Robot off-line teaching programming method, device and equipment and storage medium

Abstract

The application discloses a robot offline teaching programming method and device, equipment and storage medium, relates to the technical field of robot programming, and the method comprises the steps that three-dimensional point cloud data corresponding to a robot in a work site environment is acquired, and a three-dimensional model is constructed according to the three-dimensional point cloud data; in response to an interactive instruction input by an operator to the three-dimensional model, a work path of the robot is generated according to the interactive instruction; the robot is subjected to collision detection according to the work path and the three-dimensional model, and the work path is superimposed and displayed in the work site environment after the collision detection passes, so that a to-be-verified environment is obtained; if a confirmation instruction of the operator for the to-be-verified environment is received, the interactive instruction is converted into an offline teaching program executable by the robot. The above-mentioned method of the application avoids the problem that a lot of time is still consumed for on-site correction and repeated debugging after the program is deployed, and finally realizes efficient and accurate robot offline teaching programming without relying on CAD numerical models and programming experts.

Description

Technical Field

[0001] This application relates to the field of robot programming technology, and in particular to a robot offline teaching programming method, apparatus, device and storage medium. Background Technology

[0002] Currently, the mainstream programming method for industrial robots is still traditional teach-in programming, where an operator holds a teach pendant and controls the robot to move along the desired trajectory by teaching it point by point, while simultaneously recording the movement trajectory and generating a control program. In this method, the operator must manually guide the robot through each path point sequentially. For complex curved surfaces, this often requires teaching hundreds or even thousands of points, which is not only extremely time-consuming, but the smoothness and accuracy of the trajectory also highly dependent on the operator's skill and experience. To meet product changeover requirements, repeated iterative processes of teaching, debugging, and modification are necessary on-site, resulting in long equipment downtime and slow progress in production line flexibility upgrades.

[0003] To improve programming efficiency, offline programming technology has emerged. Existing offline programming methods typically rely on workpiece CAD models, generating control programs after planning robot paths in a computer environment. However, in practical applications, many field devices (such as outdated production lines and purchased workpieces) lack usable CAD models, and remodeling requires specialized 3D design capabilities and sufficient original drawings, which is difficult for general process engineers to accomplish. Even with CAD models, differences between the CAD model and the actual field environment (such as workpiece clamping deviations and equipment position offsets) mean that offline-generated trajectories still require significant time for on-site calibration and repeated debugging before deployment, hindering effective improvements in programming efficiency.

[0004] Therefore, how to achieve efficient and accurate offline teaching programming of robots without relying on CAD models and programming experts is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] The main purpose of this application is to provide a method, apparatus, device and storage medium for offline teaching programming of robots, aiming to solve the technical problem of how to achieve efficient and accurate offline teaching programming of robots without relying on CAD models and programming experts.

[0006] To achieve the above objectives, this application provides a robot offline teaching programming method, the method comprising the following steps: Acquire the 3D point cloud data corresponding to the robot in the work site environment, and construct a 3D model based on the 3D point cloud data; In response to the interactive instructions input by the operator to the 3D model, the robot's work path is generated according to the interactive instructions; The robot is subjected to collision detection based on the work path and the 3D model. After the collision detection is passed, the work path is superimposed on the work site environment to obtain the environment to be verified. If the operator receives a confirmation instruction for the environment to be verified, the interactive instruction is converted into an offline teaching program that the robot can execute.

[0007] In one embodiment, the step of acquiring the 3D point cloud data corresponding to the robot in the work site environment and constructing a 3D model based on the 3D point cloud data includes: The robot's operating environment is scanned from multiple stations to obtain corresponding 3D point cloud data; The three-dimensional point cloud data is spliced ​​from multiple stations, noise is filtered out, and redundant points are reduced to obtain preprocessed three-dimensional point cloud data. A 3D point cloud model is generated based on the preprocessed 3D point cloud data, and the 3D point cloud model is reverse-engineered to generate a 3D model including the robot, the robot's workpiece, and the robot's peripheral equipment.

[0008] In one embodiment, the step of generating the robot's work path based on the interaction instructions includes: The operation trajectory and operation posture input by the operator are determined based on the interactive instructions. The normal of the working posture is adjusted according to the workpiece surface curvature information of the three-dimensional model to obtain the target working posture of the robot's end effector. The path inflection points in the work trajectory are smoothed, and the robot's work path is generated based on the target work posture and the work trajectory after the smoothing process.

[0009] In one embodiment, the step of performing collision detection on the robot based on the work path and the 3D model includes: Obtain the kinematic model of the robot, and perform reachability analysis on the robot based on the operation path and the kinematic model to obtain the reachable space of the robot; The robot performs self-collision detection and environmental collision detection based on the reachable space and the three-dimensional model.

[0010] In one embodiment, the step of overlaying the work path onto the work site environment after the collision detection is passed to obtain the environment to be verified includes: After the collision detection is passed, a real-time image of the work site environment is acquired through an augmented reality display device; A virtual overlay image is generated based on the 3D model and the work path, and the virtual overlay image is superimposed on the real-time image to obtain the environment to be verified.

[0011] In one embodiment, the step of converting the interactive instructions into an offline teaching program executable by the robot includes: The corresponding post-processor is determined based on the robot's device type; The post-processor converts the interactive instructions into control code format corresponding to the device type, thereby obtaining an offline teaching program that the robot can execute.

[0012] In one embodiment, after the step of converting the interactive instructions into an offline teaching program executable by the robot, the method further includes: The robot is simulated in a virtual environment according to the offline teaching program to obtain the simulation results, which include trajectory reachability verification results, joint range of motion verification results, and cycle time verification results. If the simulation results meet the preset operation conditions, the offline teaching program is sent to the robot for execution via the communication interface.

[0013] Furthermore, to achieve the above objectives, this application also proposes a robot offline teaching and programming device, which includes: The model building module is used to acquire the 3D point cloud data corresponding to the robot in the working environment, and to build a 3D model based on the 3D point cloud data; The path generation module is used to generate the robot's working path in response to the interactive instructions input by the operator to the 3D model; The collision detection module is used to perform collision detection on the robot based on the work path and the 3D model, and after the collision detection is passed, to overlay and display the work path on the work site environment to obtain the environment to be verified. The instruction conversion module is used to convert the interactive instruction into an offline teaching program that the robot can execute if it receives a confirmation instruction from the operator for the environment to be verified.

[0014] Furthermore, to achieve the above objectives, this application also proposes a robot offline teaching programming device, the device comprising: a memory, a processor, and a robot offline teaching programming program stored in the memory and executable on the processor, the robot offline teaching programming program being configured to implement the steps of the robot offline teaching programming method as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, storing a robot offline teaching programming program, which, when executed by a processor, implements the steps of the robot offline teaching programming method described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a robot offline teaching programming program. When the robot offline teaching programming program is executed by a processor, it implements the steps of the robot offline teaching programming method described above.

[0017] One or more technical solutions proposed in this application have at least the following technical effects: The robot offline teaching programming method of this application includes: acquiring three-dimensional point cloud data corresponding to the robot in the work site environment, and constructing a three-dimensional model based on the three-dimensional point cloud data; responding to the interactive command input by the operator to the three-dimensional model, generating the robot's work path according to the interactive command; performing collision detection on the robot based on the work path and the three-dimensional model, and superimposing the work path on the work site environment after the collision detection is passed to obtain the environment to be verified; if a confirmation command from the operator for the environment to be verified is received, converting the interactive command into an offline teaching program executable by the robot.

[0018] This application acquires 3D point cloud data of the work site environment and constructs a 3D model, enabling the generation of a digital model for offline programming based on actual scan data, even without a workpiece CAD model. Responding to operator input commands on the 3D model, a robot's work path is generated and then overlaid on the work site environment. Collision detection based on the work path and 3D model is introduced before AR verification, pre-screening paths with collision risks in the virtual environment and reducing safety hazards and repeated debugging during subsequent on-site verification. The sequential combination of AR verification and collision detection effectively reduces the discrepancy between the offline planned path and the actual on-site working conditions, making the verified offline teaching program more closely resemble on-site execution conditions. This avoids the need for significant time-consuming on-site calibration and repeated debugging after program deployment, ultimately achieving efficient and accurate offline robot teaching programming without relying on CAD models or programming experts. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the first embodiment of the robot offline teaching programming method of this application; Figure 2 This is a flowchart illustrating the second embodiment of the robot offline teaching programming method of this application; Figure 3 This is a flowchart illustrating the third embodiment of the robot offline teaching programming method of this application; Figure 4 This is a structural block diagram of the first embodiment of the robot offline teaching and programming device of this application; Figure 5 This is a schematic diagram of the structure of the robot offline teaching and programming device of this application.

[0022] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0024] This application provides an offline teaching and programming method for robots, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the robot offline teaching programming method of this application.

[0025] In this embodiment, the robot offline teaching programming method includes the following steps: Step S10: Obtain the 3D point cloud data corresponding to the robot in the work site environment, and construct a 3D model based on the 3D point cloud data.

[0026] It should be noted that the executing entity of this application embodiment can be a robot offline teaching and programming device capable of executing the robot offline teaching and programming method of this application, and this embodiment does not limit this. The following uses a robot offline teaching and programming device (hereinafter referred to as programming device) as an example to describe this embodiment and the following embodiments.

[0027] It should be understood that the aforementioned robot can be a multi-jointed industrial robot used in industrial manufacturing scenarios, such as a six-axis serial industrial robot or a collaborative robot. The aforementioned 3D point cloud data can be a set of discrete points recording the spatial positions of the surface of the work site environment in 3D coordinate form. The aforementioned work site environment can include the complete physical work space comprising the robot body, the workpiece to be processed, the worktable, fixtures, conveyor lines, and other surrounding fixed equipment. The aforementioned 3D model can be a digital twin model with real spatial coordinates and geometric dimensions, reflecting the 3D geometric shape and relative spatial relationships of various objects in the work site environment.

[0028] In practice, the programming device can acquire the original 3D point cloud data corresponding to the work site environment from a 3D laser scanner, then perform preprocessing operations on the 3D point cloud data, and perform reverse modeling operations based on the preprocessed 3D point cloud model. Through 3D reconstruction algorithms, the discrete point cloud data is converted into continuous geometric surfaces and solid models, generating a complete 3D model including the robot, workpiece, and peripheral equipment.

[0029] Step S20: In response to the interactive instructions input by the operator to the 3D model, generate the robot's work path according to the interactive instructions.

[0030] It should be noted that the aforementioned interactive commands can be control signals generated when operators manipulate the 3D model through a graphical user interface, used to express the operator's intention to plan tasks on the surface of the 3D model. For example, interactive commands may include trajectory lines drawn by dragging with a mouse, key path points determined by clicking on the screen, or free curve paths input by direct drawing. The aforementioned work path can be a continuous spatial trajectory used to guide the movement of the robot's end effector, containing a series of spatial position points and corresponding posture information that the robot's end effector needs to pass through during the operation. The aforementioned end effector can be a tool installed at the end of the robot to directly perform the work task, such as a spray gun in painting operations, a welding torch in welding operations, a grinding head in grinding operations, or a gripper in assembly operations.

[0031] It should be understood that after the programming device completes the construction of the 3D model, it will present a graphical interface to the operator. This graphical interface allows the operator to perform task planning operations directly on the surface of the 3D model. Through task planning operations, interactive instructions input by the operator to the 3D model can be generated.

[0032] Step S30: Perform collision detection on the robot based on the work path and the 3D model, and after the collision detection is passed, overlay the work path onto the work site environment to obtain the environment to be verified.

[0033] It should be noted that the aforementioned environment to be verified can be a visual scene in which the programmed device presents the planned work path in a virtual overlay manner on the work site environment, so that operators can intuitively observe and evaluate the performance and rationality of the work path in the actual space.

[0034] In practical implementation, the programming device can perform self-collision detection and environmental collision detection on the robot. Self-collision detection is used to determine whether the links of the robot will collide with each other during movement, while environmental collision detection is used to determine whether the robot body and end effector will spatially interfere with the workpiece or surrounding equipment during movement. If the collision detection passes, that is, no collision or interference is detected, the work path can be displayed as a virtual image overlaid on the real image of the work site environment to obtain the environment to be verified.

[0035] Step S40: If a confirmation instruction from the operator for the environment to be verified is received, the interactive instruction is converted into an offline teaching program that the robot can execute.

[0036] It should be noted that the aforementioned confirmation command can be an affirmative operation signal issued by the operator through a graphical interface or AR display device after observing the environment to be verified. This signal indicates that the operator confirms that the current work path meets the process requirements in terms of spatial location, accessibility, and safety, and that subsequent program generation can proceed. For example, the operator can click the confirmation button in the AR preview verification interface or trigger the confirmation command through gesture operation. The aforementioned offline teaching program can be a computer-readable code file that can be directly recognized and executed by the target robot controller. The offline teaching program can contain all motion commands, speed parameters, I / O control commands, and process parameters required for the robot to complete the task.

[0037] In this implementation, the embodiment acquires 3D point cloud data of the work site environment and constructs a 3D model, enabling the generation of a digital model for offline programming based on actual scan data, even without a workpiece CAD model. The robot's work path is generated in response to the operator's interactive commands input to the 3D model, and then overlaid and displayed on the work site environment. Collision detection based on the work path and 3D model is introduced before AR verification, pre-screening paths with collision risks in the virtual environment and reducing safety hazards and repeated debugging during subsequent on-site verification. The sequential combination of AR verification and collision detection effectively reduces the difference between the offline planned path and the actual on-site working conditions, making the verified offline teaching program more closely resemble the on-site execution conditions. This avoids the need for significant time for on-site calibration and repeated debugging after program deployment, ultimately achieving efficient and accurate offline robot teaching programming without relying on CAD models or programming experts.

[0038] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to the above embodiment can be referred to the above description, and will not be repeated hereafter. On this basis, a second embodiment of the robot offline teaching programming method of this application is proposed, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the robot offline teaching programming method of this application.

[0039] Furthermore, in order to reduce path planning errors caused by incomplete models or geometric deviations, step S10 may include: Step S101: Perform multi-station scanning of the robot's work environment to obtain the corresponding 3D point cloud data.

[0040] It should be understood that multi-station scanning refers to the operation of setting up 3D laser scanners from multiple different spatial positions and angles within the same work scene to collect data. Because a single scanning station has field-of-view obstructions and blind spots, it is impossible to acquire surface point cloud data of all objects in the complete scene at once. By setting up scanners at different positions and angles to perform multiple scans, and then stitching and fusing the data acquired from each scan in subsequent steps, complete 3D point cloud data covering the entire work scene can be obtained. The aforementioned stations can be the specific spatial locations where the 3D laser scanner is set up during a single data acquisition at the work site. Each station corresponds to a scanning point with specific 3D coordinates and scanning direction.

[0041] In practice, the programming device controls a 3D laser scanner to perform scanning operations on the work site environment from various stations according to a preset station plan. At each station, the 3D laser scanner emits a laser beam into the surrounding space in a non-contact manner and receives reflected signals, acquiring the spatial 3D coordinate data of the robot, workpiece, and surrounding equipment surfaces visible from that station's perspective, forming the original point cloud data for that station. The programming device controls the 3D laser scanner to sequentially traverse all preset stations, performing comprehensive data acquisition of the work space, and finally summarizing to obtain complete original 3D point cloud data covering the entire work site environment.

[0042] Step S102: Perform multi-station stitching, noise filtering, and redundant point simplification on the three-dimensional point cloud data to obtain preprocessed three-dimensional point cloud data.

[0043] In practical implementation, multi-station stitching involves combining single-station point cloud data collected from multiple different stations. By identifying common feature points or target points in overlapping areas between different stations, the individual single-station point clouds are transformed into the same global coordinate system, thus fusing them into a complete and unified point cloud scene. Noise filtering involves using filtering algorithms to identify and remove outliers and invalid points in the 3D point cloud data caused by environmental interference, equipment errors, or abnormal reflections from the surface of the measured object. Examples include stray points caused by dust in the air, light reflection, or scanning edge effects. Redundant point simplification involves reducing the number of excessively dense redundant points in the point cloud data through sampling algorithms while maintaining the geometric accuracy of the 3D point cloud model, thereby reducing data storage and subsequent processing computational load.

[0044] Step S103: Generate a 3D point cloud model based on the preprocessed 3D point cloud data, and perform reverse modeling on the 3D point cloud model to generate a 3D model including the robot, the robot's workpiece, and the robot's peripheral equipment.

[0045] It should be noted that the aforementioned 3D point cloud model can be a discrete point cloud dataset that fully represents the surface geometry of the work site environment. Each point in the 3D point cloud model has 3D spatial coordinates in a unified global coordinate system, and noise and redundant points have been filtered out or simplified, accurately reflecting the surface morphology and spatial position of objects such as robots, workpieces, and peripheral equipment. The aforementioned workpieces can be objects directly processed during robot operations, such as bumpers in a painting scenario, steel structural components in a welding scenario, castings in a grinding scenario, or parts to be assembled in an assembly scenario. The aforementioned peripheral equipment can be other functional equipment or facilities in the work site environment besides robots and workpieces, such as workbenches, conveyor lines, fixtures, positioners, control cabinets, safety fences, etc. The aforementioned reverse modeling can be the process of reconstructing the 3D geometric model of an object based on the 3D point cloud model, that is, starting from discrete point cloud data, generating a continuous 3D digital model with geometric topological relationships through surface reconstruction algorithms or manual-assisted modeling methods.

[0046] In this implementation, the robot's working environment is scanned from multiple stations, enabling the acquisition of spatial geometric information from different angles and avoiding data loss due to occlusion or limited viewpoints in a single scan. Then, the 3D point cloud data undergoes multi-station stitching, noise filtering, and redundant point reduction, unifying the point clouds from different stations into the same coordinate system and eliminating interfering data, thus improving the completeness and accuracy of the point cloud data. Further, reverse modeling is performed based on the preprocessed point cloud data to generate a 3D model containing the robot, its workpiece, and its peripheral equipment, ensuring the 3D model has complete geometric dimensions and relative positional relationships. Through the sequential connection of multi-station scanning, data preprocessing, and reverse modeling, a 3D model consistent with the actual site can be directly constructed from the on-site scan data without relying on CAD models. This provides a complete geometric constraint environment for subsequent path planning and collision detection, reducing path planning errors caused by incomplete models or geometric deviations.

[0047] Furthermore, in order to reduce path deviations and motion shocks caused by inaccurate manual input by operators, step S20 may include: Step S201: Determine and obtain the work trajectory and work posture input by the operator according to the interaction instructions.

[0048] It should be noted that the aforementioned work trajectory can be a spatial path line drawn by the operator on the surface of a 3D model through graphical interactive operation, used to represent the motion path that the robot end effector needs to traverse during the operation. For example, in a spraying operation, the work trajectory can be a spraying path line drawn by the operator on the surface of the workpiece 3D model, covering the outer surface of the workpiece; in a welding operation, the work trajectory can be a welding path line drawn by the operator on the workpiece 3D model along the weld seam. The aforementioned work posture can be the spatial orientation information that the robot end effector needs to maintain at each work position point, used to control the tilt angle of the end effector relative to the workpiece surface to ensure the quality of the work process. For example, in a spraying operation, the work posture can be the deflection angle of the spray gun relative to the normal of the workpiece surface at each path point; in a welding operation, the work posture can be the tilt angle of the welding gun relative to the weld seam.

[0049] Step S202: Adjust the normal of the working posture according to the workpiece surface curvature information of the three-dimensional model to obtain the target working posture of the robot's end effector.

[0050] It should be noted that the aforementioned workpiece surface curvature information can be a geometric measure of the degree of curvature of the workpiece surface at various locations in the 3D model. It can include the magnitude and direction of the curvature, and is used to describe the morphological characteristics of the workpiece surface, such as protrusions, depressions, or flatness in different areas. For example, for a bumper workpiece, the curvature of its corner areas is larger, while the curvature of the central plane area is smaller.

[0051] It should be understood that the aforementioned normal adjustment can be an operation in which the programming device corrects the working posture orientation of the end effector based on the normal direction of the workpiece surface at the path points, so that the orientation of the end effector meets a preset angular relationship with the normal direction of the workpiece surface, for example, ensuring that the spray gun axis is always perpendicular to the workpiece surface or maintaining a preset deflection angle. The aforementioned target working posture can be the final spatial orientation parameters of the end effector at each path point obtained after normal adjustment. The target working posture is used to guide the robot motion control in subsequent steps to ensure that the end effector has the optimal orientation relationship with the workpiece surface during operation.

[0052] Step S203: Perform smooth transition processing on the path inflection points in the work trajectory, and generate the robot's work path based on the target work posture and the work trajectory after smooth transition processing.

[0053] It should be noted that the aforementioned path inflection points can be locations where the direction of travel changes abruptly or the curvature of the workpiece changes abruptly. These typically occur at the junctions of trajectory segments when the operator manually draws the path, at the edges of workpiece surfaces where the geometry changes dramatically, or at the intersections of multiple trajectory segments. For example, when an operator draws a continuous path from the top surface to the side surface of a 3D model, the corner at the junction of the top and side surfaces is the path inflection point.

[0054] It should be understood that the above-mentioned smooth transition processing can be an operation of mathematical fitting to correct the position of curvature change in the operation trajectory. By replacing sharp corners with transition curves with continuously changing curvature (such as spline interpolation or circular arc transition), sharp turns in the trajectory are eliminated, so that the entire trajectory has a continuous curvature change in geometry, thereby avoiding the impact vibration caused by sudden changes in direction during the actual movement of the robot.

[0055] In this implementation, the working trajectory and posture are determined based on the interactive commands input by the operator. The normal orientation of the working posture is adjusted according to the workpiece surface curvature information of the 3D model, ensuring that the target working posture of the end effector adapts to local geometric changes on the workpiece surface and that the directional relationship between the end effector and the workpiece surface meets process requirements. Simultaneously, path inflection points in the working trajectory are smoothed to eliminate the impact of sharp turns on motion stability, maintaining continuity in the directional change region. Then, the robot's working path is generated based on the target working posture and the smoothed working trajectory. This results in a final working path that possesses both a reasonable end effector posture and a continuous trajectory, reducing path deviations and motion shocks caused by inaccurate manual input from the operator. This improves both the directional accuracy and motion stability of the generated working path.

[0056] Based on the first and / or second embodiments of this application, the content that is the same as or similar to that in the first and second embodiments described above in the third embodiment of this application can be referred to the above description and will not be repeated hereafter. On this basis, a third embodiment of the robot offline teaching programming method of this application is proposed; please refer to... Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the robot offline teaching programming method of this application.

[0057] Furthermore, to reduce repeated on-site debugging due to unreachable paths or collision risks, step S30 may include: Step S301: Obtain the kinematic model of the robot, and perform reachability analysis on the robot based on the operation path and the kinematic model to obtain the reachable space of the robot.

[0058] It should be noted that the above kinematic model can be a mathematical model describing the motion relationship between the joints of the robot, including the number of joint degrees of freedom of the robot, the motion type of each joint (rotational joint or translator joint), the geometric dimensional parameters of each link, the motion range limit of each joint, and the coordinate system transformation matrix.

[0059] It should be understood that the aforementioned reachability analysis refers to the process by which a programming device, based on the spatial positions of each path point on the work path and in conjunction with the robot's kinematic model, determines whether the robot can enable the end effector to reach every path point on the work path without exceeding the limits of each joint, and avoid singular poses during the movement. The aforementioned reachable space can be the set of all positions and postures that the robot's end effector can reach in physical space under the condition of satisfying the range of motion limits of each joint.

[0060] Step S302: Perform self-collision detection and environmental collision detection on the robot based on the reachable space and the three-dimensional model.

[0061] It should be understood that the programming device can reconstruct the complete configuration and posture of the robot at various positions on the work path in a virtual environment based on the angle values ​​of each joint of the robot corresponding to each path point in the reachable space, combined with the geometric dimensions of each link of the robot. Then, self-collision detection is performed on each reconstructed configuration and posture, that is, to determine whether there is spatial overlap or interference between the links of the robot at each movement position. Next, the spatial position of each configuration and posture of the robot is compared with the workpiece model and the surrounding equipment model in the 3D model, and environmental collision detection is performed, that is, to determine whether the robot body and the end effector will collide with surrounding objects such as workpieces, worktables, conveyor lines, fixtures or safety fences during the movement. Finally, the collision detection is passed if no collision or interference is detected by combining the self-collision detection results and the environmental collision detection results.

[0062] In this implementation, the kinematic model of the robot is obtained and accessibility analysis is performed in conjunction with the work path. Under kinematic constraints, it can determine whether the robot can reach each position on the planned path, thus obtaining the robot's reachable space. Based on this, self-collision detection and environmental collision detection are performed on the robot according to the reachable space and the 3D model. Self-collision detection is used to determine whether there is mutual interference between the robot's components, while environmental collision detection is used to determine whether there is interference between the robot and the workpiece and surrounding equipment in the 3D model. This ensures that collision detection is performed within the kinematically feasible space, simultaneously verifying both the robot's own interference and external interference in a virtual environment, reducing repeated on-site debugging caused by unreachable paths or collision risks.

[0063] Furthermore, in order to reduce post-deployment rework caused by differences between the virtual and real environments, step S30 may include: Step S303: After the collision detection is passed, a real-time image of the work site environment is acquired through an augmented reality display device.

[0064] It should be noted that the aforementioned augmented reality display device can be a wearable or handheld display device capable of overlaying and blending virtual images with the real environment. This device possesses both image acquisition and virtual-real overlay display capabilities. For example, the augmented reality display device can be AR glasses, a tablet computer or smartphone with integrated AR functionality. Operators can simultaneously observe the real work environment and the virtual image information overlaid on it through the display screen or optical lens of the augmented reality display device. The aforementioned real-time image can be a video stream obtained by the augmented reality display device through its built-in or external camera, capturing images of the work environment in real time. This reflects the real spatial position and posture of objects (including robots, workpieces, peripheral equipment, etc.) in the work environment at the current moment.

[0065] Step S304: Generate a virtual overlay image based on the 3D model and the work path, and overlay the virtual overlay image onto the real-time image to obtain the environment to be verified.

[0066] It should be noted that the aforementioned virtual overlay image can be a virtual visual image used for augmented reality display, which includes virtual rendering images of robot models, workpiece models, peripheral equipment models in the 3D model, as well as spatial trajectory lines of the work path. The rendering perspective and spatial scale of the virtual overlay image need to maintain a spatial alignment with the real-time image captured by the augmented reality display device so that the virtual object and the real object visually overlap when overlaid.

[0067] It should be understood that the programming device can calculate the projection position and display scale of the 3D model and work path in the real-time image coordinate system based on the shooting angle and spatial parameters of the real-time image, ensuring that the spatial position of the virtual object in the image is spatially aligned with the corresponding object in the real work environment. Then, according to the calculated projection position and display scale, the 3D model and work path are rendered as a virtual overlay image. This virtual overlay image contains the virtual outlines or semi-transparent models of the robot, workpiece, and surrounding equipment in the 3D model, as well as the spatial trajectory lines of the work path. The programming device can then blend and display the virtual overlay image on top of the real-time image in a semi-transparent overlay manner, allowing the operator to simultaneously observe the real work environment and the virtual 3D model and virtual work path superimposed within it, thus obtaining the environment to be verified.

[0068] In this implementation, after collision detection passes, a real-time image of the work site environment is acquired via an augmented reality display device, enabling subsequent path verification to be performed based on the current real-world scene. A virtual overlay image is generated based on the 3D model and the work path, and this virtual overlay image is superimposed on the real-time image to obtain the environment to be verified. This allows operators to simultaneously observe the relative positional relationship between the planned path and the on-site equipment within a real-time view of the actual work environment. By combining the real-time image and the virtual overlay image, operators can intuitively examine whether there are any deviations or interferences in the actual space, thereby verifying the path before program deployment and reducing post-deployment rework caused by differences between the virtual and real environments.

[0069] Furthermore, to improve the adaptability of the offline teaching program to different device types, step S40 may include: Step S401: Determine the corresponding post-processor according to the device type of the robot.

[0070] It should be noted that the aforementioned equipment type can be a combination of robot manufacturer and product model identifiers, used to uniquely identify the brand series and specific model of the target robot. The aforementioned post-processor can be a software module that converts general path instructions and process parameters into control code formats corresponding to specific equipment types.

[0071] Step S402: The post-processor converts the interactive instructions into the control code format corresponding to the device type to obtain an offline teaching program that the robot can execute.

[0072] It should be noted that the above control code format can be the instruction syntax specification and file structure that the controller of a specific brand or model of robot can recognize and parse. Different robot manufacturers have defined their own proprietary programming languages ​​and code formats, and different control code formats differ in terms of instruction keywords, parameter arrangement, syntax rules and file extensions.

[0073] In this implementation, the corresponding post-processor is determined based on the robot's device type. The post-processor converts the interactive instructions into control code format corresponding to the device type, resulting in an offline teaching program executable by the robot. This allows general interactive instructions input by the operator to be converted into an instruction format recognizable by a specific robot controller. Through the coordination of device type matching and post-processor conversion, the same set of interactive instructions can automatically generate corresponding control code based on different robot device types, eliminating the need for manual rewriting or modification of programs for different robots and improving the adaptability of the offline teaching program across different device types.

[0074] Furthermore, to reduce on-site downtime for debugging and repeated modifications due to program defects, step S40 may further include: Step S50: Perform a task simulation on the robot in a virtual environment according to the offline teaching program to obtain task simulation results. The task simulation results include trajectory reachability verification results, joint motion range verification results, and cycle time verification results.

[0075] It should be noted that the aforementioned virtual environment can be a digital simulation space with consistent spatial geometry and physical dimensions as the actual work site environment. It includes a 3D model of the robot, a 3D model of the workpiece, and 3D models of peripheral equipment, and the spatial position and orientation of each model are consistent with the actual work site. The aforementioned trajectory reachability verification result can be a verification conclusion indicating whether the robot's end effector can completely follow the planned trajectory, reflecting whether all path points are within the robot's reachable space. The aforementioned joint range of motion verification result can be a verification conclusion indicating whether the rotation angle of each joint during robot movement is within the safe limit range. The aforementioned cycle time verification result can be a calculated value indicating the total time required for the robot to execute the complete task according to the program.

[0076] Step S60: If the simulation results meet the preset operation conditions, the offline teaching program is sent to the robot for execution via the communication interface.

[0077] It should be noted that the aforementioned preset operating conditions can be a set of criteria used to determine whether the offline teaching program meets the actual operating requirements. These criteria include multiple indicators such as a "pass" result for trajectory reachability verification, a "pass" result for joint range of motion verification, and a cycle time less than or equal to a preset time threshold. The specific thresholds for the preset operating conditions can be configured by the operator according to actual production cycle requirements and safety regulations. The aforementioned communication interface can be a physical or protocol interface for data exchange between the programming device and the robot controller. This communication interface supports wired or wireless data transmission, such as industrial Ethernet interfaces, fieldbus interfaces, and wireless communication interfaces like WiFi or Bluetooth, used to transfer the offline teaching program file from the programming device to the robot controller.

[0078] In this implementation, after generating the offline teaching program, the robot undergoes a work simulation in a virtual environment based on the offline teaching program. This yields simulation results including trajectory reachability verification, joint range of motion verification, and cycle time verification. If the simulation results meet preset work conditions, the offline teaching program is sent to the robot for execution via a communication interface. This eliminates problems such as unreachable trajectories, joint over-limits, or substandard cycle times before program deployment. It allows for thorough verification of the entire robot operation process in a virtual environment, reducing on-site downtime and repeated modifications due to program defects, and improving the overall efficiency of the offline teaching program from generation to deployment.

[0079] It should be noted that the above examples are for understanding this application only and do not constitute a limitation on the offline teaching programming method for robots described in this application. Any simple modifications based on this technical concept are within the scope of protection of this application. All actions in this application that require authorization to acquire relevant data are performed in accordance with the relevant data protection regulations of the country where the application is located and with authorization from the owner of the corresponding device.

[0080] This application also provides an offline teaching and programming device for robots. Please refer to... Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the robot offline teaching and programming device of this application.

[0081] like Figure 4 As shown, the robot offline teaching and programming device proposed in this application includes: The model building module 401 is used to acquire the three-dimensional point cloud data corresponding to the robot in the work site environment, and to build a three-dimensional model based on the three-dimensional point cloud data; The path generation module 402 is used to generate the robot's working path in response to the interactive instructions input by the operator to the three-dimensional model. The collision detection module 403 is used to perform collision detection on the robot according to the operation path and the three-dimensional model, and after the collision detection is passed, overlay the operation path on the operation site environment to obtain the environment to be verified. The instruction conversion module 404 is used to convert the interactive instruction into an offline teaching program that the robot can execute if it receives a confirmation instruction from the operator for the environment to be verified.

[0082] This embodiment acquires 3D point cloud data of the work site environment and constructs a 3D model, enabling the generation of a digital model for offline programming based on actual scan data, even without a workpiece CAD model. The robot's work path is generated in response to the operator's interactive commands input into the 3D model. This work path is then overlaid and displayed in the work site environment. Collision detection based on the work path and 3D model is introduced before AR verification, pre-screening paths with collision risks in the virtual environment and reducing safety hazards and repeated debugging during subsequent on-site verification. The sequential combination of AR verification and collision detection effectively reduces the discrepancy between the offline planned path and the actual on-site working conditions, making the verified offline teaching program more closely resemble the on-site execution conditions. This avoids the need for significant time-consuming on-site calibration and repeated debugging after program deployment, ultimately achieving efficient and accurate offline robot teaching programming without relying on CAD models or programming experts.

[0083] Based on the first embodiment of the robot offline teaching programming device described in this application, a second embodiment of the robot offline teaching programming device of this application is proposed.

[0084] In this embodiment, as one implementation method, the model building module 401 is further used to perform multi-station scanning of the robot's working environment to obtain corresponding three-dimensional point cloud data; to perform multi-station stitching, noise filtering, and redundant point simplification on the three-dimensional point cloud data to obtain preprocessed three-dimensional point cloud data; to generate a three-dimensional point cloud model based on the preprocessed three-dimensional point cloud data, and to perform reverse modeling on the three-dimensional point cloud model to generate a three-dimensional model including the robot, the robot's workpiece, and the robot's peripheral equipment.

[0085] In one implementation, the path generation module 402 is further configured to determine the work trajectory and work posture input by the operator according to the interaction instructions; adjust the normal of the work posture according to the workpiece surface curvature information of the three-dimensional model to obtain the target work posture of the robot's end effector; perform smooth transition processing on the path inflection points in the work trajectory; and generate the robot's work path according to the target work posture and the work trajectory after smooth transition processing.

[0086] In one implementation, the collision detection module 403 is further configured to acquire the kinematic model of the robot, and perform reachability analysis on the robot based on the operation path and the kinematic model to obtain the reachable space of the robot; and perform self-collision detection and environmental collision detection on the robot based on the reachable space and the three-dimensional model.

[0087] In one implementation, the collision detection module 403 is further configured to acquire a real-time image of the work site environment through an augmented reality display device after the collision detection is passed; generate a virtual overlay image based on the three-dimensional model and the work path, and overlay the virtual overlay image onto the real-time image to obtain the environment to be verified.

[0088] In one implementation, the instruction conversion module 404 is further configured to determine the corresponding post-processor based on the device type of the robot; and to convert the interactive instructions into the control code format corresponding to the device type through the post-processor to obtain an offline teaching program executable by the robot.

[0089] In one implementation, the instruction conversion module 404 is further configured to perform a task simulation on the robot in a virtual environment according to the offline teaching program, and obtain task simulation results. The task simulation results include trajectory reachability verification results, joint motion range verification results, and cycle time verification results. If the task simulation results meet the preset task conditions, the offline teaching program is sent to the robot for execution through the communication interface.

[0090] Furthermore, the aforementioned offline teaching programming device for robots may also include a coating coverage simulation and film thickness simulation module. The function of the coating coverage simulation and film thickness simulation module is that, after the system obtains the relevant environmental data model and product model, the visual programming platform can support the simulation of coating coverage and film thickness for the product, reducing a significant amount of physical product debugging. Specifically, after collision detection and generating the work path, before converting the interactive instructions into an offline teaching program executable by the robot, the system can utilize the constructed 3D model and the generated work path to perform coating coverage simulation and film thickness simulation operations. Coating coverage simulation is used to calculate whether each area in the work path is completely covered by the coating trajectory, avoiding areas with missed or repeated coating; film thickness simulation is used to simulate the coating thickness distribution formed at various locations on the workpiece surface by the work path, ensuring that the coating thickness meets process requirements. Through coverage simulation and film thickness simulation, the system can predict the coating quality of the work path in advance without performing actual coating.

[0091] Furthermore, after collision detection passes and relevant interactive instructions are generated, a quality simulation confirmation can be performed on the corresponding work path. This quality simulation confirmation process includes the aforementioned spray coverage simulation and film thickness simulation operations to verify whether the work path can meet the expected spray quality requirements during actual execution. Only after the quality simulation confirmation is passed will the system convert the interactive instruction into an offline teaching program and deliver it to the backend robot for execution. By introducing quality simulation debugging in the offline teaching programming stage, quality defects in the spray path can be identified and corrected in advance in a virtual environment, eliminating the need for repeated trial spraying and debugging on physical workpieces. This significantly saves on the consumption of debugging supplies such as paint and workpieces, while also significantly shortening the debugging cycle and improving production line changeover efficiency.

[0092] The robot offline teaching programming device provided in this application, employing the robot offline teaching programming method in the above embodiments, can solve the technical problem of how to achieve efficient and accurate robot offline teaching programming without relying on CAD models and programming experts. Compared with the prior art, the beneficial effects of the robot offline teaching programming device provided in this application are the same as those of the robot offline teaching programming method provided in the above embodiments, and other technical features in the robot offline teaching programming device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0093] This application provides a robot offline teaching programming device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the robot offline teaching programming method in the above embodiment 1.

[0094] The following reference Figure 5 The diagram illustrates a structural schematic suitable for implementing the robot offline teaching programming device in the embodiments of this application. The robot offline teaching programming device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The robot offline teaching and programming device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0095] like Figure 5 As shown, the robot offline teaching programming device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory 1002 or the program loaded from the storage device 1003 into the random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the robot offline teaching programming device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the robot offline teaching and programming device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows robot offline teaching and programming devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0096] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0097] The robot offline teaching programming device provided in this application, employing the robot offline teaching programming method described in the above embodiments, can solve the technical problem of how to achieve efficient and accurate robot offline teaching programming without relying on CAD models and programming experts. Compared with the prior art, the beneficial effects of the robot offline teaching programming device provided in this application are the same as those of the robot offline teaching programming method provided in the above embodiments, and other technical features in this robot offline teaching programming device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0098] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0099] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included 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.

[0100] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the robot offline teaching programming method in the above embodiments.

[0101] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0102] The aforementioned computer-readable storage medium may be included in the robot offline teaching and programming device; or it may exist independently and not be assembled into the robot offline teaching and programming device.

[0103] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a robot offline teaching programming device, enable the device to write computer program code for performing the operations of this application in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++; and also conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet using an Internet service provider).

[0104] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0105] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0106] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-described robot offline teaching programming method. This solves the technical problem of how to achieve efficient and accurate robot offline teaching programming without relying on CAD models and programming experts. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the robot offline teaching programming method provided in the above embodiments, and will not be repeated here.

[0107] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the robot offline teaching programming method described above.

[0108] The computer program product provided in this application solves the technical problem of how to achieve efficient and accurate offline teaching programming of robots without relying on CAD models and programming experts. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the offline teaching programming method for robots provided in the above embodiments, and will not be repeated here.

[0109] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A robot offline teaching programming method, characterized in that, The method includes the following steps: Acquire the 3D point cloud data corresponding to the robot in the work site environment, and construct a 3D model based on the 3D point cloud data; In response to the interactive instructions input by the operator to the 3D model, the robot's work path is generated according to the interactive instructions; The robot is subjected to collision detection based on the work path and the 3D model. After the collision detection is passed, the work path is superimposed on the work site environment to obtain the environment to be verified. If the operator receives a confirmation instruction for the environment to be verified, the interactive instruction is converted into an offline teaching program that the robot can execute.

2. The robot offline teaching programming method as described in claim 1, characterized in that, The step of acquiring the 3D point cloud data corresponding to the robot in the work site environment and constructing a 3D model based on the 3D point cloud data includes: The robot's operating environment is scanned from multiple stations to obtain corresponding 3D point cloud data; The three-dimensional point cloud data is spliced ​​from multiple stations, noise is filtered out, and redundant points are reduced to obtain preprocessed three-dimensional point cloud data. A 3D point cloud model is generated based on the preprocessed 3D point cloud data, and the 3D point cloud model is reverse-engineered to generate a 3D model including the robot, the robot's workpiece, and the robot's peripheral equipment.

3. The robot offline teaching programming method as described in claim 1, characterized in that, The step of generating the robot's work path based on the interactive instructions includes: The operation trajectory and operation posture input by the operator are determined based on the interactive instructions. The normal of the working posture is adjusted according to the workpiece surface curvature information of the three-dimensional model to obtain the target working posture of the robot's end effector. The path inflection points in the work trajectory are smoothed, and the robot's work path is generated based on the target work posture and the work trajectory after the smoothing process.

4. The robot offline teaching programming method as described in claim 1, characterized in that, The step of performing collision detection on the robot based on the work path and the 3D model includes: Obtain the kinematic model of the robot, and perform reachability analysis on the robot based on the operation path and the kinematic model to obtain the reachable space of the robot; The robot performs self-collision detection and environmental collision detection based on the reachable space and the three-dimensional model.

5. The robot offline teaching programming method as described in claim 1, characterized in that, The step of overlaying the work path onto the work site environment after the collision detection is passed to obtain the environment to be verified includes: After the collision detection is passed, a real-time image of the work site environment is acquired through an augmented reality display device; A virtual overlay image is generated based on the 3D model and the work path, and the virtual overlay image is superimposed on the real-time image to obtain the environment to be verified.

6. The robot offline teaching programming method as described in claim 1, characterized in that, The step of converting the interactive instructions into an offline teaching program executable by the robot includes: The corresponding post-processor is determined based on the robot's device type; The post-processor converts the interactive instructions into control code format corresponding to the device type, thereby obtaining an offline teaching program that the robot can execute.

7. The robot offline teaching programming method as described in claim 1, characterized in that, After the step of converting the interactive instructions into an offline teaching program executable by the robot, the method further includes: The robot is simulated in a virtual environment according to the offline teaching program to obtain the simulation results, which include trajectory reachability verification results, joint range of motion verification results, and cycle time verification results. If the simulation results meet the preset operation conditions, the offline teaching program is sent to the robot for execution via the communication interface.

8. A robot offline teaching and programming device, characterized in that, The robot offline teaching and programming device includes: The model building module is used to acquire the 3D point cloud data corresponding to the robot in the working environment, and to build a 3D model based on the 3D point cloud data; The path generation module is used to generate the robot's working path in response to the interactive instructions input by the operator to the 3D model; The collision detection module is used to perform collision detection on the robot based on the work path and the 3D model, and after the collision detection is passed, to overlay and display the work path on the work site environment to obtain the environment to be verified. The instruction conversion module is used to convert the interactive instruction into an offline teaching program that the robot can execute if it receives a confirmation instruction from the operator for the environment to be verified.

9. A robot offline teaching programming device, characterized in that, The device includes: a memory, a processor, and a robot offline teaching programming program stored in the memory and executable on the processor, the robot offline teaching programming program being configured to implement the steps of the robot offline teaching programming method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and the storage medium stores a robot offline teaching programming program. When the robot offline teaching programming program is executed by a processor, it implements the steps of the robot offline teaching programming method as described in any one of claims 1 to 7.

Images