Robot system, control method, control device, and readable storage medium

Abstract

This invention provides a robot system and its control method, control device, and readable storage medium, comprising the following steps: receiving first image information of a workpiece to be processed, the first image information containing one or more identification information; determining a target processing area in the first image information based on the identification information; performing feature recognition on the target processing area; and determining the robot's target motion trajectory based on the result of feature recognition. This invention determines the target processing area in the first image information based on the identification information, eliminating a large number of invalid areas, especially some complex curved surfaces or blurry contours that are difficult to process. This reduces the workload of the image processing unit, improves processing efficiency and accuracy, and makes the system more intelligent and simpler. Furthermore, it allows workers to directly draw on the workpiece to be processed, greatly lowering the skill threshold and resulting in more accurate patterns.

Description

Technical Field

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

[0002] In existing technologies, robots can identify information such as the contour, shape, and edges of workpieces. However, there are some scenarios where complex curved surfaces or blurred contours are difficult to handle. In addition, there are some scenarios where the robot acquires visual information but still has difficulty distinguishing which information is effective for processing. Therefore, workers need to further process the information based on image recognition to tell the robot what work really needs to be done.

[0003] Currently, the robot's visual processing is not human-friendly, intelligent, or simple enough; there is still a certain threshold for using the robot, and human error is also prone to occur during the later stages of information processing. Summary of the Invention

[0004] The purpose of this invention is to provide a control method, control device, robot system, and readable storage medium for a robot system, so as to overcome the shortcomings of the prior art.

[0005] The above objective is achieved through the following technical solution:

[0006] This invention provides a control method for a robot system, comprising the following steps:

[0007] Receive first image information of the workpiece to be processed, wherein the first image information contains one or more identification information;

[0008] The target processing area in the first image information is determined based on the identification information;

[0009] Feature recognition is performed on the target processing region;

[0010] The target motion trajectory of the robot is determined based on the results of feature recognition.

[0011] According to a technical solution of the present invention, determining the target processing region in the image information based on the identification information includes:

[0012] The type of the identification information is determined based on the characteristics of the identification information, wherein the characteristics include one or more of color, line type, and symbol.

[0013] If the type of the identification information is edge identification information, then the edge where the edge identification information is located is determined to be the target processing area;

[0014] If the type of the identification information is regional identification information, then the region where the regional identification information is located is determined to be the target processing region.

[0015] According to a technical solution of the present invention, the step of determining the edge where the edge identification information is located as the target processing area if the type of the identification information is identified as edge identification information includes:

[0016] If the edge identification information is determined to be the first identification information, then the edge extending along the first identification information is determined to be the target processing area;

[0017] If the edge identification information is determined to be the second identification information, then the portion of the edge covered by the second identification information is determined to be the target processing area.

[0018] According to a technical solution of the present invention, determining the type of the identification information based on the characteristics of the identification information includes:

[0019] If the identification information has the first feature, then the identification information is determined to be the edge identification information;

[0020] If the identification information has a second feature, then the identification information is determined to be the area identification information;

[0021] Wherein, the first feature includes the second feature and the distinguishing feature, or the second feature includes the first feature and the distinguishing feature.

[0022] According to a technical solution of the present invention, before determining the target processing region in the image information based on the identification information, the method further includes:

[0023] If the identification information is valid, it is determined according to preset conditions. If it is, the step of determining the target processing area in the image information based on the identification information is executed.

[0024] The preset conditions include the length, width, or area of ​​the region covered by the identification information meeting preset values.

[0025] According to a technical solution of the present invention, the image information contains multiple identification information, wherein determining the target motion trajectory of the robot based on the result of feature recognition further includes:

[0026] Identify whether each of the identified information pieces has corresponding sequential identified information, wherein,

[0027] The target trajectory is determined based on the order of the sequence identification information among the multiple identification information.

[0028] The target trajectory is determined according to a preset order if none of the multiple identification information items have sequential identification information.

[0029] Among the multiple identification information, those with sequential identification information take precedence over those without sequential identification information.

[0030] According to a technical solution of the present invention, the feature recognition of the target processing region includes:

[0031] Edge detection is performed on the target processing area.

[0032] According to a technical solution of the present invention, before receiving the first image information of the workpiece to be processed, the method further includes:

[0033] Receive the second image information of the workpiece to be processed;

[0034] The outline of the workpiece to be processed is identified based on the second image information;

[0035] The identified outline of the workpiece to be processed is matched with a visual feature model in the database, the visual feature model including the outline of the workpiece to be processed and the result of feature recognition.

[0036] If a match is successful, the target's motion trajectory is determined based on the matched visual feature model.

[0037] According to a technical solution of the present invention, after performing feature recognition on the target processing region, the method further includes:

[0038] The outline of the workpiece to be processed is identified based on the first image information;

[0039] A visual feature model of the workpiece to be processed is generated based on the result of feature recognition and the outline of the workpiece to be processed.

[0040] The generated visual feature model is stored in the database.

[0041] The present invention also provides a control device, characterized in that it comprises:

[0042] A memory, on which programs or instructions are stored;

[0043] A processor that executes the program or instructions to implement the steps of the control method for the robot system as described in any of the above technical solutions.

[0044] The present invention also provides a robot system, characterized in that it comprises:

[0045] robotic arm;

[0046] The control device of the robot system as described in the foregoing technical solution is communicatively connected to the robotic arm.

[0047] The present invention also provides a readable storage medium having a program or instructions stored thereon, wherein the program or instructions, when executed by a processor, implement the steps of the control method for the robot system as described in any of the above technical solutions.

[0048] In this invention, the first image information received by the robot system contains identification information. It can be understood that since the identification information is the area to be processed drawn by the worker, the image processing unit can easily determine the target processing area in the first image information and perform feature recognition on the target processing area, thereby eliminating a large number of invalid areas, especially some complex curved surfaces or blurry contours that are difficult to process. This greatly reduces the workload of the image processing unit, improves processing efficiency and accuracy, and makes the system more intelligent and simpler.

[0049] Furthermore, compared to existing technologies where images are acquired by image acquisition equipment and then professional workers select and label information from the images, this invention allows workers to draw directly on the workpiece to be processed. This greatly reduces the skill requirements for workers and also results in a higher accuracy rate for the drawn patterns.

[0050] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the invention. Attached Figure Description

[0051] The above and other objects, features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0052] Figure 1 This is a flowchart illustrating the control method of the robot system according to an embodiment of the present invention.

[0053] Figure 2 This is a schematic diagram of a portion of the structure of the robot system according to an embodiment of the present invention.

[0054] Figure 3 This is a schematic diagram of the structure of the area identification information of the workpiece to be processed according to an embodiment of the present invention.

[0055] Figure 4 This is a schematic diagram of the edge marking information of the workpiece to be processed according to an embodiment of the present invention.

[0056] Figure 5 This is a flowchart illustrating the control method of the robot system according to an embodiment of the present invention.

[0057] Figure 6This is a schematic diagram of the control device according to an embodiment of the present invention.

[0058] Image acquisition device 100; workpiece to be processed 200; control device 300; memory 310; processor 320. Detailed Implementation

[0059] Although the invention can be readily embodied in various forms, only some specific embodiments are shown in the accompanying drawings and will be described in detail in this specification. It is understood that this specification should be regarded as an exemplary illustration of the principles of the invention and is not intended to limit the invention to what is described herein.

[0060] Therefore, a feature pointed out in this specification is used to describe one feature of one embodiment of the invention, and does not imply that every embodiment of the invention must have the described feature. Furthermore, it should be noted that this specification describes many features. Although certain features may be combined to illustrate possible system designs, these features may also be used in other combinations not explicitly stated. Therefore, unless otherwise stated, the described combinations are not intended to be limiting.

[0061] In the embodiments shown in the accompanying drawings, the directional indications (such as up, down, inside, outside) used to explain the structure and movement of the various elements of the invention are relative rather than absolute. These descriptions are appropriate when these elements are in the positions shown in the drawings. If the description of the positions of these elements changes, these directional indications also change accordingly.

[0062] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of the invention will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art. The drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0063] Example 1

[0064] like Figure 1 and Figure 2 As shown, this embodiment provides a control method for a robot system, including the following steps:

[0065] S101: Receive first image information of the workpiece 200 to be processed, wherein the first image information contains one or more identification information.

[0066] For example, before performing step S101, the image acquisition device 100 (e.g., camera, video camera, scanning device) acquires the first image information of the workpiece 200 to be processed. The image acquisition device 100 sends the acquired first image information to the image processing unit of the robot system so that the image processing unit can process the first image information.

[0067] It should be noted that the image acquisition device 100 can be designed as part of the robot system, or the image acquisition device 100 and the robot system can be designed as two independent devices.

[0068] Regarding the identification information, the workpiece 200 to be processed has a manually marked identification pattern. For example, the worker manually draws the identification pattern on the area of ​​the workpiece 200 that needs to be processed (welded, sprayed). In this way, the first image information obtained by the image acquisition device 100 will contain the identification information accordingly.

[0069] S102: Determine the target processing area in the first image information based on the identification information.

[0070] S103: Perform feature recognition on the target processing area.

[0071] S104: Determine the target motion trajectory of the robot based on the results of feature recognition.

[0072] In this embodiment, the first image information received by the robot system contains identification information. It can be understood that since the identification information is the area to be processed drawn by the worker, the image processing unit can easily determine the target processing area in the first image information and perform feature recognition on the target processing area, thereby eliminating a large number of invalid areas, especially some complex curved surfaces or blurry contours that are difficult to process. This greatly reduces the workload of the image processing unit, improves processing efficiency and accuracy, and makes the system more intelligent and simpler.

[0073] Furthermore, compared to the existing technology where professional workers select and label information in the image after the image acquisition device 100 has acquired it, this embodiment allows workers to draw directly on the workpiece 200 to be processed. This greatly reduces the threshold requirement for workers, and the accuracy of the drawn pattern is also higher.

[0074] Example 2

[0075] like Figure 3 and Figure 4 As shown, this embodiment is a further limitation based on the foregoing embodiment. S102: Determining the target processing area in the first image information according to the identification information includes:

[0076] The type of identification information is determined based on its characteristics, which include one or more of the following: color, line type, and symbol.

[0077] In detail, the identification information includes at least edge identification information and area identification information. The characteristics of the edge identification information are different from those of the area identification information. For example, one of them uses a dotted line, while the other uses a continuous line. Preferably, the two use different colors for identification. Color features are easier for the image processing unit to recognize and obtain, resulting in higher recognition accuracy and less computation. Typically, the design uses a color that is significantly different from the color of the workpiece 200 to be processed for identification.

[0078] It is worth noting that, attached Figure 3 and Figure 4 For the purpose of clear expression, different line types are used to draw different signs. However, in practical applications, various drawing methods can be used to distinguish different types of signs. In particular, using color features to distinguish edge sign information and area sign information is more convenient and accurate.

[0079] If the type of identification information is edge identification information, then the edge where the edge identification information is located is determined as the target processing area;

[0080] If the type of identification information is regional identification information, then the region where the regional identification information is located is determined as the target processing region.

[0081] In this embodiment, the marking information is divided into edge marking information and area marking information. As the name suggests, the worker marks some edges of the workpiece 200 to be processed, which is edge marking information, while some surfaces and local areas of the workpiece 200 to be processed are marked, which is area marking information. Different types of marking information are processed separately, thereby accurately planning the trajectory and further improving processing efficiency and accuracy.

[0082] Example 3

[0083] like Figure 4 As shown, this embodiment is a further limitation based on the aforementioned embodiment two. If the type of identification information is identified as edge identification information, then the edge where the edge identification information is located is determined as the target processing area, including:

[0084] If the edge identification information is determined to be the first identification information, then the edge extending along the first identification information is determined to be the target processing area;

[0085] If the edge identification information is determined to be the second identification information, then the part of the edge covered by the second identification information is determined to be the target processing area.

[0086] In this embodiment, the edge marking information is further designed to include at least a first marking information and a second marking information. The first marking information and the second marking information have different features. For example, both of them use continuous lines, but one of them uses a straight line and the other uses a wavy line. Preferably, the two marking information use different colors. Color features are easier for the image processing unit to identify and obtain, resulting in higher recognition accuracy and less computation. Typically, the marking information is designed to use a color that is significantly different from the color of the workpiece 200 to be processed.

[0087] Specifically, if the edge identification information is determined to be the first identification information, then the edge extending along the first identification information is determined to be the target processing area. That is, the entire edge where the first identification information is located is the target processing area.

[0088] If the edge identification information is determined to be the second identification information, then the portion of the edge covered by the second identification information is determined to be the target processing area. That is, only the area covered by the second identification information within an edge is the target processing area.

[0089] In scenarios where the workpiece 200 to be processed has a long edge, workers do not need to mark the entire edge in a complicated way. Instead, they only need to mark a small part of the edge, which greatly reduces the workers' marking workload and improves work efficiency.

[0090] In scenarios where the actual area to be processed is only a local area along a single edge, workers can also make precise markings to avoid expanding the target processing area and improve accuracy.

[0091] Example 4

[0092] This embodiment is a further limitation based on any of the foregoing embodiments, determining the type of identification information based on the characteristics of the identification information, including:

[0093] If the identification information has the first feature, then the identification information is determined to be edge identification information;

[0094] If the identification information has a second feature, then the identification information is determined to be regional identification information;

[0095] The first feature includes the second feature and the distinguishing feature.

[0096] For example, the second feature is a color feature, such as red, while the area feature is a distinguishing mark used to differentiate between edge markings and area markings. For example, the distinguishing feature is the special symbol "#". In this way, workers mark the edges with red and mark "#" next to the red mark, while marking the area with only red.

[0097] In another embodiment, the second feature may be designed to include both the first feature and the distinguishing feature. For example, such as... Figure 3 and Figure 4 As shown, the first feature is a color feature, for example, the first feature is red, while the area feature is a distinguishing mark used to differentiate between edge markings and area markings, for example, the distinguishing feature is a special symbol "#" or a dashed line. In this way, the worker marks the edge with only red, while marking the area with red, and marks "#" next to the red mark.

[0098] In this embodiment, the edge marking information and the area marking information are designed to have some of the same features. The two are then distinguished by distinguishing features. This reduces the number of features in the marking information, making it easier for the image processing module to accurately identify and process the image. On the other hand, it also facilitates the marking operation for workers, avoids marking errors, reduces the marking difficulty, and improves the marking accuracy.

[0099] Of course, those skilled in the art can also use other methods to distinguish between edge markers and area markers.

[0100] Example 5

[0101] This embodiment further defines the preceding embodiments by including, before determining the target processing area in the first image information based on the identification information, the method further includes:

[0102] If the identification information is valid, it is determined based on the preset conditions. If it is, the target processing area in the first image information is determined based on the identification information.

[0103] In detail, the first image information contains one or more identification information. The validity of each identification information needs to be judged to avoid some marks drawn by workers by mistake or the edges or areas of the workpiece itself in the first image information being misidentified as identification information, which would lead to the wrong processing area being determined by the wrong identification information. This would avoid increasing the workload of the system and improve the accuracy of the system.

[0104] Furthermore, the preset conditions include that the length, width, or area of ​​the region covered by the identification information meets preset values.

[0105] It should be noted that this embodiment does not limit the specific value of the preset value. Those skilled in the art can set it according to specific needs. For example, the area covered by the identification information is more than 5cm to 10cm in length or width, or the area covered by the identification information is more than 1 / 4 of the marked edge, and it can be identified as valid.

[0106] Example 6

[0107] This embodiment is a further limitation based on any of the foregoing embodiments. The first image information contains multiple identification information, and the determination of the robot's target motion trajectory based on the feature recognition result also includes:

[0108] Identify whether each identifier has a corresponding sequential identifier, where...

[0109] Among multiple identification information, those with sequential identification information are used to determine the target's trajectory based on the order corresponding to the sequential identification information;

[0110] If there is no sequential identification information among multiple identification information, the target's trajectory is determined according to a preset order.

[0111] Among multiple identification information, those with sequential identification information take precedence over those without.

[0112] This embodiment further designs the identification information to include the sequence information of trajectory planning, which further enriches the meaning of the identification information. At the same time, it also facilitates the system to plan the trajectory according to the sequence identification information, further reducing the system's processing load and making the trajectory planning more reasonable.

[0113] For a detailed example, the sequential identification information uses numerical identifiers. For instance, a worker might mark multiple lines on the workpiece 200 according to its actual condition, and write a corresponding number next to each mark based on certain rules (e.g., the shortest path rule). Figure 4 As shown, the four edges a, b, c, and g are marked respectively, and a corresponding number is marked next to each mark. The trajectory can then be planned in the order of abcg.

[0114] The preset order can be processed according to the default order from left to right or from top to bottom, or it can be processed according to the size order of the area covered by the marker. Examples will not be given here.

[0115] Example 7

[0116] This embodiment is a further limitation based on any of the foregoing embodiments, performing feature recognition on the target processing region, including: edge detection on the target processing region.

[0117] In detail, after the robot system determines the target processing area based on the identification information in the first image information, the robot system performs edge detection on the target processing area. By determining these edges, the outline of the target processing area can be determined, which enables the robot to more accurately identify and process the effective target area.

[0118] Edge detection is a fundamental method in image processing and computer vision. Its purpose is to identify points in a digital image where brightness changes are significant. Significant changes in image attributes often reflect important events and shifts in those attributes. Those skilled in the art can process target areas using existing edge detection methods; therefore, specific edge detection methods will not be elaborated upon here.

[0119] Example 8

[0120] This embodiment further defines the preceding embodiments by including, before receiving the first image information of the workpiece 200 to be processed, the following steps are also included:

[0121] Receive the second image information of the workpiece 200 to be processed;

[0122] The outline of the workpiece 200 to be processed is identified based on the information in the second image;

[0123] The identified outline of the workpiece 200 to be processed is matched with the visual feature model in the database. The visual feature model includes the outline of the workpiece 200 to be processed and the result of feature recognition.

[0124] If a match is successful, the target's motion trajectory is determined based on the matched visual feature model.

[0125] This embodiment further designs the robot system to have a database. It can first match the workpiece contour with the data in the database. When the match is successful, it means that the system has previously performed image recognition and processing on the same type of workpiece. In this way, the data in the database can be directly called without repeating the work, which further reduces the workload of the system and improves work efficiency.

[0126] Example 9

[0127] This embodiment is a further limitation based on the aforementioned Embodiment Eight. After performing feature recognition on the target processing region, it also includes:

[0128] The outline of the workpiece 200 to be processed is identified based on the information in the first image;

[0129] A visual feature model of the workpiece 200 is generated based on the results of feature recognition and the outline of the workpiece 200 to be processed.

[0130] The generated visual feature model is stored in the database.

[0131] This embodiment records the workpieces 200 that are not yet entered into the database so that when processing the same type of workpieces again, repetitive work can be avoided and work efficiency can be improved.

[0132] Example 10

[0133] This embodiment further defines the preceding embodiments by including, between receiving the first image information of the workpiece 200 to be processed, the following:

[0134] Receive identification prompt request;

[0135] Generate and output identification prompt information based on the identification prompt request.

[0136] To facilitate workers' marking and ensure the system can correctly identify the markings, workers can send a prompt request to the system before marking. The system will then inform the worker of the meaning of each marking based on the prompt request, making the system more user-friendly and providing a better user experience.

[0137] For example, the signage information may include one or more of images, text, and sounds.

[0138] A specific embodiment

[0139] One object of the present invention is to provide a robot system, more specifically, a robot vision-assisted system. This system can improve the intelligence of robot vision, enabling the robot to more intelligently and accurately identify and process effective targets, and can further reduce the practical threshold of robot use and improve robot efficiency.

[0140] Furthermore, the invention utilizes a database-based graphical comparison method. Any workpiece feature recorded in the database is used to create a feature model. When processing workpieces with the same features, the robot will reference that workpiece feature model from the database to perform the corresponding processing. This further improves the robot's working efficiency and convenience.

[0141] A robot vision-assisted system includes a robot, an image acquisition device 100, an image processing module, and a database system.

[0142] The robot provides basic functions such as trajectory planning and motion. The image acquisition device 100 can acquire images and send the image data to the robot through a video interface. The image processing module can receive image signals, perform edge detection and feature recognition, and construct a visual feature model of the scanned object. The database system stores the visual features of the current workpiece and uses them for visual comparison and visual feature model fitting and reuse when processing the next workpiece.

[0143] Before identifying the workpiece 200, the worker marks the workpiece 200, and the image acquisition device 100 acquires images of the calibrated workpiece to obtain first image information, thereby providing the robot with richer and more accurate processing information.

[0144] Regarding calibration, in detail, different colors or marks are marked on the target processing area or its edges to help the robot accurately identify the target processing area.

[0145] The identification information includes two types: area identification information and edge identification information.

[0146] like Figure 3 As shown, workers use red to mark certain areas of the entire workpiece and add a "#" symbol next to the mark. This information is the area identification information. The "#" symbol helps the robot to identify and process the area and edge identification information.

[0147] like Figure 4 As shown, the worker uses red and green to mark parts of the edges of the entire workpiece. The marking information obtained by the red marking is the first marking information, and the robot will process the entire edge marked with the color. The marking information obtained by the green marking is the second marking information, and the robot will process the edge of the currently marked area.

[0148] Furthermore, the identification information also includes sequence information, such as writing a number next to each label to indicate the order in which the robot processes the calibrated area.

[0149] The robot prioritizes processing labeled information with sequence information, and processes labels without sequence information in the default order of left to right and top to bottom.

[0150] The following description, in conjunction with the accompanying drawings, details this embodiment.

[0151] In this embodiment, the calibrated workpiece is scanned. The scanned information is processed by the image processing module, a model is built and saved to the database. At the same time, a motion trajectory is generated based on the model, and then the robot performs the corresponding work according to the predetermined trajectory.

[0152] See Figure 3 A red marker "A" is added between different areas of the workpiece to guide the robot system to process the area marked by the red marker. The marker "#" outside the area instructs the robot to process the target area according to the area marker information.

[0153] See Figure 4 The workpiece was calibrated along four edges: a, b, c, and g. Edge a was calibrated in green, and the robot's trajectory was limited to the edge of the calibrated area. The other three edges were calibrated in red, and the robot's trajectory covered the entire edge.

[0154] Furthermore, according to the given priority (1-2-3-4), the robot will plan its trajectory in the order of abcg.

[0155] See Figure 5 It is a system flowchart.

[0156] S201: Image acquisition device 100 scans workpiece 200 to be processed; for example, image acquisition device 100 scans workpiece 200 to be processed to obtain second image information.

[0157] S202: Image feature recognition and processing; for example, the image processing module recognizes and processes the second image information to obtain the outline of the workpiece 200 to be processed;

[0158] S203: Results of matching image feature recognition and processing and database;

[0159] S204: If the match is successful, extract all feature data from the database and proceed to step S208;

[0160] S205: Otherwise, calibrate the workpiece 200 to be processed;

[0161] S206: Image feature recognition and processing;

[0162] S207: Save image features to the database;

[0163] S208: Generate robot motion trajectory based on image features.

[0164] After the workpiece 200 is calibrated, the robot's vision scanning program is started. The image acquisition device 100 scans the workpiece 200, and the image processing algorithm acquires the image boundaries and all calibration information. Based on this information, a model of the workpiece is constructed. The database system saves the current workpiece model data to the database for comparison and confirmation by the next tool.

[0165] The robot then plans its trajectory and moves according to the generated workpiece model. If the workpiece has already been saved in the database, the next time a workpiece with the same graphic features is processed, the workpiece does not need to be calibrated. The vision module will match the scanned feature data with the database and process the workpiece according to the matched model parameters.

[0166] like Figure 6 As shown, the present invention also provides a control device 300, comprising:

[0167] Memory 310, on which programs or instructions are stored;

[0168] Processor 320 executes programs or instructions to implement the steps of the control method for the robot system as described in any of the foregoing embodiments.

[0169] The present invention also provides a robot system, including: a robotic arm, the robotic arm being communicatively connected to a control device 300.

[0170] The present invention also provides a readable storage medium having a program or instructions stored thereon, which, when executed by processor 320, implement the steps of the control method of the robot system as described in any of the foregoing embodiments.

[0171] Although this embodiment has been described with reference to several typical implementations, it should be understood that the terminology used is descriptive and exemplary, and not restrictive. Since this embodiment can be embodied in many forms without departing from the spirit or essence of the embodiment, it should be understood that the above embodiments are not limited to any of the foregoing details, but should be interpreted broadly within the spirit and scope defined by the appended claims. Therefore, all variations and modifications falling within the scope of the claims or their equivalents should be covered by the appended claims.

Claims

1. A control method for a robot system, characterized in that, Includes the following steps: Receive first image information of the workpiece to be processed, wherein the first image information contains one or more identification information; The target processing region in the first image information is determined based on the identification information; Feature recognition is performed on the target processing region; The robot's target motion trajectory is determined based on the results of feature recognition. Determining the target processing region in the first image information based on the identification information includes: The type of the identification information is determined based on the characteristics of the identification information, wherein the characteristics include one or more of color, line type, and symbol; If the type of the identification information is edge identification information, then the edge where the edge identification information is located is determined to be the target processing area; If the type of the identification information is regional identification information, then the region where the regional identification information is located is determined to be the target processing region.

2. The control method for the robot system according to claim 1, characterized in that, If the type of the identification information is identified as edge identification information, then the edge where the edge identification information is located is determined to be the target processing area, including: If the edge identification information is determined to be the first identification information, then the edge extending along the first identification information is determined to be the target processing area; If the edge identification information is determined to be the second identification information, then the portion of the edge covered by the second identification information is determined to be the target processing area.

3. The control method for the robot system according to claim 1 or 2, characterized in that, The method of determining the type of the identification information based on its characteristics includes: If the identification information has the first feature, then the identification information is determined to be the edge identification information; If the identification information has a second feature, then the identification information is determined to be the area identification information; Wherein, the first feature includes the second feature and the distinguishing feature, or the second feature includes the first feature and the distinguishing feature.

4. The control method for the robot system according to claim 1 or 2, characterized in that, Before determining the target processing region in the image information based on the identification information, the method further includes: If the identification information is valid, it is determined according to preset conditions. If it is, the step of determining the target processing area in the image information based on the identification information is executed. The preset conditions include the length, width, or area of ​​the region covered by the identification information meeting preset values.

5. The control method for the robot system according to claim 1 or 2, characterized in that, The image information contains multiple identification information, and the process of determining the robot's target motion trajectory based on the feature recognition result further includes: Identify whether each of the identified information pieces has corresponding sequential identified information, wherein, The target trajectory is determined based on the order of the sequence identification information among the multiple identification information. The target trajectory is determined according to a preset order if none of the multiple identification information items have sequential identification information. Among the multiple identification information, those with sequential identification information take precedence over those without sequential identification information.

6. The control method for the robot system according to claim 1 or 2, characterized in that, The aforementioned feature recognition of the target processing region includes: Edge detection is performed on the target processing area.

7. The control method for the robot system according to claim 1 or 2, characterized in that, Before receiving the first image information of the workpiece to be processed, the process also includes: Receive the second image information of the workpiece to be processed; The outline of the workpiece to be processed is identified based on the second image information; The identified outline of the workpiece to be processed is matched with a visual feature model in the database, the visual feature model including the outline of the workpiece to be processed and the result of feature recognition. If a match is successful, the target's motion trajectory is determined based on the matched visual feature model.

8. The control method for the robot system according to claim 7, characterized in that, After performing feature recognition on the target processing region, the method further includes: The outline of the workpiece to be processed is identified based on the first image information; A visual feature model of the workpiece to be processed is generated based on the result of feature recognition and the outline of the workpiece to be processed. The generated visual feature model is stored in the database.

9. A control device, characterized in that, include: A memory, on which programs or instructions are stored; A processor that executes the program or instructions to implement the steps of the control method for the robot system as described in any one of claims 1 to 8.

10. A robot system, characterized in that, include: robotic arm; The control device of the robot system as described in claim 9 is communicatively connected to the robotic arm.

11. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the steps of the control method for the robot system as described in any one of claims 1 to 8.

Images