Welding track generation method, device and equipment and storage medium

Abstract

The invention provides a welding track generation method and device, equipment and a storage medium, and relates to the technical field of automatic welding. In some embodiments of the invention, welding seam point cloud data of a target welding seam of a to-be-welded object is obtained; the welding seam point cloud data are input into a welding track generation model, at least one welding track corresponding to the target welding seam is obtained, and each welding track comprises a plurality of control points; the robot is controlled to conduct welding operation on the at least one welding track; according to the welding track generation model, the accurate welding line track is generated, the robot is guided to conduct welding operation, the automatic welding efficiency is improved, and the welding track extraction accuracy is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of automatic welding, and in particular to a welding trajectory generation method, device, equipment and storage medium. Background Art

[0002] Welding automation is an important means to improve welding quality and efficiency and reduce labor costs. Weld seam tracking is one of the necessary technologies for achieving welding automation and has been widely used in the field of high-end equipment manufacturing.

[0003] Traditional methods for extracting welding trajectories require pre-determining the weld type and then selecting a pre-defined trajectory extraction method. This approach has limited generalizability and requires manual specification of weld types, which is cumbersome and results in low accuracy in welding trajectory extraction.

[0004] Currently, the efficiency of automatic welding is low and the accuracy of welding trajectory extraction is low. Summary of the Invention

[0005] The present disclosure provides a welding trajectory generation method, device, equipment and storage medium method to at least solve the problems of low efficiency and low accuracy of welding trajectory extraction in existing automatic welding.

[0006] The technical solutions disclosed in this disclosure are as follows:

[0007] The present disclosure provides a method for generating a welding trajectory, comprising:

[0008] Acquire weld point cloud data of a target weld of an object to be welded;

[0009] Inputting the weld point cloud data into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes a plurality of control points;

[0010] The robot is controlled to perform welding operations on at least one of the welding tracks.

[0011] Optionally, obtaining weld point cloud data of a target weld of the object to be welded includes:

[0012] The object to be welded is photographed using a 3D camera to obtain weld point cloud data of the target weld.

[0013] Optionally, the weld point cloud data includes: point cloud information and position information; the welding trajectory generation model includes: a feature extraction module, an encoder, a decoder, and a feedforward neural network; inputting the weld point cloud data into the welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld includes:

[0014] Inputting the point cloud information and position information into the feature extraction module to perform feature extraction to obtain point cloud features and position embedding vectors;

[0015] Inputting the point cloud features and the position embedding vector into the encoder for feature encoding to obtain a global feature vector;

[0016] After inputting the global feature vector into the decoder, an initial control point set is obtained;

[0017] After the control point set is input into the feedforward neural network, at least one welding trajectory corresponding to the target weld is obtained.

[0018] Optionally, after inputting the global feature vector into the decoder, obtaining an initial control point set includes:

[0019] Within the decoder, generating a weld type and a type probability corresponding to the weld type according to the global feature vector;

[0020] generating a query vector according to the type probability;

[0021] An initial control point set corresponding to the weld type is determined according to the global feature vector and the query vector.

[0022] Optionally, the weld type of the target weld is single-layer single-pass or multi-layer multi-pass; inputting the weld point cloud data into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld includes:

[0023] In a case where the weld type of the target weld is the single-layer single-pass weld, inputting the weld point cloud data into a welding trajectory generation model to obtain a welding trajectory;

[0024] In a case where the weld type of the target weld is the multi-layer and multi-pass weld, the weld point cloud data is input into a welding trajectory generation model to obtain a plurality of welding trajectories.

[0025] Optionally, the welding trajectory generation model is an Encoder-Decoder model or a Transformer-Based model.

[0026] The present disclosure also provides a welding trajectory generating device, comprising:

[0027] An acquisition module, used to acquire weld point cloud data of a target weld of an object to be welded;

[0028] A trajectory generation module, configured to input the weld point cloud data into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes a plurality of control points;

[0029] The control module is used to control the robot to perform welding operations on at least one welding track.

[0030] The present disclosure also provides an electronic device, including:

[0031] processor;

[0032] a memory for storing processor-executable instructions;

[0033] The processor is configured to execute instructions to implement each step in the above method.

[0034] The embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, each step in the above method is implemented.

[0035] The embodiments of the present disclosure further provide a computer program product, including a computer program / instruction, which implements the steps in the above method when executed by a processor.

[0036] The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:

[0037] In some embodiments of the present disclosure, weld point cloud data of a target weld of an object to be welded is obtained; the weld point cloud data is input into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes multiple control points; a robot is controlled to perform welding operations on the at least one welding trajectory; the welding trajectory generation model of the present disclosure generates an accurate weld trajectory, guides the robot to perform welding operations, improves automatic welding efficiency, and improves the accuracy of welding trajectory extraction.

[0038] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0040] Figure 1 A schematic flow chart of a welding trajectory generation method provided by an exemplary embodiment of the present disclosure;

[0041] Figure 2A schematic structural diagram of a welding trajectory generation model provided by an exemplary embodiment of the present disclosure;

[0042] Figure 3 A schematic structural diagram of a welding trajectory generating device provided by an exemplary embodiment of the present disclosure;

[0043] Figure 4 A schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] In order to enable ordinary people in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0045] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0046] It should be noted that the user information involved in this disclosure includes but is not limited to: user device information and user personal information; the collection, storage, use, processing, transmission, provision and disclosure of user information in this disclosure comply with the relevant laws and regulations and do not violate public order and good morals.

[0047] Welding automation is an important means to improve welding quality and efficiency and reduce labor costs. Weld seam tracking is one of the necessary technologies for achieving welding automation and has been widely used in the field of high-end equipment manufacturing.

[0048] Traditional methods for extracting welding trajectories require pre-determining the weld type and then selecting a pre-defined trajectory extraction method. This approach has limited generalizability and requires manual specification of weld types, which is cumbersome and results in low accuracy in welding trajectory extraction.

[0049] Currently, the efficiency of automatic welding is low and the accuracy of welding trajectory extraction is low.

[0050] In response to the above technical problems, in some embodiments of the present disclosure, weld point cloud data of a target weld of an object to be welded is obtained; the weld point cloud data is input into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes multiple control points; a robot is controlled to perform welding operations on at least one welding trajectory; the welding trajectory generation model of the present disclosure generates an accurate weld trajectory, guides the robot to perform welding operations, improves automatic welding efficiency, and improves the accuracy of welding trajectory extraction.

[0051] The technical solutions provided by various embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0052] Figure 1 Schematic diagram of a welding trajectory generation method provided by an exemplary embodiment of the present disclosure. Figure 1 As shown, the method includes:

[0053] S101: Acquire weld point cloud data of a target weld of an object to be welded;

[0054] S102: Inputting the weld point cloud data into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes a plurality of control points;

[0055] S103: Control the robot to perform welding operations on at least one welding track.

[0056] In this embodiment, the execution subject of the above method may be a terminal device or a server. Optionally, the execution subject of the above method may be a robot.

[0057] Among them, terminal devices include but are not limited to mobile stations (MS), mobile terminals, mobile phones, handsets, and portable equipment. The terminal devices can communicate with one or more core networks via a radio access network (RAN). For example, the terminal devices can be mobile phones (or "cellular" phones), computers with wireless communication capabilities, etc. The terminal devices can also be computers with wireless transceiver capabilities, virtual reality (VR) terminal devices, AR terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical care, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, etc., and the operating systems installed on the terminal devices include but are not limited to: iOS, Android, Windows, Linux, Mac OS, etc. In different networks, a terminal may be called by different names, such as user equipment, mobile station, subscriber unit, station, cellular phone, personal digital assistant, wireless modem, wireless communication device, handheld device, laptop computer, cordless phone, wireless local loop station, television, etc. For the convenience of description, the terminal is referred to as terminal equipment in this embodiment.

[0058] In this embodiment, the server implementation is not limited. For example, the server can be a conventional server, a cloud server, a cloud host, a virtual center, or other server devices. The server components primarily include a processor, a hard disk, memory, a system bus, and other common computer architecture types.

[0059] In this embodiment, weld point cloud data of a target weld of an object to be welded is obtained; the weld point cloud data is input into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes a plurality of control points; a robot is controlled to perform a welding operation on the at least one welding trajectory; the welding trajectory generation model disclosed herein generates an accurate weld trajectory, guides the robot to perform welding operations, improves automatic welding efficiency, and improves the accuracy of welding trajectory extraction.

[0060] It should be noted that the present disclosure does not limit the object to be welded, and the object to be welded may be an H-shaped steel.

[0061] In some embodiments of the present disclosure, weld point cloud data of a target weld of an object to be welded is obtained. One achievable method is to use a 3D camera to photograph the object to be welded and obtain weld point cloud data of the target weld. The 3D camera obtains a depth map of the scene through different technologies (structured light, ToF, binocular vision, etc.), that is, the distance value (Z coordinate) corresponding to each pixel point; converts the 2D pixel coordinates (u, v) + depth value (Z) in the depth map into 3D world coordinates (X, Y, Z); converts the 2D pixel coordinates (u, v) + depth value (Z) in the depth map into 3D world coordinates (X, Y, Z) to generate weld point cloud data.

[0062] It should be noted that the present disclosure may also use sensors such as laser radar to obtain weld point cloud data of the target weld of the object to be welded.

[0063] It should be noted that the weld point cloud data includes: point cloud information and position information.

[0064] In an optional embodiment, the welding trajectory generation model includes: a feature extraction module, an encoder, a decoder and a feedforward neural network.

[0065] Figure 2 Schematic diagram of a welding trajectory generation model provided by an exemplary embodiment of the present disclosure. Figure 2 As shown, the welding trajectory generation model includes: a feature extraction module, an encoder, a decoder and a feedforward neural network. The weld point cloud data is input into the welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes multiple control points. The point cloud information and position information are input into the feature extraction module for feature extraction to obtain point cloud features and position embedding vectors; the point cloud features and position embedding vectors are input into the encoder for feature encoding to obtain a global feature vector; after the global feature vector is input into the decoder, an initial control point set is obtained; after the control point set is input into the feedforward neural network, at least one welding trajectory corresponding to the target weld is obtained. The present disclosure can quickly generate a welding trajectory corresponding to a target weld through a welding trajectory generation model, thereby improving the accuracy of the welding trajectory.

[0066] In the above embodiment, after the global feature vector is input into the decoder, the initial control point set is obtained. Inside the decoder, the weld type and the type probability corresponding to the weld type are generated based on the global feature vector; a query vector is generated based on the type probability; and the initial control point set corresponding to the weld type is determined based on the global feature vector and the query vector.

[0067] In some embodiments of the present disclosure, the welding trajectory generation model can determine the weld type based on the weld point cloud; and output the corresponding weld trajectory based on the weld type. Among them, the weld types include single-layer single-pass and multi-layer multi-pass. When the weld type of the target weld is single-layer single-pass, the weld point cloud data is input into the welding trajectory generation model to obtain a welding trajectory; when the weld type of the target weld is multi-layer multi-pass, the weld point cloud data is input into the welding trajectory generation model to obtain the generation efficiency and accuracy of multiple welding trajectories. Among them, input: global feature vector z (encoder output, including groove angle, plate thickness and other information); type prediction: classification head output probability: single-layer single-pass weld (0.9), multi-layer multi-pass weld (0.1). Query vector generation: obtain a 128-dimensional query vector; control point generation: through the attention mechanism, guide the model to focus on the straight line trajectory features and output a set of control points along the center line of the weld.

[0068] It should be noted that single-layer single-pass means that the joint is filled with only one layer of welding, and this layer is formed by a continuous welding operation (one weld pass). Multi-layer multi-pass means that the joint is filled in multiple weld layers (such as root layer, fill layer, and cap layer), and each layer consists of multiple parallel or overlapping weld passes.

[0069] In an optional embodiment, the welding trajectory generation model is an Encoder-Decoder model or a Transformer-Based model.

[0070] In an optional embodiment, after the welding trajectory of the target weld is acquired, the robot is controlled to perform welding operations on at least one welding trajectory.

[0071] In the above method embodiment of the present disclosure, weld point cloud data of a target weld of an object to be welded is obtained; the weld point cloud data is input into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes a plurality of control points; a robot is controlled to perform a welding operation on the at least one welding trajectory; the welding trajectory generation model of the present disclosure generates an accurate weld trajectory, guides the robot to perform welding operations, improves automatic welding efficiency, and improves the accuracy of welding trajectory extraction.

[0072] Figure 3 Schematic diagram of a welding trajectory generating device provided by an exemplary embodiment of the present disclosure. Figure 3 As shown, the welding trajectory generating device 30 includes: an acquisition module 31 , a trajectory generating module 32 and a control module 33 .

[0073] The acquisition module 31 is used to acquire weld point cloud data of a target weld of an object to be welded;

[0074] A trajectory generation module 32 is used to input the weld point cloud data into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes a plurality of control points;

[0075] The control module 33 is used to control the robot to perform welding operations on at least one welding track.

[0076] Optionally, when acquiring the weld point cloud data of the target weld of the object to be welded, the acquisition module 31 is configured to: photograph the object to be welded using a 3D camera to obtain the weld point cloud data of the target weld.

[0077] Optionally, the weld point cloud data includes: point cloud information and position information; the welding trajectory generation model includes: a feature extraction module, an encoder, a decoder, and a feedforward neural network; when the trajectory generation module 32 inputs the weld point cloud data into the welding trajectory generation model and obtains at least one welding trajectory corresponding to the target weld, it is used to:

[0078] Input the point cloud information and position information into the feature extraction module for feature extraction to obtain point cloud features and position embedding vectors;

[0079] The point cloud features and position embedding vectors are input into the encoder for feature encoding to obtain the global feature vector;

[0080] After the global feature vector is input into the decoder, the initial control point set is obtained;

[0081] After the control point set is input into the feedforward neural network, at least one welding trajectory corresponding to the target weld is obtained.

[0082] Optionally, after inputting the global feature vector into the decoder, the trajectory generation module 32 obtains the initial control point set, and is used to:

[0083] Inside the decoder, the weld type and the corresponding type probability are generated based on the global feature vector;

[0084] Generate query vector based on type probability;

[0085] According to the global feature vector and the query vector, the initial control point set corresponding to the weld type is determined.

[0086] Optionally, the weld type of the target weld is single-layer single-pass or multi-layer multi-pass; when the trajectory generation module 32 inputs the weld point cloud data into the welding trajectory generation model and obtains at least one welding trajectory corresponding to the target weld, it is used to:

[0087] When the weld type of the target weld is single-layer single-pass, the weld point cloud data is input into the welding trajectory generation model to obtain a welding trajectory;

[0088] When the weld type of the target weld is multi-layer and multi-pass, the weld point cloud data is input into the welding trajectory generation model to obtain multiple welding trajectories.

[0089] Optionally, the welding trajectory generation model is an Encoder-Decoder model or a Transformer-Based model.

[0090] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0091] Figure 4 FIG. 1 is a structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. Figure 4 As shown, the electronic device includes: a memory 41 and a processor 42. In addition, the electronic device also includes a power supply component 43 and a communication component 44.

[0092] The memory 41 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device.

[0093] The memory 41 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0094] The communication component 44 is used for data transmission with other devices.

[0095] The processor 42 can execute computer instructions stored in the memory 41 to: obtain weld point cloud data of a target weld of an object to be welded; input the weld point cloud data into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes multiple control points; and control the robot to perform welding operations on the at least one welding trajectory.

[0096] Optionally, when acquiring weld point cloud data of a target weld of an object to be welded, the processor 42 is configured to:

[0097] Use a 3D camera to shoot the object to be welded and obtain the weld point cloud data of the target weld.

[0098] Optionally, the weld point cloud data includes: point cloud information and position information; the welding trajectory generation model includes: a feature extraction module, an encoder, a decoder, and a feedforward neural network; when the processor 42 inputs the weld point cloud data into the welding trajectory generation model and obtains at least one welding trajectory corresponding to the target weld, it is configured to:

[0099] Input the point cloud information and position information into the feature extraction module for feature extraction to obtain point cloud features and position embedding vectors;

[0100] The point cloud features and position embedding vectors are input into the encoder for feature encoding to obtain the global feature vector;

[0101] After the global feature vector is input into the decoder, the initial control point set is obtained;

[0102] After the control point set is input into the feedforward neural network, at least one welding trajectory corresponding to the target weld is obtained.

[0103] Optionally, after inputting the global feature vector into the decoder and obtaining the initial control point set, the processor 42 is configured to:

[0104] Inside the decoder, the weld type and the corresponding type probability are generated based on the global feature vector;

[0105] Generate query vector based on type probability;

[0106] According to the global feature vector and the query vector, the initial control point set corresponding to the weld type is determined.

[0107] Optionally, the weld type of the target weld is single-layer single-pass or multi-layer multi-pass; when the processor 42 inputs the weld point cloud data into the welding trajectory generation model and obtains at least one welding trajectory corresponding to the target weld, it is used to:

[0108] When the weld type of the target weld is single-layer single-pass, the weld point cloud data is input into the welding trajectory generation model to obtain a welding trajectory;

[0109] When the weld type of the target weld is multi-layer and multi-pass, the weld point cloud data is input into the welding trajectory generation model to obtain multiple welding trajectories.

[0110] Optionally, the welding trajectory generation model is an Encoder-Decoder model or a Transformer-Based model.

[0111] Accordingly, the embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program. When the computer-readable storage medium stores the computer program and the computer program is executed by one or more processors, the one or more processors are caused to execute Figure 1 Each step in the method embodiment.

[0112] Accordingly, the present disclosure also provides a computer program product, which includes a computer program / instruction, and the computer program / instruction is executed by a processor. Figure 1 Each step in the method embodiment.

[0113] above Figure 4 The communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0114] above Figure 4 The power supply component in a device provides power to various components of the device in which the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which the power supply component is located.

[0115] The electronic device also includes a display screen and an audio component.

[0116] The display screen includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0117] The audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as call mode, recording mode, and voice recognition mode, the microphone is configured to receive external audio signals. The received audio signal can be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0118] In the embodiments of the above-mentioned apparatus, device, storage medium and computer program product disclosed herein, weld point cloud data of a target weld of an object to be welded is obtained; the weld point cloud data is input into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes multiple control points; a robot is controlled to perform welding operations on the at least one welding trajectory; the welding trajectory generation model disclosed herein generates an accurate weld trajectory, guides the robot to perform welding operations, improves automatic welding efficiency, and improves the accuracy of welding trajectory extraction.

[0119] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0123] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0124] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0125] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0126] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0127] The above are merely specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not limited to these embodiments, but is to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A welding trajectory generation method, characterized in that: include: Acquire weld point cloud data of a target weld of an object to be welded; Inputting the weld point cloud data into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes a plurality of control points; The robot is controlled to perform welding operations on at least one of the welding tracks.

2. The method according to claim 1, characterized in that The step of obtaining weld point cloud data of a target weld of an object to be welded comprises: The object to be welded is photographed using a 3D camera to obtain weld point cloud data of the target weld.

3. The method according to claim 1, characterized in that The weld point cloud data includes: point cloud information and position information, and the welding trajectory generation model includes: a feature extraction module, an encoder, a decoder and a feedforward neural network; the weld point cloud data is input into the welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, including: Inputting the point cloud information and position information into the feature extraction module to perform feature extraction to obtain point cloud features and position embedding vectors; Inputting the point cloud features and the position embedding vector into the encoder for feature encoding to obtain a global feature vector; After inputting the global feature vector into the decoder, an initial control point set is obtained; After the control point set is input into the feedforward neural network, at least one welding trajectory corresponding to the target weld is obtained.

4. The method according to claim 3, characterized in that After the global feature vector is input into the decoder, an initial control point set is obtained, including: Within the decoder, generating a weld type and a type probability corresponding to the weld type according to the global feature vector; generating a query vector according to the type probability; An initial control point set corresponding to the weld type is determined according to the global feature vector and the query vector.

5. The method according to claim 1, wherein The weld type of the target weld is single-layer single-pass or multi-layer multi-pass; inputting the weld point cloud data into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld includes: In a case where the weld type of the target weld is the single-layer single-pass weld, inputting the weld point cloud data into a welding trajectory generation model to obtain a welding trajectory; In a case where the weld type of the target weld is the multi-layer and multi-pass weld, the weld point cloud data is input into a welding trajectory generation model to obtain a plurality of welding trajectories.

6. The method according to claim 1, characterized in that The welding trajectory generation model is an Encoder-Decoder model or a Transformer-Based model.

7. A welding trajectory generating device, characterized in that: include: An acquisition module, used to acquire weld point cloud data of a target weld of an object to be welded; A trajectory generation module, configured to input the weld point cloud data into a welding trajectory generation model to obtain at least one welding trajectory corresponding to the target weld, wherein each welding trajectory includes a plurality of control points; The control module is used to control the robot to perform welding operations on at least one welding track.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute instructions to implement each step in the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images