425 results about "Collaborative robotics" patented technology

The invention relates to the field of robot intelligent control and man-machine collaboration, in particular to a multi-sensing collaborative robot control method, which comprises the following steps: synchronously filtering mechanical, tactile, visual and physiological signals to generate a unified observation frame, and calculating power flow and energy in combination with a joint state to form an execution vector; extracting a topological descriptor by using persistent coherence, and outputting an interaction potential field and a human body intention by using the topological descriptor as a conditional driving diffusion model; then, power density is constructed based on the potential field gradient and intention, joint torque and impedance are generated through entropy regular optimal transmission and Jacobian and microoperator kernel mapping, and an energy Lagrange multiplier is updated in real time; and if the consistency error continuously exceeds a threshold value, estimating a Koopman lifting model on line by using a causal weight, completing model prediction control under the energy, conformal security and topology consistency constraint, outputting an update instruction and performing closed-loop feedback. The method improves the cooperation precision and safety, reduces the energy consumption, and is suitable for a high-dynamic man-machine cooperation scene.

The present invention relates to a collaborative robot system used in an industrial environment where workers collaborate. The collaborative robot system comprises: a collaborative robot body having a multi-joint structure; a control unit for controlling each joint or auxiliary shaft; one or more sensors for detecting the operational state of the robot in real time; and a status diagnosis and response module for diagnosing the state of the robot on the basis of detected data and controlling the operation of the robot accordingly. Specifically, the system is configured to enable the robot to autonomously perform actions such as deceleration, stopping, and recovery in response to various state changes occurring during work, and to perform self-learning and trajectory optimization on the basis of data accumulated through repetitive tasks. Furthermore, the system includes a graphical user interface (GUI) for intuitive user interaction, which is linked to a digital twin-based virtual simulation environment, enabling presetting and modification of work paths. When multiple collaborative robots are operated together, the system enables task synchronization, path collision avoidance, and sharing of status information among the robots, and may be connected to an external control server or a cloud-based control system to allow integrated management of the entire workflow.

The invention discloses a constraint following control method of a two-arm collaborative robot based on differential homeomorphic mapping, and relates to the field of robot control. According to the method, a nominal dynamical model of a robot is established, and a geometric constraint equation is defined according to a cooperative task; establishing global differential homeomorphic mapping by constructing constraint tracking variables and complementary coordinates, and decoupling a system dynamics model into a constraint tracking subsystem and a complementary subsystem; designing a robust adaptive controller fusing sliding mode control and an adaptive law, and estimating and compensating the uncertainty of the system on line; according to the method, the constraint processing complexity is effectively simplified through differential homeomorphic mapping, the constraint tracking precision and robustness of the system under model uncertainty and external interference are remarkably improved, and high-precision and high-stability cooperative task execution of the two-arm robot in the dynamic environment is achieved.

The invention relates to a robot track synchronization control method. According to the technical scheme, efficient collection and over-distance transmission of neural signals are achieved through the quantum entanglement technology, the brain movement intention is analyzed in combination with a high-sensitivity sensor and an intelligent algorithm, an instruction is transmitted to a robot power driving system through a low-delay communication architecture, and real-time synchronization of man-machine tracks is achieved through a two-way feedback system. Meanwhile, the movement flexibility of the robot is improved by adopting a lightweight design, the problems of high delay, low precision, poor interaction experience and the like in traditional man-machine synchronous control are solved, and the method can be widely applied to the fields of exoskeleton robots, industrial collaborative robots, rehabilitation medical robots and the like. The method has the advantages of being low in delay, high in precision, capable of improving interaction experience and wide in application range.

The invention belongs to the technical field of intelligent and robot operation, and discloses a collaborative robot closed-loop operation method based on scene perception and thinking chain reasoning, which comprises the following steps of: firstly, generating structured semantic representation containing confidence by utilizing a visual language model of LoRA efficient fine tuning and fusing multi-view data, and providing semantic understanding for a robot; secondly, utilizing a three-dimensional diffusion model to generate explicit geometric priori under the condition of no real CAD, and correspondingly completing PnP initial pose estimation in combination with 2D-3D; then, carrying out pose optimization by adopting a tracking-refining strategy, and triggering reinitialization based on geometric prior when a residual error exceeds a threshold value; and finally, decomposing a global task by utilizing a thinking chain reasoning module, and realizing'perception-reasoning-execution 'closed-loop control based on visual servo in cooperation with an execution module. The method realizes effective combination of large model reasoning and physical execution, has strong robustness under dynamic disturbance, and is suitable for intelligent manufacturing and man-machine cooperation scenes.

The invention discloses a collaborative robot joint external force estimation method, and relates to the technical field of collaborative robot joint external force estimation, and the method comprises the steps: building a joint kinetic model, and obtaining the basic kinetic parameters of a collaborative robot joint; the angular displacement deviation between the input shaft and the output shaft of the speed reducer is obtained, and the compensated torsional angle difference is calculated according to the angular displacement deviation; a joint variable stiffness model is established, multiple sets of calibration data are obtained through experiments, and parameters in the joint variable stiffness model are identified according to the multiple sets of calibration data; based on the basic dynamic model and the joint variable stiffness model after parameter identification, a nonlinear disturbance observer is constructed in combination with introduced auxiliary variables; and system disturbance is observed and compensated through a nonlinear disturbance observer, so that an external torque estimated value acting on the tail end of the joint is calculated and output in real time. According to the method, high-precision and real-time estimation of the external torque can be effectively considered, and meanwhile, the system hardware cost and the structure complexity are greatly reduced.

The invention belongs to the technical field of robots, and discloses a collaborative robot intelligent feeding and discharging system, which comprises a station structure sensing module for collecting station structure information of a station where a collaborative robot is located when the collaborative robot executes feeding and discharging tasks, and performing structured coding on the station structure information to generate a station structure constraint matrix; the part task decomposition module is used for constructing a loading and unloading task queue of parts on the basis of the station structure constraint matrix, and converting the loading and unloading task queue into an action instruction set which can be executed by the collaborative robot in combination with a preset station rhythm requirement; the path deduction avoidance module projects the action instruction set to a joint space of the collaborative robot, and deduces and generates a candidate path set based on a station constraint path mapping mechanism; performing optimization selection on the candidate paths by adopting dual-target scheduling of energy consumption and process rhythm, and selecting the candidate path with the optimal performance as an execution path of the robot; and the safety of feeding and discharging operation of the collaborative robot is improved.

The invention discloses a cooperative robot joint adaptive control system and method based on multi-sensor fusion, and relates to the technical field of robot joint control. According to the invention, through an improved extended Kalman filtering and deep neural network compensation mechanism integrated by the multi-source data fusion unit, sensor noise is effectively suppressed, and multi-source data conflicts are solved; the sensor reliability evaluation unit is based on a dynamic weight distribution mechanism of Bayesian reasoning, and can reduce the fusion weight of the sensor in real time when the sensor is detected to be abnormal, and improve the contribution degree of reliable sensor data. The adaptive control unit is combined with the self-learning optimization unit to form a closed-loop optimization architecture, so that the performance limitation caused by fixed traditional PID parameters is thoroughly solved; through adaptive weighted fusion of multi-source sensor data, the joint state estimation precision is improved; and a deep neural network residual error compensation mechanism is utilized to reduce a torque control steady-state error.

Robot calibration is crucial in multi-robot cooperative systems where the inaccuracy of robots can add up and cause large errors in the final trajectory of handled parts or process tools. In this work, a two-step calibration approach is proposed based on artificial neural networks (ANNs) and definition of compensated pose for a master-slave cooperative robot system. Measuring the pose of master and slave robots at different locations in their shared workspace is required to create pairs of joint angles and output pose errors as training data. The generated data is used to train two ANN models for compensating the master-slave relative error and the master robot errors. The master-slave relative error is corrected by introducing a compensated pose for the slave robot with respect to the master robot. A neural network is then trained to predict the error parameters of the compensated pose for the joint angles of both robots as the input. The master robot is then corrected individually using another ANN model to address the absolute accuracy of the cooperative system.Measurements and simulations have been performed on a dual-robot cooperative system before and after geometric calibration. The process of cross validation is carried out to find the best network architecture for the optimal performance in correcting the robots'errors. It has been shown that even after pre-existing model-based calibration of each robot, both the absolute accuracy of the master robot and the relative tracking accuracy can be further improved by the proposed implementation of ANN calibration.

The invention discloses a full-automatic verification system of a temperature sensor, and relates to the technical field of temperature sensor verification, in the system, a main control computer is used for reading a verification scheme, controlling a collaborative robot to install a detected temperature sensor to a tool, and controlling the collaborative robot to transfer the tool provided with the detected temperature sensor into a thermostatic bath; the thermostatic bath provides a thermostatic environment through bath liquid, and the temperature of the bath liquid is monitored in real time through a temperature standard device; the acquisition system is used for acquiring an output signal of the detected temperature sensor transferred into the thermostatic bath and converting the output signal into a temperature value under the control of the main control computer; the main control computer is further used for comparing the temperature value measured by the detected temperature sensor with the standard temperature value measured by the temperature standard device and determining whether the detected temperature sensor is qualified or not according to the comparison result. According to the invention, the verification efficiency can be effectively improved, and the high-efficiency verification requirement of a large batch of temperature sensors can be met.

The invention relates to the technical field of CTP-S battery module assembly, in particular to an automatic module boxing system and method for a CTP-S battery pack. Comprising a line body integration unit, a code scanning mechanism, a material taking mechanism, a carrying truss, a PACK jacking positioning unit, a collaborative robot unit and a control system. The control system is in communication connection with the carrying truss, the material taking mechanism, the collaborative robot unit, the line body integration unit, the code scanning mechanism and the PACK jacking positioning unit. The control system obtains position compensation data generated after a plurality of preset positions in the battery pack box body are subjected to visual positioning by a visual camera of the collaborative robot unit; the control system controls the carrying truss and the material taking mechanism to act cooperatively according to the position compensation data, grabbing and placing operation is executed through the material taking mechanism, and grabbing of the module from the line body integration unit and box entering of the battery pack box on the carrying trolley are achieved. And the effects of high precision, no damage, high efficiency, wide compatibility and full-automatic assembly of the heavy CTP-S battery module are achieved.

A system for human-robot collaboration is provided herein. The system includes a robotic device having at least one mechanism for moving at least a part of the robot, one or more sensors configured to capture environmental data, a processor in communication with the robotic device and the one or more sensors, and a memory in communication with the processor. The memory has instructions that, when executed, cause the processor to capture an image of a scene, detect objects, generate manipulation options, receive a prompt indicating an overall objective, generate a list of task steps, generate a task graph, determine a probability for each task step, determine a predicted next intention step, and execute a manipulation option corresponding to the next intention step via the robotic device.

The invention discloses a cooperative control method and system for a man-machine cooperative assembly robot based on digital twinning. According to the method, firstly, a digital twinborn simulation environment is constructed in a Unity engine, and mapping of a physical cooperation assembly scene and a virtual scene is achieved; personnel actions and assembled workpiece states are collected in real time through a multi-modal sensing technology, and virtual-real mapping is introduced to realize intention recognition. And then based on a reinforcement learning algorithm, performing path planning on the collaborative robot in a digital twin environment to generate an optimal collaborative path sequence. And finally, mapping the planned path to a real robot control instruction through coordinate transformation and an inverse kinematics algorithm, and dynamically optimizing a motion track by adopting an online self-adaptive strategy. Through the combination of digital twinning and reinforcement learning, the intelligent and flexible scheduling capability of a man-machine cooperation assembly system is improved, the rapid adaptability and assembly precision of the system to unstructured changes are enhanced, and the problems that task programming is tedious and the adaptability is poor in a traditional method are solved.

The invention relates to the technical field of collaborative robot welding, in particular to a collaborative robot welding system suitable for ship narrow cabin moving operation, which comprises a ship bottom plate, the ship bottom plate comprises an outer bottom plate, an inner bottom plate, a rib plate and a girder, the outer bottom plate, the inner bottom plate, the rib plate and the girder form a cabin, and a plurality of pipelines are arranged at the top of the cabin. A movable U-shaped magnetic attraction rail is arranged at the center of the top of the ship bottom plate, a six-degree-of-freedom small collaborative robot is arranged at the top of the movable U-shaped magnetic attraction rail, and an auxiliary rail is arranged between every two adjacent cabins. The robot system is compact in structure, the technical problems that an existing welding robot system is inconvenient to move, poor in obstacle avoidance capacity, insufficient in welding accessibility, low in path planning efficiency and the like in narrow cabin environments such as ship cubicles are solved, welding blind areas are effectively reduced, efficient and stable movement and welding in the dense obstacle environment are achieved, and the welding efficiency is improved. And the working efficiency and the quality consistency are obviously improved.

The invention provides a man-machine cooperation assembly track generation method, device and equipment based on a digital human, and relates to the technical field of man-machine cooperation, and the method comprises the steps: constructing a digital human model, a cooperation robot model and an assembly environment based on musculoskeletal on a target simulation platform, defining the attributes of each model, and forming a man-machine cooperation assembly simulation platform; taking the man-machine cooperation assembly simulation platform as an interaction environment, training a digital human control strategy network based on a deep reinforcement learning algorithm, and generating a digital human assembly track in an assembly process; introducing the trained digital human control strategy network into a man-machine collaborative assembly simulation platform, taking a dynamic assembly environment as a training environment of a collaborative robot, training the obstacle avoidance capability of the collaborative robot to avoid dynamic actions of a digital human through a deep reinforcement learning algorithm, generating a robot obstacle avoidance strategy network, and performing robot obstacle avoidance simulation on the robot. And outputting a robot assembly track based on the robot obstacle avoidance strategy network. By means of the method, man-machine safety cooperation assembly can be achieved.

The invention relates to the technical field of robot control, in particular to a control method and system for a mechanical arm of a collaborative robot. The method comprises the following steps: collecting multi-modal observation data such as vision, force and moment, touch, joint state and the like, and outputting an operation intention, a task stage and an uncertainty index after time sequence alignment and feature fusion; calculating security constraints according to the information, constructing a feasible region, adaptively updating impedance parameters, generating a control instruction, and issuing and executing the control instruction after constraint projection; meanwhile, an online self-calibration mechanism triggered by a residual error is introduced, and parameters such as sensing zero offset, friction and TCP are updated. According to the method, the flexibility, the operation precision and the safety of man-machine cooperation can be considered, the risks of impact, collision and clamping stagnation are reduced, and the long-term operation stability of the mechanical arm is improved.

This invention discloses an airport FOD (Foreign Object Debris) detection and removal system and method based on multi-source sensing fusion. The system includes a mobile transport chassis, a multi-source heterogeneous sensing unit, a six-degree-of-freedom collaborative robotic arm, a composite cleaning end effector, and an edge computing platform. During operation, environmental data is first collected using LiDAR, millimeter-wave radar, and a binocular camera. Spatiotemporal fusion and state estimation algorithms are used to achieve all-weather, high-precision positioning and attribute calculation of FOD. The composite cleaning end effector integrates a high-negative-pressure suction port, a ring-shaped electromagnetic adsorption array, and a flexible mechanical claw. Subsequently, the system adaptively switches between magnetic suction, suction pickup, or gripping modes based on the material, volume, and shape characteristics of the FOD, and combines a visual closed-loop feedback mechanism to automatically upgrade and verify the cleaning strategy. This invention effectively solves the problems of poor perception robustness under complex weather conditions and insufficient adaptability of single cleaning methods, significantly improving the intelligence level and operational efficiency of airport pavement foreign object removal.

To provide a control device, a bending processing system, a robot control method, and a robot control program that enable use of a cooperative robot in a reduced space while securing user safety.SOLUTION: A control device includes a control part capable of controlling a multi-joint cooperative robot that conveys a workpiece with respect to a carrying target. The control part is configured to cause the multi-joint cooperative robot to operate in prior to the workpiece such that at least a part of the multi-joint cooperative robot is located in front of the workpiece in a travel direction, in at least one of carrying-out operation of carrying out the workpiece from the carrying target and carrying-in operation of carrying in the workpiece toward the carrying target.SELECTED DRAWING: Figure 7

The present invention provides a collaborative robot that allows for easy attachment and detachment of the fifth-axis motor and torque converter from the upper arm. [Solution] The output shaft 512 of the fifth-axis motor 51, which rotates the support arm 16 of the collaborative robot 1 around the fifth axis A5, is positioned along the fourth axis A4. Inside the upper arm 15 of the collaborative robot 1, the fifth-axis motor 51 and a torque converter 53 that converts the torque of the output shaft 512 into torque around the fifth axis A5 are housed. The upper arm 15 is a cylindrical housing and has an arm body 151 with an opening 2 for mounting the fifth-axis motor 51 and the torque converter 53, and a cover 152 that covers the opening 2 and is attached to the arm body 151. When viewed from a direction along the fifth axis A5, the fifth-axis motor 51 and the torque converter 53 are housed in the internal region within the opening edge 20 of the opening 2.

The invention provides a collaborative robot end safety protection and feedback system based on bimodal touch, and the system comprises a bimodal sensing unit which is disposed at an end executor of a collaborative robot and is configured to synchronously collect physical signals when touching an external object, and the physical signals comprise a contact pressure signal and a contact transient acoustic signal; the processing main control unit is in signal connection with the bimodal sensing unit and is configured to receive the physical signals and perform data fusion on the physical signals so as to identify a touch type; and the multi-stage feedback execution unit is in signal connection with the processing main control unit and comprises at least one tactile feedback device worn on an operator of the collaborative robot, and the tactile feedback device is configured to output a corresponding tactile feedback signal to the operator of the collaborative robot based on the touch type. According to the method, accurate distinguishing can be achieved under various working conditions such as light touch, rapid impact and continuous extrusion, and real-time feedback of safety grading is provided for an operator and a robot control system.

The utility model discloses a robot automatic welding trolley which comprises a walking body, and a wire feeder and a collaborative robot are arranged on the walking body. The walking body comprises a lower bottom plate, four stand columns are fixed to the lower bottom plate, a surrounding assembly is arranged between every two stand columns, an upper bottom plate is fixed to the upper sides of the surrounding assemblies and the stand columns, and the wire feeder and the collaborative robot are fixed to the upper bottom plate. The wire feeder is fixed through a rapid fixing assembly; the surrounding assembly comprises a welding machine front door plate, a back sealing plate, a fixed door plate and a movable door plate structure, the welding machine front door plate and the back sealing plate are oppositely arranged, and the fixed door plate and the movable door plate structure are oppositely arranged; the movable door plate structure comprises an upper side plate and a lower side plate which are fixed between the two stand columns, and a first door plate and a second door plate are installed between the upper side plate and the lower side plate through hinges. The device has the advantages of being convenient to maintain and compact in structure.

The utility model discloses a paint surface polishing tool installed on a collaborative robot, which comprises a device body, the device body comprises a driving device, guide rods, a guide device and a polishing device, a group of guide rods are symmetrically installed at the bottom of the driving device, the polishing device is installed at the bottom of the group of guide rods, and the guide device is sleeved on the group of guide rods; the polishing device comprises a base block and a set of swing discs, the swing discs are of a semicircular structure, the base block is located between the set of swing discs, hinges are arranged between the base block and the swing discs, swing shaft lugs are arranged at the tops of the swing discs, connecting shafts are installed in the swing shaft lugs through rotating shafts, and the other ends of the connecting shafts are connected with the guiding device. Burr buckles are arranged at the bottoms of the swing discs, and sponge abrasive paper discs are installed at the bottoms of the burr buckles. According to the device, the paint surface polishing efficiency can be improved, the polishing range can be adjusted, accordingly, abrasive paper is driven to be in a folded state, and narrow areas such as A columns can be polished.

1.The name of the design product: the wrist of a collaborative robot. 2.The use of the design product: the collaborative robot is used for carrying and stacking in the industrial fields of automobile parts, 3C electronics, lithium batteries, photovoltaics, etc., and the wrist is used for end dragging demonstration of the collaborative robot. 3.The design points of the design product: the combination of shape and pattern. 4.The picture or photo that best indicates the design points: perspective view 1. 5.The rear view has been expressed in perspective view 2, and the rear view is omitted. 6.Other circumstances that need to be explained: the part shown in blue is the part to be protected, and the appearance design to be protected does not include color.

To provide a control unit capable of charging a portable teaching device while using an industrial robot and its control device.SOLUTION: The control unit 1 includes the control device 10 that controls the industrial robot 30, which is a collaborative robot, and the portable teaching device 20 that teaches the operation of the industrial robot 30 through wireless communication, and the control device 10 includes the power transmission coil 12 disposed inside the control device 10 so as to face the 11a of the wall portion of the housing 11 of the control device 10. The teaching device 20 has a power reception coil 22 magnetically coupled to the power transmission coil 12 and a storage battery 23 for storing power generated by the power reception coil 22 inside the teaching device 20, and the control device 10 and the teaching device 20 have positioning mechanisms 14, 24 for detachably positioning the power reception coil 22 at a position opposed to the power transmission coil 12.SELECTED DRAWING: Figure 2

The invention discloses a joint control method and device of a robot and a nonvolatile storage medium. The method comprises the steps that the environment temperature and the current temperature of a target joint of the robot are collected; inputting the current temperature and the environment temperature into a preset joint loss power model of the robot, and determining the maximum joint loss power of the robot; determining the maximum output power corresponding to the target joint based on the maximum joint loss power; and based on the maximum output power, the target joint output power is controlled. The technical problem that due to the fact that temperature rise of part of joints is too large, the collaborative robot may be directly suspended or shut down, and risks are brought to production operation of a terminal user is solved.

The invention provides a non-contact on-line measuring device and method for excavator structural members, a double-scanning system cooperation mode is adopted, a tracker and a ball cage scanner are respectively used on two sides of a detection device, the ball cage scanners are installed on a cooperative robot to execute automatic scanning actions, and meanwhile, the robot is driven by the robot to move. The tracker and the robot are both installed on the linear guide rail, displacement operation can be carried out, the scanning and collecting range of the system is expanded, and therefore full scanning work of the large structural part is completed. The two scanning systems scan and collect the structural member from the left side and the right side at the same time, then data are spliced together, a three-dimensional point cloud model of the structural member is obtained, size information is analyzed and extracted, a detection report is generated, communication with a workshop data management system is carried out, and measurement data are integrated and applied.

Disclosed example methods to generate a robotic welding program involve: generating a robotic welding program to weld a part using a collaborative robot welding system by manually manipulating the collaborative robot welding system to generate commands and robotic positioning information; automatically converting, using a processor, a first plurality of instructions of the robotic welding program for execution on the collaborative robot welding system to a second plurality of instructions to execute the robotic welding program on a non-collaborative type of robotic welding system; and performing the robotic welding program using the non-collaborative type of robotic welding system to weld the part using the second plurality of instructions.

The invention relates to the technical field of magnetic element manufacturing, in particular to an automatic spot spraying selective welding system and method for magnetic element customized parts, the system comprises a feeding conveying belt, a collaborative robot, a scaling powder spraying device, a selective wave soldering device and a discharging device, and the method comprises the steps that S1, the feeding conveying belt conveys products to a feeding position; s2, the collaborative robot moves to a feeding position to clamp a product, then the product is moved to the position above a quantitative injection valve, and scaling powder is sprayed to a welding point position; s3, a camera collects tin wave images in real time and transmits the tin wave images to a controller, and the controller detects that tin waves are qualified; s4, the collaborative robot moves the product to the position above the tin wave to preheat the scaling powder, and then the welding point position is aligned with the nozzle and makes contact with the tin wave to complete welding; and S5, the product is moved to a discharging positioning tool. The problem that traditional fixed station equipment is difficult to adapt to the production requirements of multi-variety and small-batch customized parts is solved, and the stability of tin waves is monitored in real time through machine vision in the welding process.

The invention relates to the technical field of logistics sorting, in particular to a multi-arm collaborative robot for efficiently separating small parcels. Comprising a robot trunk, a mechanical arm assembly, a rotary driving module and a flexible end effector. The mechanical arm assembly and the rotary driving module are arranged on the robot trunk; the mechanical arm assembly comprises a first mechanical arm and a second mechanical arm, and the first mechanical arm and the second mechanical arm are oppositely arranged on the robot trunk; the mechanical arm comprises an upper arm section, a lower arm section and a flexible end effector. And through a double-arm reciprocating cooperation or four-arm parallel operation mode, the single parcel processing period is greatly shortened, and compared with traditional manual separation and single-arm robot separation, leap-type improvement of the operation efficiency is achieved, and the large-scale sorting requirement is met.

The utility model relates to the technical field of labeling devices, in particular to automatic moving labeling equipment used in a steel coil warehouse, which comprises a top frame, a labeling mechanism, a label printing mechanism and two travelling mechanisms, the labeling mechanism and the label printing mechanism are both arranged on the top frame, and the two travelling mechanisms are arranged on two sides below the top frame. And the labeling mechanism comprises a moving assembly, a collaborative robot and a labeling assembly, the moving assembly is arranged on the top frame, the collaborative robot is arranged on the moving assembly, and the labeling assembly is arranged at the output end of the collaborative robot. The whole equipment is driven by the walking mechanism to move to the position of a steel coil, the label printer prints a label, the collaborative robot takes the label and adheres the label to the circumference of the steel coil, accurate and timely adhesion of the label can be achieved, and the whole equipment can span two rows of saddle libraries and can move between the two rows of saddle libraries. And in cooperation with reciprocating movement of the collaborative robot relative to the top frame, the labeling efficiency is improved.