JOINTING SYSTEM FOR SECURING THE END ENDS OF A SHEET PRODUCT

A robotic unit with grippers and visual perception system addresses ergonomic challenges in joining thick, rigid sheet products by adapting to material stiffness, ensuring precise and efficient alignment and fixation of end ends.

FR3147136B1Active Publication Date: 2026-05-08MICHELIN & CO (CIE GEN DES ESTAB MICHELIN)
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
FR · FR
Patent Type
Patents
Current Assignee / Owner
MICHELIN & CO (CIE GEN DES ESTAB MICHELIN)
Filing Date
2023-03-31
Publication Date
2026-05-08

AI Technical Summary

Technical Problem

Existing joining systems struggle to handle and join thick, rigid sheet products like tire treads used in large vehicles due to ergonomic challenges and the need for manual operations, with prior solutions failing to account for variations in material stiffness and stability.

Method used

A robotic unit equipped with grippers and a visual perception system that identifies product profiles, characterizes deformations, and controls movements to systematically grasp and join the ends of sheet products, using tactile sensors to adapt to material stiffness and geometric rigidity.

Benefits of technology

Enables efficient and ergonomic joining of thick, rigid sheet products by aligning and fixing end ends with high precision, reducing manual labor and improving handling efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000023_0000
    Figure 00000023_0000
  • Figure 00000023_0001
    Figure 00000023_0001
  • Figure 00000024_0000
    Figure 00000024_0000
Patent Text Reader

Abstract

JOINTING SYSTEM FOR ATTACHING TERMINAL ENTREMITIES OF A SHEET PRODUCT The invention relates to a joining system (100) for attaching terminal ends (102) of a sheet product (104), the joining system comprising a detection unit which captures images of the sheet product and a processor which processes the images by imposing a geometric mesh (137) on surfaces of the sheet product to represent nodes identifying an upper end (106), a lower end (108), first parts (110, 116) of edge, second parts (112, 118) of edge and central parts (114, 120) of the terminal ends.The joining system comprises a robotic unit equipped with gripping devices (124, 126), pivoting extended arms (128, 130), and grippers (134, 136) to receive instructions from the processor in order to systematically grasp, deform, and move the upper and / or lower end in translation to align and join nodes representing central parts, first edge parts, and second edge parts. Figure for the abstract: Fig. 1.
Need to check novelty before this filing date? Find Prior Art

Description

Title of the invention: JOINTING SYSTEM FOR SECURING THE END ENDS OF A SHEET PRODUCT technical field

[0001] The invention relates to a joining system for fixing end ends of a sheet product and, in particular cases, for joining parts of tire treads to form joined tire treads during tire manufacturing operations. Context

[0002] Several joining systems are known in the trade for attaching small product components such as tires for passenger cars, two-wheelers, and tricycles (e.g., motorcycles and motorized means of transport), and similar applications for which there are known automation solutions including robotic units for applying low-rigidity products that do not require handling, such as large, heavy products. For example, European Patent No. EP1656250B1 introduces a "systematic" way of identifying the length, width, and position of tread segments to obtain a stable joining result. However, in industry, a variation in the stiffness of the tread segment material can affect the stability of robotic unit grippers and can induce variations in the joining result.Although prior art solutions describe robotic units for handling thinner sheet products, these solutions do not describe the joining of end ends (see, for example, European Patent No. EP2516142B1, US Publication No. US20160266569A1, and US Patent No. US10377101B2). Other prior art solutions describe methods and devices for manufacturing laminated articles such as multi-layered treads (see, for example, Korean Patent Application No. KR20070073739A). However, such solutions make no mention of using robotic units to handle thick products or of means for joining such products together.

[0003] On the contrary, the manufacture of large tires (including, but not limited to, those used in truck and bus transport, agricultural applications, mining applications, and similar applications) requires the handling of heavy products with high rigidity and large dimensions, and commonly involves numerous manual operations, which presents technical and economic difficulties for the handling of such products. heavy by automatic machines. The tasks involved in such handling operations are arduous, involving moderate to heavy loads and ergonomically difficult movements that might require robotic operations including one or more models assisted by software or algorithms (see for example Mohammadreza Shetab-Bushehri et al., "As-Rigid-as-Possible Shape Servoing", IEEE Robotics and Automation Letters (Volume 7, No. 2, April 2022) (https: / / ieeexplore.ieee.org / document / 9691867).

[0004] Certain solutions describe a method and apparatus for joining a first tread portion and a second tread portion to form a joined tread, each tread portion comprising a section of tire tread extending lengthwise from an end end (see Applicant's U.S. Patent No. US9573330B2). Such solutions are particularly useful for retreading applications, which involve directing the end ends of tires toward each other and making them interact vigorously with a joining elastomer material disposed between the end ends by means of dies using hydraulic or pneumatic pressure.

[0005] Therefore, the invention described herein relates to a joining system comprising a robotic unit including grippers adapted to a product to be handled, and a visual perception system that locates the products, characterizes their deformations, and controls the movements of the robotic unit throughout the joining operation. The joining system is used as an ergonomic assistant for a tread joining platform on large machines and can be applied to various product profiles of different thicknesses and taking into account rigidity by adapting its algorithms with a characterization of deformations based on variations in material properties. Summary of the invention

[0006] The invention relates to a joining system for fixing the end ends of a sheet product having a profile defined by parameters of a predetermined length, a predetermined width and a predetermined thickness, the end ends including an upper end, a lower end, first edge parts, second edge parts and central parts defining end surfaces of the end ends, the joining system comprising:

[0007] - at least one detection unit configured to capture one or more images in order to identify the product profile parameters in sheets;

[0008] - at least one processing unit comprising one or more software programs or algorithms, configured to process images of the sheet product by imposing a geometric mesh on surfaces of the sheet product to represent nodes identifying terminal ends including the top end, bottom end, first edge parts, second edge parts and central parts; and

[0009] - a robotic unit comprising at least two gripping devices, elongated pivoting arms and grippers, configured to receive instructions from the processing unit to systematically grasp, deform and move in translation the upper end and / or lower end to align and join nodes representing the central part, the first edge part and the second edge part of the upper end to the central part, the first edge part, the second edge part of the lower end of the terminal ends.

[0010] In certain embodiments of the junction system, the processing unit includes an image processing module deploying one or more deformation models based on visual or shape servoing.

[0011] In certain embodiments of the joining system, the grippers of the robotic unit include one or more tactile sensors configured to detect an effort required to deform the sheet product with respect to a stiffness expressed as a function of a geometric stiffness and a modulus of one or more materials used in the sheet product.

[0012] In certain embodiments of the joining system, the image processing module is configured to feed the deformation model with information including a stiffness or force required to deform the product into sheets, mesh data defining terminal end nodes including the top end, bottom end, first edge parts, second edge parts and central parts.

[0013] In certain embodiments of the joining system, the deformation model is configured to allow the image processing module to instruct the robotic unit to systematically deform and move in translation the first edge part, the second edge part and the central part of the upper end to align and join nodes of the upper end to the central part, the first edge part and the second edge part of the lower end.

[0014] In certain embodiments of the joining system, the image processing module is configured to assign a weighting to nodes representing central parts to be joined as a priority, followed by a weighting of nodes representing of the first edge parts and the second edge parts of the terminal extremities.

[0015] In certain embodiments of the junction system, the detection unit includes one or more sensors used to detect two-dimensional (2D) and / or three-dimensional (3D) images, to perform 3D relief perception and / or other types of detection.

[0016] In some embodiments of the joining system, the sheet product may be a tire tread, rubber tracks or products of a similar nature.

[0017] In certain embodiments of the joining system, the grippers include a movable jaw having at least two retaining fingers of defined length capable of moving back and forth in a direction orthogonal to the longitudinal axis 1-1 of the grippers relative to a fixed jaw to facilitate a firm grip on the upper end and / or the lower end of the sheet product placed between them.

[0018] The invention also relates to a joining method for fixing the end ends of a sheet product having a profile defined by parameters of a predetermined length, a predetermined width and a predetermined thickness, the end ends including an upper end, a lower end, first edge parts, second edge parts and central parts, thus defining end surfaces of the end ends, the joining method comprising:

[0019] - a step of capturing one or more images to identify the parameters of product profile in sheets;

[0020] - a step of processing images of the product in sheets by imposing a mesh geometric on surfaces of the sheet product to represent nodes identifying terminal ends including a top end, a bottom end, first edge parts, second edge parts and central parts, by at least one processing unit comprising one or more software programs or algorithms; and

[0021] - a step of giving instructions to a robotic unit, equipped with at least two gripping devices, of pivoting extended arms and grippers, to systematically grasp, deform and move in translation the upper end and / or the lower end to align and join nodes representing the central part, the first edge part and the second edge part of the upper end to the central part, the first edge part, the second edge part of the lower end of the terminal ends.

[0022] In certain embodiments of the joining process, a step is taken comprising detecting an effort required to deform the product into sheets with respect to a rigidity expressed as a function of a geometric rigidity and a modulus of one or more materials by deploying one or more tactile sensors in the grippers of the robotic unit.

[0023] In certain embodiments of the joining process, a step is involved comprising feeding a deformation model with information including a stiffness or force required to deform the product into sheets, mesh data defining terminal end nodes including the upper end, the lower end, the first edge parts, the second edge parts and the central parts.

[0024] In certain embodiments of the joining process, the step involves instructing the robotic unit, using the deformation model, to systematically deform and move in translation the first edge part, the second edge part and the central part of the upper end to align and join the nodes of the upper end to the central part, the first edge part and the second edge part of the lower end.

[0025] In certain embodiments of the joining system, a step is taken comprising assigning a weight to nodes representing central parts to be joined as a priority, followed by a weighting of nodes representing first edge parts and second edge parts of the terminal ends.

[0026] Other aspects of the invention will become apparent from the following detailed description. Brief description of the drawings

[0027] The nature and various advantages of the invention will become more apparent upon reading the following detailed description in conjunction with the accompanying drawings, in which the same numerical references denote identical parts in all drawings, and in which:

[0028] [Fig.1] Fig.1 represents a schematic view of one embodiment of the junction system of the present invention.

[0029] [Fig.2] Fig.2 represents a perspective view of an embodiment of a tread of the joining system of the present invention.

[0030] [Fig.3] The [Fig.3] represents a partial perspective view of an embodiment of a robotic system of the [Fig.1] incorporating gripping devices comprising pivoting extended arms and grippers, according to the present invention.

[0031] [Fig.4] [Fig.4] represents a side view of an embodiment of gripping a tread by the grippers of [Fig.3], according to the present invention.

[0032] [Fig.5] [Fig.5] represents a top view of another embodiment of gripping a tread by the grippers of [Fig.3], according to the present invention.

[0033] [Fig.6] [Fig.6] represents a perspective view of the deformation of the terminal ends of a tread by the grippers of [Fig.3], according to the present invention.

[0034] [Fig.7] [Fig.7] represents a perspective view of the translation of terminal ends of a tread by the grippers of [Fig.3], according to the present invention.

[0035] [Fig.8] [Fig.8] represents a perspective view of the joining of central parts of a tread by the grippers of [Fig.3], according to the present invention.

[0036] [Fig.9] The [Fig.9] represents a perspective view of the joining of terminal ends of a tread by the grippers of the [Fig.3], according to the present invention.

[0037] [Fig. 10] Fig. 10 represents a flowchart describing a method for joining the end caps of a tread according to the present invention. Detailed description

[0038] The present invention comprises a joining system and method for securing end ends of a sheet product for gripping and securing end ends of the sheet product with high rigidity. The sheet product is defined as a product of a predetermined profile, length, width, and thickness, exhibiting high rigidity that could make handling tasks difficult, involving moderate to heavy handling with ergonomically challenging movements. In several examples, the sheet product may be tire treads, rubber tracks, or sheet products of a similar nature. For the purposes of the present invention, the sheet product may be referred to as a tread for the sake of explaining the invention; however, the invention is not intended to be limited to tire treads.Due to the use of the methods and devices of the invention, a firm fixation of the end edges of a tread is efficiently achieved for products of high rigidity and thickness, compared to existing technologies.

[0039] The methods and devices described herein are used to join two opposite ends of tread sections to form a tread Tread sections are generally longitudinal portions of a tread intended for application to a tire casing. Each tread section has a predetermined length, width, and thickness. A tread section may include a tread pattern on one of the contact surfaces. It may also include any tread features, such as blocks and / or ribs separated by grooves and / or sipes. The first and second tread sections may be associated with the same tread (i.e., different parts or segments of the tread) or with separate, distinct treads.For example, the end caps of a single tread can be joined to form a continuous tread ring. As a further example, separate treads (i.e., segments, sections, or lengths of tread) can be joined to form a single unit tread comprising multiple joined tread segments. The resulting tread portion may be at least partially or fully vulcanized, although a raw or unvulcanized tread portion may be used.

[0040] The end edges of the tread portion form the end of the tread and comprise an end surface. The end surface comprises a cross-sectional area of ​​the tread extending laterally across the width of the tread and having a height extending through the thickness of the tread. The end surface may extend across the width of the tread in a direction normal to the longitudinal direction of the tread or at any other oblique angle to the longitudinal direction. Furthermore, the end surface may extend laterally along a linear or non-linear path.Similarly, the height of the terminal end surface can extend through the tread thickness in any direction, including, for example, a direction normal to the longitudinal direction of the tread, and along any linear or nonlinear path. Since the tread may include a tread pattern extending into the tread thickness, the tread end surface may include voids arranged within the tread thickness and facing inwards relative to an external cross-sectional profile.

[0041] The longitudinal location where the end end is formed along each tread portion is chosen to produce an end end with a profile that generally matches the profile of the other end end to which it will be joined. For example, it is possible to select and form, or otherwise produce, end ends that generally match (i.e., their cross-sections, profiles, and / or perimeters generally match). This results in a tread joint that is consistent with adjacent portions or details of the joined tread and with the overall tread pattern of the joined tread.In other words, by forming the end ends in such a way that they generally agree, the joined or assembled tread can comprise a tread pattern that is not appreciably disturbed at the junction where the tread details of opposite end ends are generally aligned with respect to a tread height (i.e., thickness) and width.

[0042] The arrangement of the end ends results in a joined or assembled tread in which the joined tread portions generally extend in the same longitudinal direction, which may extend linearly like a tread ribbon or annularly in the form of a tread ring. Alternatively, the location along any tread length where the end end is formed may be selected not only to generally match an end end of the tread portion to be joined, but also to select a location enabling the tread to be properly joined.

[0043] With reference to Figures 1 and 2, a joining system 100 according to the present invention is presented. The joining system 100 is defined for fixing end ends 102 of a tread 104 made of rigid materials. The end ends 102 of the tread 104 comprise an upper end 106 and a lower end 108 with predetermined profile parameters including, but not limited to, length, width, and thickness. In addition, each of the upper end 106 and the lower end 108 of the tread 104 comprises end surfaces defining first edge portions 110, 116, second edge portions 112, 118, and central portions 114, 120 as shown in [Fig. 2].

[0044] According to the present invention, the joining system 100 is provided to systematically grasp and move in translation the upper end 106 and / or the lower end 108 to align and join the central part 114, the first edge part 110, and the second edge part 112 of the upper end 106 to the central part 120, to the first edge part 116, and to the second edge part 118 of The edge of the lower end 108 of the end ends 102. In one embodiment, the joining system 100 may not depend on the predetermined profile parameters of the end ends 102 of the tread 104 because it is independent of these parameters. The joining system 100 is configured to join without limitation on the predetermined profile parameters of the end ends 102.

[0045] Referring to Figures 1 and 3, the joining system 100 comprises a mobile robotic unit (or "robot") 122 equipped with at least two gripping devices 124, 126 supported respectively by pivoting elongated arms 128, 130. The gripping devices 124, 126 extend from the pivoting elongated arms 128, 130 to a free end 132, with grippers 134, 136 arranged along a longitudinal axis 1-1 (see [Fig. 3]). The robotic unit 122 is moved such that the grippers 134, 136 can grasp the end ends 102 of the tread 104 targeted by the joining system 100 during the fastening process.By "mobile," it is understood that the robotic unit 122 can be set in motion either by integrated means of movement (for example, one or more integrated motors) or by non-integrated means of movement (for example, one or more autonomous mobile carts or other equivalent means of mobility). It is understood that the robotic unit 122 can be fixed to a ceiling, a wall, or any support that allows the connecting system 100 to perform the fixing process of the invention. It is understood that the robotic unit 122 can be a conventional industrial robot or a collaborative robot, or even a Delta robot or a tethered robot having at least 6 degrees of freedom. The robotic unit 122 can be used interchangeably with two gripping devices 124, 126, pivoting extended arms 128, 130, and grippers 134, 136, as these are part of the robotic unit 122.

[0046] Referring to [Fig. 3], the gripping devices 124, 126 are supported by pivoting elongated arms 128, 130, each comprising a platform of predetermined length between a fixed end and an opposite free end. The fixed end may include an adapter that allows the platform to be removably attached to the robotic unit 122. Attachment of the platform to the robotic unit 122 can be accomplished by screwing the adapter onto the free end of the gripping device 124, 126. It is understood that the platform can be attached to the robotic unit 122 by any known fastening method (including, but not limited to, welding, bonding, and equivalent methods).

[0047] The grippers 134, 136 comprise a movable jaw 138 and a fixed jaw 140. The movable jaw 138 may comprise at least two fingers 142 of The grippers 134, 136 are designed to maintain a defined length and move back and forth in a direction orthogonal to the longitudinal axis 1-1 of a fixed jaw 140. This facilitates a firm grip on the upper end 106 and / or the lower end 108 of the sheet product 104 placed between them. The reciprocating motion of the moving jaw 138 is achieved by an actuator Vi38, which is actuated by pressurized fluid (e.g., compressed air) from a conduit (not shown). In another example, the actuators Vi can be actuated by electrical power or alternative power sources. Furthermore, the grippers 134, 136 are also configured to be pivoted about the longitudinal axis 1-1 by actuators Vi39 actuated by a mechanism similar to that of Vi38. The Vi38 and V139 actuators are selected from commercially available actuators.Thanks to the movable jaw 138 and the fixed jaw 140, the grippers 134, 136 perform a gripping action that holds the upper end 106 and / or the lower end 108 of the tread 104 while the grippers 134, 136 move between an interaction position in which the movable jaw 146 and / or the fixed jaw 140 is in its interaction position, and in which the gripper 134, 136 is positioned to grasp the upper end 106 and / or the lower end 108 of the tread 104, and a junction position in which the grippers 134, 136 move the upper end 106 and / or the lower end 108 in translation to place it in a junction target area to fix the upper end 106 to the lower end 108 of the tread bearing 104. .

[0048] The robotic unit 122 includes a sensing system that employs one or more sensors (not shown) that capture information about the physical environment around the robotic unit 122. In the following description, the terms "sensor," "photographic equipment," "camera," and "optical sensor" may be used interchangeably and may refer to one or more devices configured to detect two-dimensional (2D) and / or three-dimensional (3D) images, to perform 3D depth perception, and / or other types of physical environment sensing. In one example, the sensors of the sensing unit could be any commercially available RGB-D camera with a frame resolution of 1920 x 1080 achieving a frame rate of 30 fps or frames per second. In another example, the sensor(s) could be a laser profilometer.The sensors of the detection system incorporated into the robotic unit 122 can be attached to at least one of the pivoting extended arms 128, 130 and / or the grippers 134, 136 of the gripping devices 124, 126. Alternatively, the . Sensors of the detection system can be incorporated away from the robotic unit 122 covering a field of view of the junction system 100.

[0049] The sensor(s) of the detection system of the junction system 100 detect the presence of a tread arrangement 104 in the field of view of the camera, which triggers the camera to capture the image of the tread 104. In some embodiments of the junction system 100, the sensor is triggered when the tread 104 enters the field of view of the camera on the background of the captured image.

[0050] The sensing system can determine information relating to the physical environment that can be used by a control system (which includes, for example, software for directing the movements of the robotic unit 122). The control system may reside on the robotic unit 122 or it may be in remote communication with the robotic unit 122. In some embodiments of the junction system 100, one or more 2D or 3D sensors mounted on the robotic unit 122 (including, but not limited to, navigation sensors) may be integrated to form a digital model of the physical environment (including, where applicable, the side(s), floor, and ceiling). Using the resulting data, the control system can cause the robotic unit 122 to move in order to navigate between the gripping positions of at least one of the end ends 102 of the tread 104.

[0051] The sensors of the detection system send captured profile parameters of the tread 104 shown in [Fig. 2] and of the physical environment around the robotic unit 122 of the junction system 100 to at least one processing unit or to at least one processor. The term "processor" (or alternatively the term "programmable logic circuit") refers to one or more devices capable of processing and analyzing data and comprising one or more software packages for processing such data (for example, one or more integrated circuits known to those skilled in the art as being included in a computer, one or more controllers, one or more microcontrollers, one or more microcomputers, one or more programmable logic controllers (or "PLCs"), one or more application-specific integrated circuits, one or more neural networks and / or one or more other known equivalent programmable circuits).The processing unit includes software for processing data captured by the subsystems associated with the junction system 100 (and the corresponding data obtained) as well as software for identifying and locating variances and identifying their sources for correction.

[0052] A person skilled in the art will recognize that many image processing techniques can be used to select and determine the parameters of the targeted tread patterns. Several commercially available image processing systems can be used.

[0053] The sensors of the detection unit capture one or more images of the tread 104. The captured image(s) are transferred and stored as captured images in the memory of the processing unit. The processing unit, which executes instructions from an image processing module of the processing unit, analyzes the image to determine one or more parameters of the tread 104 being imaged. The parameters of the tread 104 are the length, width, thickness, and information related to the end edges 102, including the upper edge 106, the lower edge 108, the first edge portions 110, 116, the second edge portions 112, 118, and the central portions 114, 120 defining the end surface of the end edges 102.

[0054] With reference to Figures 4 and 5, the grippers 134, 136 can grasp the terminal ends 102 of the tread 104 in several combinations which are not limited to the arrangement shown in [Fig.4], the gripper 134 being intended to grasp the first edge part 110 of the upper end 106 and the gripper 136 being intended to grasp the second edge part 112 of the upper end 106 located opposite the first edge part 110. In another example, the grippers 134, 136 can grasp first parts 110, 116 of edge, second parts 112, 118 of edge or central parts 114, 120 of the upper end 106 and lower end 108 together on the same side in view of joining terminal ends 102 of the tread 104 as illustrated in [Fig.5].Furthermore, the grippers 134, 136 are equipped with tactile sensors 152 to determine the contact force required for deformation based on the stiffness of the tread 104. The stiffness of the tread 104 can be expressed in terms of its geometric rigidity and the modulus of one or more materials used. The tactile sensors 144 are designed to detect forces within the tread 104, as each material has its own stiffness properties and resists forces in returning to its original shape after deformation due to elasticity. The higher the modulus of the materials of the tread 104, the greater the contact force required by the grippers 134, 136 for deformation.

[0055] The image processing module processes the images of the tread 104 to impose a geometric mesh 137 on surfaces of the tread 104 to represent nodes identifying end ends 102 including the upper end 106, the lower end 108, the first edge parts 110, 116, the second edge parts 112, 118 and the central parts 114, 120, as illustrated in Figures 4 and 5. The mesh 137 and the identification of the nodes allow the robotic unit 122 to be manipulated systematically to control the movement of the gripping devices 124, 126, the pivoting extended arms 128, 130 and the grippers 134, 136 accordingly to deform, translate or move, and join the terminal ends 102 of the tread 104.

[0056] With reference to Figures 6 to 9, the image processing module of the processing unit may include deformation models based on visual servoing or shape servoing mechanisms. The stiffness of the tread 104 at the end ends 102 detected by the tactile sensors 152 (see Figures 4, 5) is transferred to the image processing module of the processing unit. The image processing module feeds the deformation model with information regarding stiffness expressed as a function of a geometric stiffness and a modulus of one or more materials used in the tread 104, and with mesh data defining nodes identifying terminal ends 102 including the upper end 106, the lower end 108, the first parts 110, 116 of the edge, the second parts 112, 118 of the edge and the central parts 114, 120.The robotic unit 122 is configured to receive instructions from the processing unit to systematically grasp, move in translation the upper end 106 and / or the lower end 108 to align and join nodes representing the central part 114, the first edge part 110 and the second edge part 112 of the upper end 106 to the central part 120, to the first edge part 116, to the second edge part 118 of the lower end 108 of the terminal ends 102.

[0057] In an example of the present invention, the grippers 134, 136 are configured to sequentially join the central part 114, the first edge part 110 and the second edge part 112 of the upper end 106 to the central part 120, to the first edge part 116, to the second edge part 118 of the lower end 108 of the tread 104. In this configuration as shown in [Fig.[6], the grippers 134, 136 are pivoted by a closed control mechanism according to a rigidity of the tread 104 received by touch sensors 152, the image processing module sends as an instruction to the actuator V146 the amount of force necessary to deform the first part 110 of the edge and the second part 112 of the edge of the upper end 106 in such a way that nodes representing central parts 114 and 120 are assigned a weighting by the image processing module to be joined in priority.

[0058] Furthermore, as shown in Figures 7, 8 and 9, the gripping devices 124, 126 and the pivoting extended arms 128, 130 are further manipulated to perform a translational movement from an initial position (see [Fig. 6]) where the upper end 106 is away from a junction position with the lower end 108 until a desired position (see [Fig.7]) in which the upper end 106 is sufficiently close to the lower end 108 of the tread 104, in accordance with the instruction of the image processing module of the processing unit, so that the central parts 114, 120 are joined first as shown in [Fig.8].The grippers 134, 136 are further pivoted by actuators by means of a control feedback mechanism to remove the deformation of the first edge part 110 and the second edge part 112 of the upper end 106 in order to return to the initial shape of the tread 104 such that nodes representing the first edge part 110, the second edge part 112 of the upper end 106 are joined to nodes representing the first edge part 116, the second edge part 118 of the lower end 108 as shown in [Fig.9].

[0059] In other embodiments, the image processing module instructs the robotic unit 122 to systematically grasp, deform and move in translation the upper end 106 and / or the lower end 108 to align and join nodes representing the central part 114, the first edge part 110 and the second edge part 112 of the upper end 106 to the central part 120, to the first edge part 116, to the second edge part 118 of the lower end 108 in any order, without being limited to a particular sequence.

[0060] The image processing module can deploy one or more machine learning models using the captured parameters of the tread 104 from the sensors to identify terminal ends 102 of the tread 104. Although the embodiments are described here with respect to the use of neural networks (and specifically convolutional neural networks (CNNs)) as a machine learning model, other types of machine learning models can be used.These include, but are not limited to, models employing linear regression, logistic regression, decision trees, support vector machines, naive Bayesian models, K-nearest neighbors (kNN), where K denotes a grouping, random forests, dimensionality reduction algorithms, gradient descent algorithms, neural networks (e.g., autoencoders, CNNs, RNNs, perceptrons, logarithmic short-term memory (LSTM), Hopfield, Boltzmann, deep belief networks, deconvolution, generative adversarial networks (GANs), etc.) and their complements and equivalents. The CNN(s) can be trained using field-reality data generated using sensor data representative of the motion of grasping devices.124, 126 the robotic unit 122, including the positioning of the pivoting extended arms 128, 130 and the grippers 134, 136.

[0061] The processing unit can configure the joining system 100 (and in particular the robotic unit 122) on one or more parameters of the end caps 102 of the tread 104, which are calculated by the image processing module. The processing unit can also refer to a reference (for example, a size chart for various treads) to make a final determination of the target tread parameter(s). The reference can include known tread parameters corresponding to a plurality of commercially available treads. For example, after the image processing module has calculated one or more tread parameters, the processing unit can compare the calculated tread parameters to the known tread parameters stored in the reference.The processing unit can retrieve those of the known tread parameters, corresponding to commercially available treads, which most closely match the calculated tread parameters in order to configure grippers 134, 136.

[0062] The identification of the end ends 102 of the tread 104 is relevant for the representation and can be determined by post-processing a previously generated segmentation of the tread 104. For example, a method can be used to determine whether a pixel is a candidate for the end end areas 102 comprising the upper end 106, the lower end 108, the first edge parts 110, 116, the second edge parts 112, 118 and the central parts 114, 120. For example, active contour models can be applied, together with path planning and distance transformations, in order to extract the parts of the tread 104.A morphology-based level set model can be used to perform tread area extraction 104 by learning the structural patterns of a target tread-like object 104 and estimating the terminal ends 102 of the object as a path.

[0063] The invention therefore takes advantage of methods and tools based on artificial intelligence (or "AI") to supplement partial information provided by perception. The initial positioning of the robotic unit 122 and the initial orientation of the grippers 134, 136 are determined from data obtained through image acquisition of the junction system 100 and the physical environment in which the junction system 100 operates. An automatic and adaptive repositioning algorithm is used to determine an ideal starting position for the robotic unit 122 in order to grasp the target end ends 102 of The tread 104 is positioned in front of a platform of a joining system 100. The identification of the target end ends 102 of the tread 104 incorporates the identification of a position, in which the upper end 106 and / or the lower end 108 are located, that is accessible for gripping without human intervention. The system allows for continuous improvement throughout the tire gripping operations, ensuring that the robotic unit 122 improves based on the experience it gains, particularly with regard to selecting the end ends 102 of the tread 104 of the tires to be joined.

[0064] With reference to [Fig. 10], an embodiment of a method 1000 for joining end ends (referred to as the "method") according to the invention is defined therein. Following the initiation of a joining process according to the invention, the method of the invention comprises a step consisting of capturing one or more images of the tread 104 having a profile defined by parameters of a predetermined length, a predetermined width, and a predetermined thickness. This step is performed by sensors of the detection unit to identify end ends 102 of the tread 104, including the upper end 106, the lower end 108, the first edge portions 110, 116, the second edge portions 112, 118, and the central portions 114, 120.

[0065] The method of the invention also includes a step 1100 consisting of processing the images of the tread 104 by imposing a geometric mesh 137 on surfaces of the tread 104 to represent nodes identifying terminal ends 102 including the upper end 106, the lower end 108, the first parts 110, 116 of the edge, the second parts 112, 118 of the edge and the central parts 114, 120, by at least one processing unit comprising one or more software programs or algorithms; and a stiffness detected by tactile sensors 152 of grippers 134, 136 of the robotic unit 122 (see [Fig.4]) to the deformation model.

[0066] The method of the invention further comprises a step 1200 in which the image processing module instructs the robotic unit 122, based on calculations from the deformation model using visual or shape servoing, to systematically grasp, deform, and move in translation the upper end 106 and / or the lower end 108 to align and join nodes representing the central part 114, the first edge part 110, and the second edge part 112 of the upper end 106 to the central part 120, the first edge part 116, and the second edge part 118 of the lower end 108 of the terminal ends 102. The method further comprises a step in detecting the force required to deform the tread 104 by relation to a rigidity expressed as a function of a geometric rigidity and a modulus of one or more materials by deploying one or more tactile sensors 152 in the grippers 134, 136 of the robotic unit 122.

[0067] The method of the invention includes a step of having the image processing module feed a deformation model with information including a stiffness or force required to deform the tread 104, mesh data defining end nodes 102 including the upper end 106, the lower end 108, the first edge portions 110, 116, the second edge portions 112, 118, and the central portions 114, 120. The step further includes instructing the robotic unit 122, using the deformation model, to systematically deform and move in translation the first edge portion 110, the second edge portion 112, and the central portion 114 of the upper end 106 to align and join nodes of the upper end 106 to the central portion 120, to the first portion 116 edge and to the second part 118 edge of the lower end 108.

[0068] In one embodiment, the grippers 134, 136 are instructed by the image processing module to sequentially join the central part 114, the first edge part 110 and the second edge part 112 of the upper end 106 to the central part 120, the first edge part 116 and the second edge part 118 of the lower end 108 of the tread 104, according to step 1300.

[0069] In another embodiment, the grippers 134, 136 are instructed by the image processing module to join the central part 114, the first edge part 110 and the second edge part 112 of the upper end 106 to the central part 120, the first edge part 116 and the second edge part 118 of the lower end 108 of the tread 104 in any order, without being limited to a particular sequence.

[0070] In addition, the gripping devices 124, 126 and the pivoting extended arms (128, 130) are further instructed to perform a translational movement from an initial position to a desired position (see [Fig.7]) so as to bring the upper end 106 close enough to the lower end 108 of the tread 104 so that the central parts 114, 120 are joined first as shown in [Fig.8]. The grippers 134, 136 are further instructed to be pivoted by actuators using a feedback control mechanism to remove the deformation of the first edge portion 110 and the second edge portion 112 of the upper end 106 in order to return to the initial shape of the tread 104 such that nodes representing the first edge portion 110, the second edge portion 112 of the upper end 106 are joined to nodes representing the first part 116 of edge, the second part 118 of edge of the lower end 108 as shown in [Fig.9].

[0071] Although embodiments of the disclosed apparatus have been illustrated and described, it will be understood that various changes, additions, and modifications can be made without departing from the spirit or scope of this description. Therefore, no limitations should be imposed on the scope of the invention described except those set forth in the appended claims.

Claims

1. Demands Joining system (100) for fixing end ends (102) of a sheet product (104) having a profile defined by parameters of a predetermined length, a predetermined width and a predetermined thickness, the end ends (102) including an upper end (106), a lower end (108), first edge parts (110, 116), second edge parts (112, 118) and central parts (114, 120) defining end surfaces of the end ends (102), the joining system (100) comprising: - at least one detection unit configured to capture one or more images in order to identify the profile parameters of the sheet product (104); - at least one processing unit comprising one or more software programs or algorithms, configured to process images of the product (104) in sheets by imposing a geometric mesh (137) on surfaces of the product (104) in sheets to represent nodes identifying terminal ends (102) including an upper end (106), a lower end (108), first edge parts (110, 116), second edge parts (112, 118) and central parts (114, 120), the processing unit comprising an image processing module deploying one or more deformation models based on visual or shape servoing; and - a robotic unit (122) comprising at least two gripping devices (124, 126), pivoting extended arms (128, 130) and grippers (134, 136), configured to receive instructions from the processing unit to systematically grasp, deform and move in translation the upper end (106) and / or the lower end (108) to align and join nodes representing the central part (114), a first edge part (110) and a second edge part (112) of the upper end (106) to the central part (120), to the first edge part (116), to the second edge part (118) of the lower end (108) of the terminal ends (102); whose image processing module is configured to assign weights to nodes representing central parts (114, 120) to be joined as a priority, followed by a weighting of nodes representing first parts (110, 116) of edge and second parts (112, 118) of edge of terminal ends (102).

2. Joining system (100) according to claim 1, the grippers (134, 136) of the robotic unit (122) comprising one or more tactile sensors configured to detect an effort required to deform the product (104) into sheets with respect to a stiffness expressed as a function of a geometric stiffness and a modulus of one or more materials used in the product (104) into sheets.

3. A joining system (100) according to claim 1 or claim 2, wherein the image processing module is configured to feed a deformation model with information including stiffness or force required to deform the product (104) into sheets, mesh data defining terminal end nodes (102) including an upper end (106), a lower end (108), first edge parts (110, 116), second edge parts (112, 118) and central parts (114, 120).

4. Joining system (100) according to any one of claims 1 to 3, a deformation pattern being configured to enable the image processing module to instruct the robotic unit (122) to systematically deform and move in translation the first edge part (110), the second edge part (112) and the central part (114) of the upper end (106) to align and join nodes of the upper end (106) to the central part (120), the first edge part (116) and the second edge part (118) of the lower end (108).

5. Junction system (100) according to any one of claims 1 to 4, the detection unit comprising one or more sensors for detecting two-dimensional (2D) and / or three-dimensional (3D) images, for achieving 3D relief perception and / or other types of detection.

6. Joining system (100) according to any one of claims 1 to 5, the product (104) in sheets being a tread of a tire, rubber tracks or products of a similar nature.

7. A joining system (100) according to any one of claims 1 to 6, the grippers (134, 136) comprising a movable jaw

8. (146) having at least two retaining fingers (150) of defined length capable of moving back and forth in a direction orthogonal to the longitudinal axis 11 of the grippers (134, 136) relative to a fixed jaw (148) to facilitate a firm grip on the upper end (106) and / or the lower end (108) of the product (104) in sheets placed between them. A joining method for fixing the end ends (102) of a product (104) in sheets having a profile defined by parameters of a predetermined length, a predetermined width and a predetermined thickness, the end ends (102) including an upper end (106), a lower end (108), first edge parts (110, 116), second edge parts (112, 118) and central parts (114, 120) thus defining end surfaces of the end ends (102), the method comprising: - a step of capturing one or more images to identify the product profile parameters (104) in sheets; - a step of processing one or more images of the product (104) in sheets by imposing a geometric mesh (137) on surfaces of the product (104) in sheets to represent nodes identifying terminal ends (102) including an upper end (106), a lower end (108), first edge parts (110, 116), second edge parts (112, 118) and central parts (114, 120), by at least one processing unit comprising one or more software programs or algorithms; and - a step of instructing a robotic unit (122), this step comprising at least two grasping devices (124, 126), pivoting extended arms (128, 130) and grippers (134, 136), to systematically grasp, deform and move in translation the upper end (106) and / or the lower end (108) to align and join nodes representing the central part (114), the first edge part (110) and the second edge part (112) of the upper end (106) to the central part (120), to the first edge part (116), to the second edge part (118) of the lower end (108) of the terminal ends (102); and a step of assigning a weight to nodes representing central parts (114, 120) to be joined as a priority, followed by a weighting of nodes representing first parts (110, 116) edge and second parts (112, 118) edge of terminal extremities (102).

9. Method according to claim 8, comprising a step of detecting an effort required to deform the product (104) into sheets with respect to a stiffness expressed as a function of a geometric stiffness and a modulus of one or more materials by deploying one or more tactile sensors (152) in the grippers (134, 136) of the robotic unit (122).

10. A method according to any one of claims 8 to 9, comprising a step of feeding, by the image processing module, a deformation model with information including a stiffness or force required to deform the product (104) into sheets, mesh data defining terminal end nodes (102) including an upper end (106), a lower end (108), first edge parts (110, 116), second edge parts (112, 118) and central parts (114, 120).

11. A method according to any one of claims 8 to 10, wherein the step of instructing the robotic unit (122) is carried out using the deformation model, to systematically deform and move in translation the first edge part (110), the second edge part (112) and the central part (114) of the upper end (106) to align and join nodes of the upper end (106) to the central part (120), the first edge part (116) and the second edge part (118) of the lower end (108).