an industrial robot, or a unibody robot. The computer equipment can include a server or a terminal device. The server can be a single server or a server cluster consisting of multiple servers. The terminal device can be an electronic device such as a mobile phone, tablet computer, laptop computer, desktop computer, personal digital assistant, or wearable device.

[0016] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0017] Please see Figure 1 , Figure 1 This is a schematic flowchart of a robot control method provided in one embodiment of this application.

[0018] like Figure 1 As shown, the robot control method includes steps S101 to S105.

[0019] Step S101: Obtain the target operation task.

[0020] The target operation task is used to instruct the robot to perform a target operation on a calibrated object. The target operation task can include the location information of the calibrated object, the type of target operation, and the operation parameter requirements. The calibrated object can be any type of object to be processed, such as parts, electronic components, etc. There can be one or more calibrated objects, and the target operation can include grasping, assembly, and inspection.

[0021] For example, in the assembly operation in a precision manufacturing workshop, the calibration object can be the bearing assembly to be assembled, and the target operation task is to press the bearing assembly into the designated position of the motor shaft fixed on the fixture according to the preset angle and force. The target operation task can include the model and specifications of the bearing assembly, the coordinate data of the target assembly position, etc.

[0022] Step S102: Based on the position information of the calibration object, control the robot to move to the first workstation near the calibration object.

[0023] The location information of the calibration object is used to determine its three-dimensional coordinates in the robot's current workspace. This information can be obtained through sensors, radar, or a pre-configured coordinate system. The first workstation near the calibration object can be located at a certain distance from the calibration object. This certain distance can be determined by the type of operation of the target operation and the structural characteristics of the robot, ensuring that the robot has sufficient degrees of freedom and operating space at the first workstation, thereby ensuring the smooth execution of subsequent target operation tasks.

[0024] Understandably, by calibrating the location information of the object, the robot is moved to the first workstation near it, thus achieving the robot's initial positioning, which helps to control the robot more accurately for more precise adjustments in the future.

[0025] In one embodiment, controlling a robot to move to a first workstation near the calibration object based on the location information of the calibration object includes: determining the location information of multiple candidate workstations near the calibration object based on the location information of the calibration object; determining the current location information of the robot, and determining a first workstation from the multiple candidate workstations based on the current location information of the robot and the location information of each candidate workstation; and controlling the robot to move to the first workstation based on the location information of the first workstation.

[0026] Taking the assembly operation in a precision manufacturing workshop as an example, let the workshop be the robot's workspace, the calibrated object be the bearing assembly to be assembled, and the target operation task be to press the bearing assembly into the designated position of the motor shaft fixed on the fixture according to the preset angle and force.

[0027] Specifically, using the geometric centers of the bearing assembly and the motor shaft as reference points for their positional information, multiple candidate positions are generated within a preset radius according to preset angular intervals or a grid division method. Each candidate position corresponds to a candidate workstation. The robot's current position information can be obtained through the robot's built-in measurement unit or internal / external positioning system, and may include the robot's current three-dimensional coordinates, attitude, and angle in the workspace.

[0028] Furthermore, after determining the robot's current position and the position information of each candidate workstation, the path from the robot's current position to each candidate workstation is calculated, and the path cost of each path is determined. The path cost can include indicators such as path length, obstacle avoidance difficulty, and path time, and can be presented in the form of a comprehensive score. Finally, the candidate workstation with the lowest path cost can be selected as the first workstation, ensuring that the robot can move safely and quickly to the first workstation and efficiently achieve the robot's initial localization.

[0029] Step S103: Obtain the feature data of the calibrated object and the identification data of the first workstation through the robot.

[0030] The feature data of the calibration object is used to characterize specific features such as the size and position of its geometry. Taking bearing assemblies and motor shafts as examples, the feature data of a bearing assembly may include the inner ring diameter, outer ring diameter, and hardness, while the feature data of a motor shaft may include the shaft diameter and keyway dimensions. Specifically, the feature data of the calibration object can be acquired through a measuring device mounted on the robot, such as a vision sensor, laser scanner, or tactile sensor. During the acquisition of the feature data of the calibration object, the robot can perform multi-angle and multi-position measurements to obtain more detailed data associated with the calibration object, thereby improving the completeness and accuracy of the feature data.

[0031] The identification data for the first workstation may include unique coded data identifying the location information of the first workstation, which may be in the form of a QR code, barcode, RFID tag, or digital code, and is pre-stored in the identification device on the first workstation. The identification data for the first workstation may also include spatial attribute information such as the boundary of the first workstation and height restrictions. After the robot moves to the first workstation, it also reads the data through its onboard measuring device to confirm that it has accurately arrived at the first workstation, and at the same time, acquires the identification data of the first workstation, thereby establishing the correspondence between the calibrated object and the first workstation.

[0032] Understandably, compared to acquiring pre-stored feature data of the calibration object and identification data of the first station, real-time acquisition of feature data of the calibration object and identification data of the first station by the robot can ensure the timeliness of the data and avoid subsequent operation failures of the robot due to deviations between pre-stored data and actual working conditions.

[0033] In one embodiment, acquiring feature data of the calibration object and identification data of the first workstation through a robot includes: controlling the robot at the first workstation to scan the surrounding environment to obtain environmental data containing the calibration object and the first workstation; and extracting features from the environmental data to obtain feature data of the calibration object and identification data of the first workstation.

[0034] The environmental data can be point cloud data, image data, or depth map data, etc. Specifically, the measuring device built by the robot can be controlled to perform a full-range scan of the first workstation and its surrounding area to collect various types of information in three-dimensional space more comprehensively.

[0035] Furthermore, the acquisition of feature data for the calibration object can be achieved by extracting features from the environmental data using a pre-defined algorithm model. Specifically, taking point cloud data as an example, a feature recognition algorithm can be used to segment objects with specific contours from the environmental data and extract their geometric features. Alternatively, a deep learning-based object detection model can be used to directly identify and locate the calibration object from the environmental data.

[0036] In addition, the extraction of identification data from the first workstation can be determined based on the specific form of the identification. For example, if the identification is in the form of a QR code or barcode, an image decoding algorithm can be used to analyze the image captured by the camera to obtain the unique identification information encoded therein; if the identification is an RFID tag, the electronic data stored in the tag can be obtained through a radio frequency reading module; if the identification is a specific pattern or color mark, it can be identified and located through image segmentation and pattern matching algorithms.

[0037] Step S104: Based on the feature data of the calibrated object and the identification data of the first station, control the robot on the first station to perform pose correction.

[0038] It is understandable that the feature data of the calibrated object and the identification data of the first station reflect the key spatial information required for the robot to perform target operations on the calibrated object from different dimensions. Therefore, by combining the feature data of the calibrated object and the identification data of the first station, the deviation between the robot's current pose and the desired pose can be determined and calculated, thereby driving the robot to perform corresponding pose correction operations to ensure that the robot can accurately perform target operations on the calibrated object in the future.

[0039] In one embodiment, such as Figure 2 As shown, step S104 includes sub-steps S1041 to S1042.

[0040] Sub-step S1041: Determine the target pose of the robot to perform the target operation on the calibrated object based on the feature data of the calibrated object and the identification data of the first station.

[0041] For example, firstly, the feature data of the calibration object is analyzed to extract its key geometric parameters, including contour dimensions, surface normal vector distribution, feature hole coordinates, and assembly reference surface information. Simultaneously, combined with the identification data of the first workstation, the precise position, attitude angle, and preset assembly operation space range of that workstation in the global coordinate system are obtained. Further, based on the above information, the relative pose relationship between the calibration object and the first workstation is established in the kinematic model. Combining the motion limits of the robot's own components or structures, and the collision avoidance constraints of surrounding equipment or obstacles, the target pose of the robot performing target operations on the calibration object is obtained by solving the inverse kinematic equations.

[0042] Understandably, the target pose can be determined from one or more candidate poses that can satisfy the target operation on the calibrated object. For example, in assembly operations in a precision manufacturing workshop, the target pose can be the pose that makes the axis of the bearing assembly to be assembled coincide with the axis of the motor shaft and the fitting depth meet the process requirements. Similarly, in welding operations, the target pose can be the pose that makes the end effector of the robot, the welding torch, aligned with the weld start point and the welding torch posture maintains a specific angle with the weld tangent direction. When multiple candidate poses exist, they can be screened based on robot kinematic optimality indices or randomly assigned. Once the target pose is determined, the remaining candidate poses can be used as a set of candidate poses to provide alternative solutions for subsequent pose adjustments or obstacle avoidance planning, effectively reducing the probability of robot operation failure.

[0043] In one embodiment, determining the target pose of the robot to perform a target operation on the calibrated object based on the feature data of the calibrated object and the identification data of the first station includes: determining the first pose of the robot's end effector based on the feature data of the calibrated object; determining the second pose of the robot's drive mechanism based on the identification data of the first station; and determining the target pose of the robot to perform a target operation on the calibrated object based on the first pose and the second pose.

[0044] The first pose characterizes the spatial configuration that the end effector must achieve to complete the target operation on the calibration object, while the second pose characterizes the basic attitude parameters required by the drive mechanism to support the end effector in reaching the first pose. Accordingly, determining the first pose requires consideration of the geometric and spatial orientation characteristics of the calibration object. For example, when the calibration object is a precision part with a specific aperture, the clamping center of the end effector must be aligned with the centroid of the part, the normal vector of the clamping surface must be parallel to the axis of the part, and the clamping opening must be dynamically adjusted according to the outer diameter of the part to ensure uniform distribution of clamping force and avoid surface damage. Determining the second pose requires calculating the rotation angle and displacement of each joint axis of the drive mechanism using information such as the origin of the station coordinate system, the direction of the coordinate axes, and the effective working space range from the identification data of the first station, ensuring that the working space of the end effector covers the area where the calibration object is located.

[0045] It is understandable that the robot's end effector can have one or more first poses and the robot's drive mechanism can have one or more second poses. However, not any combination of a first pose and a second pose can directly constitute the target pose that enables the robot to perform target operations on the calibrated object. Therefore, multiple candidate pose combinations formed by each first pose and each second pose can be screened according to actual operational requirements. For example, when the target operation is a precision assembly task, the pose combination with the end effector's clamping stability index higher than a preset threshold and the drive mechanism's joint angular velocity change rate being the smallest should be selected to suppress vibration interference during movement. When there are obstacles in the first workstation, pose combinations that would cause the robotic arm to collide with the surrounding environment should be eliminated. In this way, the reliability and safety of the robot's operation under various working conditions can be effectively improved, thereby effectively increasing the success rate of the robot's precision operations.

[0046] Sub-step S1042: Based on the target pose of the robot performing the target operation on the calibrated object, perform pose correction on the robot at the first station.

[0047] Understandably, by correcting the robot's pose, it can be ensured that the robot's end effector can approach the calibrated object with the correct spatial position and posture, effectively ensuring the successful execution of subsequent target operations.

[0048] Step S105: Control the robot after pose correction to perform target operations on the calibrated object.

[0049] Understandably, after the robot completes pose correction based on the target pose of the calibrated object, it can accurately perform target operations on the calibrated object, thus achieving efficient and high-quality completion of the target operation task.

[0050] In one embodiment, controlling the robot after pose correction to perform a target operation on a calibrated object includes: determining the pose parameters of the robot after pose correction; determining the motion trajectory of the robot performing the target operation on the calibrated object based on the pose parameters of the robot after pose correction and the feature data of the calibrated object; and controlling the robot to perform the target operation on the calibrated object according to the motion trajectory.

[0051] Determining the robot's pose parameters may involve acquiring feedback values ​​from each moving mechanism / joint axis, spatial coordinates of the end effector, and attitude angle data. These data are then transformed using coordinate transformation to obtain a complete pose description of the robot in the base coordinate system, thus yielding the pose parameters of the robot after pose correction. The feature data of the calibration object may include its geometric contour dimensions and the spatial coordinates of key feature points.

[0052] For example, the relative spatial relationship between the end effector and the target operating area is first calculated. A smooth and continuous motion trajectory is generated using spline curve interpolation or a combination of linear and circular arc interpolation algorithms. This motion trajectory includes the coordinates of the trajectory start point, trajectory end point, intermediate points along the way, and the velocity and acceleration constraints corresponding to each trajectory segment. During the trajectory planning process, inverse kinematics calculation is performed simultaneously to convert the Cartesian space trajectory into a sequence of angular displacements of each joint axis. The angular displacements of each joint are checked to see if they exceed the mechanical limit range and if there are any singular configurations. If there are constraint conflicts, a trajectory replanning mechanism is triggered to adjust the intermediate point positions or change the interpolation strategy to generate a feasible trajectory that meets the constraints. After the motion trajectory is confirmed to be correct, the control system sends a trajectory execution command to the servo drive unit. The servo drive unit controls the motors of each axis to operate in coordination according to the velocity curve of the trajectory planning, so that the end effector approaches the calibration object along the predetermined trajectory.

[0053] In one embodiment, controlling the robot after pose correction to perform a target operation on a calibrated object further includes: acquiring an image of the calibrated object to determine the contact state parameters between the robot and the calibrated object; determining whether the target operation has been executed correctly based on the contact state parameters and a preset contact threshold range; if it is determined that the target operation has not been executed correctly, then fine-tuning the robot's pose based on the contact state parameters and the preset contact threshold range; and controlling the robot after pose fine-tuning to continue performing the target operation on the calibrated object.

[0054] The contact state parameters can include the contact area, contact pressure distribution, or deformation of the contact position between the robot's end effector and the calibration object. Understandably, in operational scenarios requiring extremely high precision, the successful execution of certain target operations on the calibration object has strict criteria, and relying solely on force control thresholds or single position feedback is often insufficient to comprehensively characterize the actual contact state.

[0055] Specifically, contact state parameters can be acquired through various sensors integrated on the robot, such as laser displacement sensors and pressure sensors on the robot's end effector. By fusing the data obtained from each sensor, a complete contact state description is generated, resulting in contact state parameters that accurately reflect the contact state between the robot and the calibration object.

[0056] The preset contact threshold range can be stored in the database for the robot to access in real time. The contact state parameters are compared with the preset contact threshold range. If the contact state parameters are within the preset threshold range, the target operation is considered to have been executed successfully; otherwise, the target operation is considered not to have been executed successfully, and further fine-tuning of the robot's pose is required. Specifically, based on the direction and amount of deviation between the contact state parameters and the preset contact threshold range, the compensation displacement and attitude adjustment angle of the robot's end effector in three-dimensional space can be calculated. This generates a pose fine-tuning command, which is then sent to the robot controller to drive each joint to perform the fine-tuning action. After the robot's pose fine-tuning is completed, the image acquisition process is triggered again to re-acquire the contact state parameters and perform iterative judgments until the target operation is executed successfully or the preset maximum number of iterations is reached.

[0057] In one embodiment, after the target operation is completed, the data associated with the calibrated object and the target operation is recorded and stored to form a traceable robot operation process database, which facilitates further optimization of robot control in the future.

[0058] The robot control method provided in the above embodiments acquires a target operation task, which instructs the robot to perform a target operation on a calibrated object; based on the position information of the calibrated object, it controls the robot to move to a first workstation near the calibrated object; it acquires feature data of the calibrated object and identification data of the first workstation through the robot; based on the feature data of the calibrated object and the identification data of the first workstation, it controls the robot at the first workstation to perform pose correction; and it controls the pose-corrected robot to perform the target operation on the calibrated object. The embodiments of this application, after guiding the robot to the first workstation, can combine the feature data of the calibrated object and the identification data of the first workstation to perform pose correction on the robot at the first workstation, enabling the robot to accurately align with the calibrated object, avoiding target operation errors caused by inaccurate pose, thus achieving high-precision control of the robot to perform target operations on the calibrated object, thereby greatly improving the success rate of the robot's precision operations.

[0059] Taking engine assembly in the automotive manufacturing industry as an example, the target task is to instruct the robot to install a precision component onto the engine block. First, the robot acquires this target task, clarifying the operation it needs to perform. Then, it acquires the position information of the engine block (the calibration object) and controls the robot to move to the first workstation near the engine block. Once at the first workstation, the robot uses a camera to acquire feature data of the engine block, such as its outline, the position and size of the mounting holes, and simultaneously acquires identification data of the first workstation, such as positioning marks and flatness. By analyzing the feature data and identification data, the deviation between the robot's current pose and the ideal installation pose is calculated. Then, the robot is controlled to perform pose correction. If the robot's current tilt angle is incorrect, the joint angles are adjusted to achieve the correct tilt angle; if there is a deviation in the relative position of the robot and the engine block, the robot is moved to accurately align with the mounting holes. Finally, the robot, after pose correction, accurately installs the precision component onto the engine block. Because the robot has undergone precise posture correction, it can complete the installation of parts with high precision, improving the quality and success rate of engine assembly. Even in the complex environment of an automobile manufacturing workshop, it can ensure the accuracy and reliability of operation.

[0060] This application also provides a control device. Please refer to... Figure 3 , Figure 3 This is a schematic block diagram of a control device provided in an embodiment of this application.

[0061] like Figure 3 As shown, the control device 200 includes a processor 201, a memory 202 and a network interface connected via a system bus 203. The memory 202 may include a storage medium and internal memory 202. The storage medium may be non-volatile or volatile.

[0062] The storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor 201 to perform any type of robot control.

[0063] The processor 201 provides computing and control capabilities to support the operation of the entire control unit 200.

[0064] The internal memory 202 provides an environment for the execution of computer programs stored in the storage medium. When the computer program is executed by the processor 201, the processor 201 can perform any kind of robot control.

[0065] Those skilled in the art will understand that Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the control device 200 to which the present application is applied. The specific control device 200 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0066] It should be understood that processor 201 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, the general-purpose processor can be a microprocessor or any conventional processor.

[0067] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps: Obtain the target operation task, which is used to instruct the robot to perform a target operation on a calibrated object; Based on the location information of the calibration object, control the robot to move to the first workstation near the calibration object; The robot acquires feature data of the calibrated object and identification data of the first workstation. Based on the feature data of the calibrated object and the identification data of the first station, control the robot on the first station to perform pose correction; After the robot's pose is corrected, it performs target operations on the calibrated object.

[0068] In one embodiment, when the processor controls the robot to move to a first workstation near the calibration object based on the location information of the calibration object, it is used to: Based on the location information of the calibration object, determine the location information of multiple candidate workstations near the calibration object; determine the current location information of the robot, and based on the current location information of the robot and the location information of each candidate workstation, determine the first workstation from the multiple candidate workstations; based on the location information of the first workstation, control the robot to move to the first workstation.

[0069] In one embodiment, when the processor acquires feature data of the calibrated object and identification data of the first workstation through the robot, it is used to: The robot at the first workstation is controlled to scan the surrounding environment to obtain environmental data containing the calibrated object and the first workstation; feature extraction is performed on the environmental data to obtain the feature data of the calibrated object and the identification data of the first workstation.

[0070] In one embodiment, when the processor controls the robot at the first workstation to perform pose correction based on the feature data of the calibrated object and the identification data of the first workstation, it is used to: Based on the feature data of the calibrated object and the identification data of the first station, the target pose of the robot for performing the target operation on the calibrated object is determined; based on the target pose of the robot for performing the target operation on the calibrated object, the pose of the robot at the first station is corrected.

[0071] In one embodiment, when the processor determines the target pose of the robot performing a target operation on the calibrated object based on the feature data of the calibrated object and the identification data of the first station, it is configured to: Based on the feature data of the calibrated object, the first pose of the robot's end effector is determined; based on the identification data of the first workstation, the second pose of the robot's drive mechanism is determined; based on the first and second poses, the target pose of the robot for performing the target operation on the calibrated object is determined.

[0072] In one embodiment, when the processor performs target operations on the calibrated object after controlling the robot's pose correction, it is used to: Determine the pose parameters of the robot after pose correction; based on the pose parameters of the robot after pose correction and the feature data of the calibration object, determine the motion trajectory of the robot to perform target operations on the calibration object; control the robot to perform target operations on the calibration object according to the motion trajectory.

[0073] In one embodiment, when the processor implements target operations on the calibrated object by the robot after control pose correction, it is also used to implement: Image acquisition is performed on the calibration object to determine the contact state parameters between the robot and the calibration object; based on the contact state parameters and the preset contact threshold range, it is determined whether the target operation has been executed properly; if it is determined that the target operation has not been executed properly, the robot's pose is fine-tuned based on the contact state parameters and the preset contact threshold range; the robot with the fine-tuned pose is then controlled to continue performing the target operation on the calibration object.

[0074] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the control device described above can be referred to the corresponding process in the aforementioned robot control embodiments, and will not be repeated here.

[0075] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0076] Please see Figure 4 , Figure 4 This is a schematic block diagram of a robot provided in an embodiment of this application.

[0077] like Figure 4 As shown, the robot 300 includes: Robot body 301; A mobile chassis 302 is mounted on the robot body 301, and the robot 300 changes position as the mobile chassis 302 moves. The motion mechanism 303 is located on the robot body 301, and the robot 300 changes its posture as the motion mechanism 303 is adjusted. The end effector 304 is mounted on the robot body 301 or the moving mechanism 303 and is used to perform the target operation; The control device 305 is used to control the mobile chassis 302, the movable mechanism 303, and each end effector 304. The control device 305 may be the control device 200 described in the preceding embodiments.

[0078] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of each module of the robot described above can be referred to the corresponding processes in the aforementioned robot control method embodiments, and will not be repeated here.

[0079] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can be referred to various embodiments of the robot control method of this application.

[0080] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0081] It should also be understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, herein, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0082] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above descriptions are merely specific implementations of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A robot control method, characterized in that, include: Obtain the target operation task, which is used to instruct the robot to perform a target operation on a calibrated object; Based on the location information of the calibrated object, the robot is controlled to move to the first workstation near the calibrated object; The robot acquires the feature data of the calibrated object and the identification data of the first workstation. Based on the feature data of the calibration object and the identification data of the first workstation, the robot on the first workstation is controlled to perform pose correction. After the robot has undergone pose correction, it performs the target operation on the calibrated object.

2. The robot control method as described in claim 1, characterized in that, The step of controlling the robot at the first workstation to perform pose correction based on the feature data of the calibrated object and the identification data of the first workstation includes: Based on the feature data of the calibrated object and the identification data of the first workstation, the target pose of the robot performing the target operation on the calibrated object is determined; Based on the target pose of the robot performing the target operation on the calibrated object, the pose of the robot at the first workstation is corrected.

3. The robot control method as described in claim 2, characterized in that, Determining the target pose of the robot performing the target operation on the calibrated object based on the feature data of the calibrated object and the identification data of the first workstation includes: Based on the feature data of the calibration object, the first pose of the robot's end effector is determined; Based on the identification data of the first workstation, the second pose of the robot's drive mechanism is determined; Based on the first pose and the second pose, the target pose of the robot performing the target operation on the calibrated object is determined.

4. The robot control method as described in claim 1, characterized in that, The step of acquiring the feature data of the calibrated object and the identification data of the first workstation through the robot includes: The robot at the first workstation is controlled to scan the surrounding environment to obtain environmental data containing the calibrated object and the first workstation. Feature extraction is performed on the environmental data to obtain the feature data of the calibrated object and the identification data of the first workstation.

5. The robot control method as described in claim 1, characterized in that, The step of controlling the robot to move to a first workstation near the calibration object based on the location information of the calibration object includes: Based on the location information of the calibrated object, the location information of multiple candidate workstations near the calibrated object is determined; Determine the current position information of the robot, and based on the current position information of the robot and the position information of each candidate workstation, determine the first workstation from the multiple candidate workstations; Based on the location information of the first workstation, the robot is controlled to move to the first workstation.

6. The robot control method according to any one of claims 1-5, characterized in that, The robot, after pose correction, performs the target operation on the calibrated object, including: Determine the pose parameters of the robot after pose correction; Based on the pose parameters of the robot after pose correction and the feature data of the calibration object, the motion trajectory of the robot performing the target operation on the calibration object is determined; The robot is controlled to perform target operations on the calibrated object according to the motion trajectory.

7. The robot control method as described in claim 6, characterized in that, The method of controlling the robot to perform the target operation on the calibrated object according to the motion trajectory further includes: Image acquisition is performed on the calibration object to determine the contact state parameters between the robot and the calibration object; Based on the contact state parameters and the preset contact threshold range, it is determined whether the target operation has been executed successfully. If it is determined that the target operation has not been performed properly, the robot's pose is fine-tuned based on the contact state parameters and the preset contact threshold range. After fine-tuning its pose, the robot continues to perform the target operation on the calibrated object.

8. A control device comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the robot control method as described in any one of claims 1 to 7.

9. A robot, characterized in that, include: The robot itself; A mobile chassis is mounted on the robot body, and the robot changes position as the mobile chassis moves. An active mechanism is provided on the robot body, and the robot changes its posture as the active mechanism is adjusted; An end effector, mounted on the robot body or the movable mechanism, is used to perform a target operation; The control device as claimed in claim 8 is used to control the mobile chassis, the movable mechanism, and each of the end effectors.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the robot control method as described in any one of claims 1 to 7.

Images