Bonding system for attaching ends of sheet products

Abstract

The present invention relates to a bonding system (100) for attaching an end (102) of a sheet product (104), where the bonding system comprises a detection unit that captures an image of the sheet product and a processor that processes the image by imposing a geometric mesh (137) on a surface of the sheet product. The first edge portion (110, 116), the second edge portion (112, 118), and the central portion (114, 120) are configured to identify a node of the top end (106), the bottom end (108), the first edge portion (110, 116), the second edge portion (112, 118), and the central portion (114, 120). The bonding system includes a robotic unit having a gripping device (124, 126), a pivotable elongate arm (128, 130), and a gripper (134, 136) to receive indications from a processor to systematically grip, deform, and move at least one of the top end and the bottom end to align and bond nodes representing the central portion, the first edge portion, and the second edge portion.

Description

Technical Field

[0001] The present invention relates to a bonding system for attaching the ends of sheet products, and in certain cases, bonding tire tread portions during tire manufacturing operations to form a bonded tire tread. Background Technology

[0002] Several bonding systems are known in the art for attaching components to small products, such as passenger car tires, two-wheeled and three-wheeled vehicles (e.g., motorcycles and motorized transport vehicles), and similar applications. For these applications, known automation solutions include robotic units for applying low-rigidity products that do not require handling large, heavy products. For example, European Patent No. EP1656250B1 describes a “systematic” method for identifying the length, width, and position of tread segments to achieve stable bonding results. However, in industry, variations in the material rigidity of the tread segments can affect the stability of the robotic unit's gripper and can induce variations in the bonding results. While prior art discloses robotic units for handling sheet products of relatively small thicknesses, such solutions do not disclose the bonding at the ends (see, for example, European Patent No. EP2516142B1, US Publication No. US20160266569A1, and US Patent No. US10377101B2). Other prior art solutions disclose methods and apparatus for manufacturing layered articles such as multi-layered tread belts (see, for example, Korean Patent Application No. KR20070073739A). However, these solutions do not mention the use of robotic units to handle thick products or the methods for combining such products.

[0003] Conversely, the manufacture of large-size tires (including, but not limited to, tires used in truck and bus transportation, agricultural applications, mining applications, etc.) requires handling heavy products with high rigidity and often involves many manual operations, thus posing technical and economic challenges to handling such heavy products by automated machines. The tasks involved in such handling operations are demanding, involving medium to heavy loads and ergonomically difficult movements, and may require robotic operation, which includes one or more software or algorithm-assisted models (see, for example, “Shape Servos as Rigid as Possible” by Mohammadreza Shetab-Bushehri et al., IEEE Robotics and Automation Letters (Vol. 7, No. 2, April 2022) (https: / / ieeexplore.ieee.org / document / 9691867).

[0004] Some solutions disclose a method and apparatus for bonding a first tread portion to a second tread portion to form a bonded tread, each tread portion comprising a portion of the tire tread extending longitudinally from its end (see the applicant's U.S. Patent No. US9573330B2). This solution is particularly useful for retreading applications, comprising guiding the ends of the tires toward each other using a hydraulic or pneumatic mold and forcefully bonding them to an elastomeric bonding material disposed between the ends.

[0005] Therefore, the present invention provides a bonding system comprising a robotic unit and a vision perception system. The robotic unit has a gripper suitable for the product to be processed, and the vision perception system locates the product, characterizes the deformation of the product, and controls the movement of the robotic unit throughout the bonding operation. The bonding system serves as an ergonomic aid for a tread bonding platform on large machines and its algorithm can be adjusted based on deformation characterization of material property variations to be applicable to various profiles of products with different thicknesses and considering rigidity. Summary of the Invention

[0006] This invention relates to a bonding system for attaching the end of a sheet product having a profile defined by parameters of a predetermined length, a predetermined width, and a predetermined thickness, wherein the end includes a top end, a bottom end, a first edge portion, a second edge portion, and a central portion, thereby defining an end face of the end. The bonding system includes:

[0007] - At least one detection unit configured to capture one or more images to identify contour parameters of the sheet product;

[0008] - At least one processing unit, comprising one or more software or algorithms, the at least one processing unit configured to process an image of a sheet product, which represents the identification of nodes including top, bottom, first edge portions, second edge portions, and central portions by imposing a geometric mesh on the surface of the sheet product; and

[0009] - A robot unit comprising at least two gripping devices, a pivotable slender arm, and a gripper, the robot unit being configured to receive instructions from a processing unit to systematically grip, deform, and translate at least one of the top or bottom ends, thereby aligning and engaging nodes representing the central portion, first edge portion, and second edge portion of the top end with the central portion, first edge portion, and second edge portion of the bottom end.

[0010] In some implementations of the combined system, the processing unit includes an image processing module that deploys one or more deformable models based on vision or shape servoing.

[0011] In some implementations of the combined system, the gripper of the robotic unit includes one or more touch sensors configured to detect the force required to deform the sheet product relative to rigidity, which is a function of geometrical rigidity and the modulus of one or more materials used in the sheet product.

[0012] In some implementations of the combined system, the image processing module is configured to feed information to the deformation model, including the force required to rigidify or deform the sheet product, and meshed data defining the ends of nodes including the top, bottom, first edge portion, second edge portion, and central portion.

[0013] In some implementations of the combined system, the deformable model is configured to allow the image processing module to instruct the robot unit to systematically deform and translate the first edge portion, the second edge portion, and the central portion of the top end, thereby aligning and combining the nodes of the top end with the central portion, the first edge portion, and the second edge portion of the bottom end.

[0014] In some implementations of the bonding system, the image processing module is configured to first provide weights to nodes representing the central portion to be bonded, and then provide weights to nodes representing the first and second edge portions at the ends.

[0015] In some implementations of the combined system, the detection unit includes one or more sensors for detecting two-dimensional (2-D) and / or three-dimensional (3-D) images to achieve 3-D depth sensing and / or other types of detection.

[0016] In some implementations of the combined system, the sheet product may be a tire tread, a rubber track, or a product of similar nature.

[0017] In some embodiments of the coupling system, the gripper includes a movable jaw having at least two retaining fingers of a defined length, capable of reciprocating relative to a fixed jaw in a direction orthogonal to the longitudinal axis 11 of the gripper to facilitate a secure engagement of at least one top or bottom end of a sheet product placed therebetween.

[0018] The present invention also relates to a joining method for attaching the end of a sheet product having a profile defined by parameters of a predetermined length, a predetermined width, and a predetermined thickness, wherein the end includes a top end, a bottom end, a first edge portion, a second edge portion, and a central portion, thereby defining an end face of the end, the method comprising:

[0019] - The steps of capturing one or more images to identify the contour parameters of sheet products;

[0020] - The step of processing an image of a sheet product, which is performed by at least one processing unit including one or more software or algorithms by imposing a geometric mesh on the surface of the sheet product to represent and identify nodes including the ends of a top, bottom, first edge portion, second edge portion, and central portion; and

[0021] - Instructs a robotic unit having at least two gripping devices, a pivotable slender arm, and a gripper to systematically grip, deform, and translate at least one of the top or bottom ends, thereby aligning and engaging the nodes representing the central portion, first edge portion, and second edge portion of the top end with the central portion, first edge portion, and second edge portion of the bottom end.

[0022] In some implementations of the combined method, a step is taken to detect the force required to deform the sheet product relative to rigidity by deploying one or more touch sensors in the gripper of the robotic unit, the rigidity being a function of geometrical rigidity and the modulus of one or more materials.

[0023] In some implementations of the combined method, the step of feeding information to the deformation model via an image processing module includes the force required to rigidify or deform the sheet product, and meshed data defining the ends of nodes including the top, bottom, first edge portion, second edge portion, and central portion.

[0024] In some implementations of the joining method, the steps of aligning and joining the nodes at the top to the central portion, first edge portion, and second edge portion at the bottom are performed by using a deformation model to instruct the robot unit to systematically deform and translate the first edge portion, second edge portion, and central portion at the top.

[0025] In some implementations of the joining method, there is a step of first assigning weights to the nodes representing the central portion to be joined, followed by assigning weights to the nodes representing the first and second edge portions at the ends.

[0026] Other aspects of the invention will become apparent from the following detailed description. Attached Figure Description

[0027] The nature and various advantages of the invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which the same reference numerals always denote the same parts, and wherein:

[0028] Figure 1 A schematic diagram illustrating an embodiment of the combined system of the present invention.

[0029] Figure 2 A perspective view showing an embodiment of the tread of the bonding system of the present invention.

[0030] Figure 3 According to the present invention Figure 1 A partial perspective view of an implementation scheme for a robotic system, which incorporates a gripping device including a pivotable slender arm and a gripper.

[0031] Figure 4 This indicates the passage according to the invention. Figure 3 A side view of an embodiment of a clamping device for holding the tire tread.

[0032] Figure 5 This indicates the passage according to the invention. Figure 3 A top view of another embodiment of the clamp holding the tire tread.

[0033] Figure 6 This indicates the passage according to the invention. Figure 3 A three-dimensional diagram showing how the clamps deform the end of the tire tread.

[0034] Figure 7 This indicates the passage according to the invention. Figure 3 A three-dimensional view of the end of the tread being translated by the clamp.

[0035] Figure 8 This indicates the passage according to the invention. Figure 3 A three-dimensional view of the clamping device combined with the central part of the end of the tire tread.

[0036] Figure 9 This indicates the passage according to the invention. Figure 3 A three-dimensional view of the clamping device combined with the end of the tire tread.

[0037] Figure 10 A flowchart illustrating the method for joining the ends of the tread according to the present invention. Detailed Implementation

[0038] This invention includes a bonding system and method for attaching the ends of sheet products, for clamping and attaching the ends of highly rigid sheet products. Sheet products are defined as products with a predetermined profile, length, width, and thickness, exhibiting high rigidity, which can make handling tasks arduous, involving moderate to heavy handling and ergonomically difficult movement. In several examples, the sheet product may be a tire tread or a rubber track or a sheet product of similar nature. For the purposes of this invention and for the explanation of this invention, the sheet product may be referred to as a tread; however, this invention is not intended to be limited to tire treads. Due to the method and apparatus of this invention, a robust attachment of the tread ends can be achieved efficiently for products with high rigidity and thickness, compared to the prior art.

[0039] The methods and apparatus disclosed herein are used to join two opposite ends of a tread portion to form a joined tread. Typically, a tread portion is a longitudinal section of a tread applied to a tire carcass, having a predetermined length, predetermined width, and predetermined thickness. The tread portion may include a tread having a tread pattern on its ground-engaging side. The tread pattern may include any known tread feature, such as protrusions and / or ribs separated by grooves and / or slots. First and second tread portions may be associated with the same tread (i.e., different portions or segments of the tread) or with separate and different treads. For example, the ends of a single tread may be joined to form a continuous tread ring. By further example, individual tread segments (i.e., tread sections, segments, or lengths) may be joined to form a single integral tread comprising multiple joined tread segments. The provided tread portion may be at least partially or completely cured, but may be raw or uncured tread portions.

[0040] The end of the tread portion forms the end of the tread and includes an end face. The end face includes a cross-sectional surface of the tread, extending laterally across the tread width and having a height extending through the thickness of the tread. The end face may extend across the width of the tread in a direction perpendicular to the longitudinal direction of the tread or at any other angle offset relative to the longitudinal direction. Furthermore, the end face may extend laterally in a linear or non-linear path. Similarly, the height of the end face may extend through the tread thickness in any direction, including directions perpendicular to the longitudinal direction of the tread, and in any linear or non-linear path. Since the tread may include tread patterns extending into the tread thickness, the tread end face may include a gap disposed within the tread thickness and arranged inwardly from the outer cross-sectional profile.

[0041] The longitudinal location for forming the ends along each tread segment is selected to provide ends with a profile that substantially matches the profile of the other end to which it will be joined. For example, substantially matching ends can be selected and formed or otherwise provided (i.e., their cross-sections, profiles, and / or peripheries substantially match). This provides a tread joint that is consistent with adjacent portions or features of the joined tread and with the entire tread pattern of the joined tread. In other words, by forming ends to substantially match, the joined or assembled tread can include a tread pattern that is substantially uninterrupted at the joint, where tread features at opposite ends are substantially aligned with respect to the height (i.e., thickness) and width of the tread.

[0042] The arrangement of the ends provides a coupled or assembled tread, wherein the coupled tread portions extend in generally the same longitudinal direction, which may extend linearly as tread strips or circumferentially as tread rings. Alternatively, determining the location for forming the ends along any tread length can be chosen not only to substantially match the ends of the tread portions to be coupled, but also to select a location that allows for proper tread coupling.

[0043] Reference Figure 1 and Figure 2 A bonding system 100 according to the present invention is shown. The bonding system 100 is defined for attaching an end 102 of a tread 104 to a rigid material. The end 102 of the tread 104 includes a top end 106 and a bottom end 108 with predetermined profile parameters, including but not limited to length, width, and thickness. Furthermore, each of the top end 106 and the bottom end 108 of the tread 104 includes an end face defining a first edge portion (110, 116), a second edge portion (112, 118), and a central portion (114, 120), as shown. Figure 2 As shown.

[0044] According to the invention, the engagement system 100 is adapted to systematically clamp and translate at least one of the tip 106 or the bottom 108 to align and engage the central portion 114, the first edge portion 110, and the second edge portion 112 of the tip 106 to the central portion 120, the first edge portion 116, and the second edge portion 118 of the bottom 108 of the end 102. In one embodiment, the engagement system 100 may be independent of predetermined profile parameters of the end 102 of the tread 104, as it is independent of those parameters. The engagement system 100 is configured to engage without limiting the predetermined profile parameters of the end 102.

[0045] Reference Figure 1 and Figure 3 The combined system 100 includes a mobile robotic unit (or "robot") 122 having at least two gripping devices (124, 126) respectively supported by pivotable elongated arms (128, 130). The gripping devices (124, 126) extend from the pivotable elongated arms (128, 130) to a free end 132, wherein the grippers (134, 136) are arranged along a longitudinal axis 11 (see...). Figure 3The robot unit 122 is configured to move such that the grippers (134, 136) can grip the end 102 of the tread 104 targeted by the bonding system 100 during the attachment process. The term "movement" should be understood to mean that the robot unit 122 can be configured to move via integrated movement devices (e.g., one or more integrated motors) or via non-integrated movement devices (e.g., one or more autonomous moving brackets or other equivalent movement devices). It should be understood that the robot unit 122 can be attached to a ceiling, wall, or any support that allows the bonding system 100 to perform the attachment process of the present invention. It should be understood that the robot unit 122 can be a conventional industrial robot or collaborative robot, or even a delta robot or wired robot with at least six degrees of freedom (DOF). The robot unit 122 can be used interchangeably with the two gripping devices (124, 126), the pivotable elongated arms (128, 130), and the grippers (134, 136), as they are part of the robot unit 122.

[0046] Reference Figure 3 The gripping devices 124 and 126 are supported by pivotable elongated arms 128 and 130, respectively, each including a platform of predetermined length between an attachment end and an opposite free end. The attachment end may include an adapter that allows the platform to be removably attached to the robot unit 122. Attachment of the platform to the robot unit 122 can be achieved by screwing the adapter to the free end of the gripping devices (124, 126). It should be understood that the attachment of the platform to the robot unit 122 can be affected by any known attachment means (including but not limited to welding, bonding, and equivalent means).

[0047] The grippers (134, 136) include a movable jaw 138 and a fixed jaw 140. The movable jaw 138 may include at least two retaining fingers 142 of defined length, which are reciprocating relative to the fixed jaw 140 in a direction orthogonal to the longitudinal axis 11 of the grippers (134, 136) to facilitate a secure engagement of at least one of the top end 106 or bottom end 108 of the tread 104 placed therebetween. The reciprocating movement of the movable jaw 138 is mediated by an actuator V. 138 To perform this action, the actuator is actuated by pressurized fluid (e.g., compressed air) from a conduit (not shown). In another example, actuator V 146 It can be actuated by electrical energy or alternative energy sources. Furthermore, the grippers (134, 136) are also configured to operate via a connection with V... 138 Actuator V, similar to a mechanism. 139 And rotates along the longitudinal axis ll. Actuator V 138 V 139The actuator is selected from commercially available products. By means of the movable claw 138 and the fixed claw 140, as the grippers (134, 136) move between the engagement position and the mating position, the grippers (134, 136) achieve the clamping of at least one of the top end 106 and the bottom end 108 of the tread 104. In the engagement position, at least one of the movable claw 146 and the fixed claw 140 is in its engagement position, and in the engagement position, the grippers (134, 136) are positioned to clamp at least one of the top end 106 and / or the bottom end 108 of the tread 104. In the mating position, the grippers (134, 136) translate at least one of the top end 106 or the bottom end 108 to place it in the target mating area to attach the top end 106 to the bottom end 108 of the tread 104.

[0048] Robotic unit 122 includes a detection system employing one or more sensors (not shown) that capture information about the physical environment surrounding robotic unit 122. In the following description, the terms “sensor,” “photographic device,” “camera,” and “optical sensor” are used interchangeably and can refer to one or more devices configured to detect two-dimensional (2-D) and / or three-dimensional (3-D) images to achieve 3-D depth perception and / or other types of detection of the physical environment. In one example, the sensor of the detection unit can be any commercially available RGB-D camera with a frame resolution of 1920 × 1080, achieving a frame rate of 30 fps or frames per second. In another example, one or more sensors can be a laser profilometer. The sensors of the detection system coupled to robotic unit 122 can be fixed to at least one of the pivotable slender arms (128, 130) and / or grippers (134, 136) of the gripping devices (124, 126). Alternatively, the sensors of the detection system can be remotely coupled to robotic unit 122, covering the field of view of the coupled system 100.

[0049] One or more sensors of the detection system of the combined system 100 detect the presence of the arrangement of the tread 104 in the field of view of the camera, and this triggers the camera to capture an image of the tread 104. In some embodiments of the combined system 100, the sensor is triggered when the tread 104 enters the field of view of the camera in the context of the captured image.

[0050] The detection system can determine information related to the physical environment, which can be used by a control system (including, for example, software for guiding the movement of robot unit 122). The control system may reside on robot unit 122 or may communicate remotely with robot unit 122. In some embodiments of the integrated system 100, one or more 2-D or 3-D sensors (including, but not limited to, navigation sensors) mounted on robot unit 122 may be integrated to form a digital model of the physical environment (including, where applicable, the sides, floor, and ceiling). Using the obtained data, the control system can induce movement of robot unit 122 to navigate between positions for gripping at least one end 102 of the tread 104.

[0051] The sensors of the detection system will Figure 2 The captured profile parameters of the tread 104 shown and the physical environment surrounding the robot unit 122 of the integration system 100 are sent to at least one processing unit or processor. The term "processor" (or, alternatively, the term "programmable logic circuit") refers to one or more devices capable of processing and analyzing data and having one or more software packages for its processing (e.g., including, as known to those skilled in the art, one or more integrated circuits, 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 (and corresponding data obtained) by the subsystems associated with the integration system 100, and software for identifying and locating discrepancies and identifying their sources for correction.

[0052] Those skilled in the art will recognize that many image processing techniques can be used to select and determine the parameters of a target tire tread. Several commercially available image processing systems are available.

[0053] The sensor of the detection unit captures one or more images of the tread 104. These captured images are transmitted and stored as captured images in the memory of the processing unit. The processing unit, acting on instructions from its image processing module, analyzes the images to determine one or more parameters of the imaged tread 104. The parameters of the tread 104 are length, width, thickness, and information related to the end 102, which includes a top end 106, a bottom end 108, a first edge portion (110, 116), a second edge portion (112, 118), and a central portion (114, 120), which define the end face of the end 102.

[0054] Reference Figure 4 and Figure 5The grippers (134, 136) can be used in various ways, including but not limited to... Figure 4 The arrangement shown includes several combinations of clamps holding the ends 102 of the tread 104, wherein clamp 134 is adapted to clamp a first edge portion 110 of the top end 106, and clamp 136 is adapted to clamp a second edge portion 112 of the top end 106 positioned opposite the first edge portion 110. In another example, clamps (134, 136) may clamp the first edge portions (110, 116), second edge portions (112, 118), or central portions (114, 120) of the top end 106 and bottom end 108 together on the same side for engagement of the ends 102 of the tread 104, such as... Figure 5 As shown in the diagram. Furthermore, the grippers (134, 136) are equipped with a touch sensor 152 to determine the contact force required for deformation based on the rigidity of the tread 104. The rigidity of the tread 104 can be expressed as a function of its geometric rigidity and the modulus of one or more materials used. The touch sensor 144 is adapted to detect forces within the tread 104 because each material has its own rigidity characteristics and provides resistance to forces to recover its initial shape due to elasticity in the event of deformation. The higher the modulus of the material of the tread 104, the greater the contact force required by the grippers (134, 136) for deformation.

[0055] The image processing module processes the image of the tread 104 to impose a geometric mesh 137 on the surface of the tread 104 to represent the nodes of the identified end 102, which includes a top end 106, a bottom end 108, a first edge portion (110, 116), a second edge portion (112, 118), and a central portion (114, 120), as shown. Figure 4 and Figure 5 As shown in the diagram, the grid 137 of nodes and the identification allow the robot unit 122 to be systematically manipulated to control the movement of the gripping devices (124, 126), the pivotable slender arms (128, 130), and the grippers (134, 136), thereby deforming, translating, or moving and engaging the end 102 of the tread 104.

[0056] Reference Figures 6 to 9 The image processing module of the processing unit may include a deformation model based on a visual servo or shape servo mechanism. This is achieved by the touch sensor 152 (see...). Figure 4 , 5The sensed rigidity of the tread 104 at its end 102 is transmitted to the image processing module of the processing unit. The image processing module feeds information about the rigidity, along with meshed data defining the nodes of the end 102, including the top 106, bottom 108, first edge portions (110, 116), second edge portions (112, 118), and central portions (114, 120), into the deformation model. The rigidity is expressed as a function of geometric rigidity and the modulus of one or more materials used in the tread 104. The robot unit 122 is configured to receive instructions from the processing unit to systematically clamp and translate at least one of the top 106 or bottom 108, thereby aligning and engaging the nodes representing the central portion 114, first edge portion 110, and second edge portion 112 of the top 106 with the central portion 120, first edge portion 116, and second edge portion 118 of the bottom 108 of the end 102.

[0057] In one example of the invention, the clamps (134, 136) are configured to sequentially engage the central portion 114, the first edge portion 110, and the second edge portion 112 of the top end 106 with the central portion 120, the first edge portion 116, and the second edge portion 118 of the bottom end 108 of the tread 104. Figure 6 In the configuration shown, the grippers (134, 136) are rotated by a closing control mechanism based on the rigidity of the tread 104 received by the touch sensor 152, and the image processing module directs the actuator V... 146 Send an indication of the amount of force required to deform the first edge portion 110 and the second edge portion 112 of the top 106, such that the nodes representing the central portions 114 and 120 are weighted by the image processing module for preferential bonding.

[0058] In addition, such as Figure 7 , Figure 8 and Figure 9 As shown, the clamping devices (124, 126) and the pivotable slender arms (128, 130) are further manipulated to move from the initial position of engagement with the bottom end 108 away from the top end 106 (see Figure 124). Figure 6 ) Translate it to the desired position at the top 106 of the tread 104, close enough to the bottom 108 of the tread (see Figure 7 As instructed by the image processing module of the processing unit, the central portions (114, 120) are preferentially combined, such as... Figure 8As shown in the diagram. The grippers (134, 136) are further rotated by the actuator via a control feedback mechanism to prevent the first edge portion 110 and the second edge portion 112 of the top 106 from deforming, thereby returning to the initial shape of the tread 104. This causes the nodes representing the first edge portion 110 and the second edge portion 112 of the top 106 to engage with the nodes representing the first edge portion 116 and the second edge portion 118 of the bottom 108, as shown. Figure 9 As shown in the image.

[0059] In other embodiments, the image processing module instructs the robot unit 122 to systematically clamp, deform, and translate at least one of the top end 106 or the bottom end 108, thereby aligning and engaging the nodes representing the central portion 114, the first edge portion 110, and the second edge portion 112 of the top end 106 with the central portion 120, the first edge portion 116, and the second edge portion 118 of the bottom end 108 in any order (not limited to a specific order).

[0060] The image processing module can use parameters of the tread 104 captured from the sensor to deploy one or more machine learning models to identify the ends 102 of the tread 104. Although this paper describes the implementation using neural networks (specifically, convolutional neural networks (CNNs)) as the 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 Bayes, K-nearest neighbors (kNN) (where K denotes grouping), random forests, dimensionality reduction algorithms, gradient algorithms, neural networks (e.g., autoencoders, CNNs, RNNs, perceptrons, log short-term memory (LSTM), Hopfield, Boltzmann, deep belief networks, deconvolution, generative adversarial networks (GANs), etc.) and their complementary and equivalent models. One or more CNNs can be trained using ground-based data generated using sensor data representing the movement of the grippers (124, 126) of robot unit 122, including the localization of the pivotable slender arms (128, 130) and grippers (134, 136).

[0061] The processing unit can configure the coupling system 100 (especially the robot unit 122) based on one or more parameters of the end 102 of the tread 104 calculated by the image processing module. The processing unit can also refer to reference materials (e.g., size tables for various treads) to make a final determination of one or more target tread parameters. The reference materials may include known tread parameters corresponding to multiple known commercially available treads. For example, after the image processing module calculates one or more tread parameters, the processing unit can compare the calculated tread parameters with known tread parameters recorded in the reference materials. The processing unit can retrieve those known tread parameters corresponding to the commercially available treads that are closest to the calculated tread parameters in order to configure the grippers (134, 136).

[0062] Identifying the ends 102 of the tread 104 is crucial for representation and can be achieved through post-processing of previously generated tread 104 segments. For example, a method can be used to determine whether a pixel is a candidate for the region encompassing the ends 102 of the tread 104, which includes the top 106, bottom 108, first edge portions (110, 116), second edge portions (112, 118), and central portions (114, 120). For instance, an active contour model can be applied in conjunction with path planning and distance transformation to extract portions of the tread 104. A morphological level set model can be used to perform tread 104 region extraction by learning structural patterns of objects similar to the target tread 104 and by estimating the ends 102 of the objects as paths.

[0063] Therefore, the present invention utilizes artificial intelligence (or “AI”) based methods and tools to supplement the 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 via image acquisition from the bonding system 100 and the physical environment in which the bonding system 100 operates. An automatic and adaptive repositioning algorithm is used to find the ideal starting position of the robotic unit 122 for gripping the target end 102 of the tread 104 in front of the platform of the bonding system 100. The identification of the target end 102 of the tread 104 is combined with the identification of the position of at least one of the top end 106 or bottom end 108, where gripping is easy without human intervention. This system allows for continuous improvement in all tire gripping operations, ensuring that the robotic unit 122 improves from its acquired experience, particularly regarding the selection of the end 102 of the tread 104 tire used for bonding.

[0064] Reference Figure 10The embodiment of the bonding end method 1000 (or "method") of the present invention is defined therein. After initiating the bonding process of the present invention, the method of the present invention includes the step of capturing one or more images of a tread 104 having a contour defined by parameters of a predetermined length, a predetermined width, and a predetermined thickness. This step is performed by a sensor of a detection unit to identify the end 102 of the tread 104, including a top end 106, a bottom end 108, a first edge portion (110, 116), a second edge portion (112, 118), and a central portion (114, 120).

[0065] The method of the present invention further includes a step 1100 of processing an image of the tread 104, which is performed by at least one processing unit comprising one or more software or algorithms by imposing a geometric mesh 137 on the surface of the tread 104 to represent the nodes of the end 102, including the top 106, bottom 108, first edge portions (110, 116), second edge portions (112, 118), and central portions (114, 120); and by providing a deformable model to the robot unit 122 (see Figure 4 The rigidity is sensed by the touch sensor 152 of the gripper (134, 136).

[0066] The method of the present invention further includes step 1200: based on calculations from a deformable model via shape servoing or visual servoing, an image processing module instructs robot unit 122 to systematically clamp, deform, and translate at least one of the top end 106 or bottom end 108, thereby aligning and engaging nodes representing the central portion 114, the first edge portion 110, and the second edge portion 112 of the top end 106 with the central portion 120, the first edge portion 116, and the second edge portion 118 of the bottom end 108 of the bottom end 102. The method further includes the step of detecting the force required to deform the tread 104 relative to rigidity by deploying one or more touch sensors 152 in the grippers (134, 136) of robot unit 122, the rigidity being a function of geometrical rigidity and the modulus of one or more materials.

[0067] The method of the present invention includes the steps of: feeding information to a deformation model via an image processing module, the information including the force required to rigidify or deform the tread 104, and meshed data defining the nodes of the end 102, which includes a top end 106, a bottom end 108, first edge portions (110, 116), second edge portions (112, 118), and a central portion (114, 120). Furthermore, this step includes instructing a robot unit 122 to systematically deform and translate the first edge portions 110, second edge portions 112, and central portion 114 of the top end 106 using the deformation model, thereby aligning and engaging the nodes of the top end 106 with and connecting them to the central portion 120, first edge portions 116, and second edge portions 118 of the bottom end 108.

[0068] In the implementation, according to step 1300, the clamps (134, 136) are instructed by the image processing module to sequentially engage the central portion 114, the first edge portion 110, and the second edge portion 112 of the top end 106 with the central portion 120, the first edge portion 116, and the second edge portion 118 of the bottom end 108 of the tread 104.

[0069] In another embodiment, the clamps (134, 136) are instructed by the image processing module to engage the central portion 114, the first edge portion 110 and the second edge portion 112 of the top end 106 in any order (not limited to a specific order) to the central portion 120, the first edge portion 116 and the second edge portion 118 of the bottom end 108 of the tread 104.

[0070] Furthermore, the clamping devices (124, 126) and the pivotable slender arms (128, 130) are further instructed to translate from the initial position to the desired position (see [link]). Figure 7 This moves the top 106 close enough to the bottom 108 of the tread 104, allowing the central portions (114, 120) to engage preferentially, such as... Figure 8 As shown in the diagram. Further, the grippers (134, 136) are instructed by the control feedback mechanism to rotate by the actuator, so that the first edge portion 110 and the second edge portion 112 of the top end 106 remain undeformed, thereby returning to the initial shape of the tread 104, such that the nodes representing the first edge portion 110 and the second edge portion 112 of the top end 106 are joined to the nodes representing the first edge portion 116 and the second edge portion 118 of the bottom end 108, as shown. Figure 9 As shown in the image.

[0071] Although embodiments of the disclosed device have been shown and described, it will be understood that various changes, additions, and modifications can be made without departing from the spirit or scope of this specification. Therefore, the scope of the invention described should not be limited except for those set forth in the appended claims.

Claims

1. A bonding system (100) for attaching the end (102) of a sheet product (104) having a profile defined by parameters of a predetermined length, a predetermined width, and a predetermined thickness, wherein, The end (102) includes a top end (106), a bottom end (108), a first edge portion (110, 116), a second edge portion (112, 118), and a central portion (114, 120), thereby defining an end face of the end (102), the coupling system (100) including: - At least one detection unit configured to capture one or more images to identify contour parameters of the sheet product (104); - At least one processing unit, comprising one or more software or algorithms, configured to process an image of the sheet product (104) by imposing a geometric grid (137) on the surface of the sheet product (104) to represent and identify nodes including a top (106), a bottom (108), a first edge portion (110, 116), a second edge portion (112, 118), and a central portion (114, 120) at the end (102); and - A robot unit (122) comprising at least two gripping devices (124, 126), a pivotable slender arm (128, 130), and a gripper (134, 136), the robot unit being configured to receive instructions from a processing unit to systematically grip, deform, and translate at least one of the top end (106) or bottom end (108), thereby aligning and engaging the nodes representing the central portion (114), the first edge portion (110), and the second edge portion (112) of the top end (106) with the central portion (120), the first edge portion (116), and the second edge portion (118) of the bottom end (108) of the bottom end (102).

2. The bonding system (100) according to claim 1, wherein, The processing unit includes an image processing module, which deploys one or more deformable models based on vision or shape servoing.

3. The bonding system (100) according to claim 1 or claim 2, wherein, The grippers (134, 136) of the robot unit (122) include one or more touch sensors configured to detect the force required to deform the sheet product (104) relative to a rigidity expressed as a function of geometrical rigidity and the modulus of one or more materials used in the sheet product (104).

4. The bonding system (100) according to any one of claims 1 to 3, wherein, The image processing module is configured to feed information to the deformation model, including the force required to rigidify or deform the sheet product (104), and meshed data defining the nodes including the top (106), bottom (108), first edge portions (110, 116), second edge portions (112, 118), and the end (102) of the central portion (114, 120).

5. The bonding system (100) according to any one of claims 1 to 4, wherein, The deformable model is configured to allow the image processing module to instruct the robot unit (122) to systematically deform and translate the first edge portion (110), the second edge portion (112), and the central portion (114) of the top end (106), thereby aligning and engaging the nodes of the top end (106) with the central portion (120), the first edge portion (116), and the second edge portion (118) of the bottom end (108).

6. The bonding system (100) according to any one of claims 1 to 5, wherein, The image processing module is configured to first provide weights to the nodes representing the central portions (114, 120) to be combined, and then provide weights to the nodes representing the first edge portions (110, 116) and the second edge portions (112, 118) of the end (102).

7. The bonding system (100) according to any one of claims 1 to 6, wherein, The detection unit includes one or more sensors for detecting two-dimensional (2-D) and / or three-dimensional (3-D) images to achieve 3-D depth perception and / or other types of detection.

8. The bonding system (100) according to any one of claims 1 to 7, wherein, The sheet product (104) may be a tire tread, a rubber track, or a product of similar nature.

9. The bonding system (100) according to any one of claims 1 to 8, wherein, The grippers (134, 136) include a movable claw (146) having at least two retaining fingers 150 of a defined length, capable of reciprocating relative to a fixed claw 148 in a direction orthogonal to the longitudinal axis 11 of the grippers (134, 136) to facilitate a secure engagement of at least one of the top end 106 or bottom end 108 of a sheet product (104) placed therebetween.

10. A method for attaching an end (102) of a sheet product (104), the sheet product having a profile defined by parameters of a predetermined length, a predetermined width, and a predetermined thickness, wherein, The end (102) includes a top end (106), a bottom end (108), a first edge portion (110, 116), a second edge portion (112, 118), and a central portion (114, 120), thereby defining the end face of the end (102), the method comprising the following steps: - Capture one or more images to identify the contour parameters of the sheet product (104); - Processing an image of a sheet product (104), which is represented by at least one processing unit including one or more software or algorithms by imposing a geometric grid (137) on the surface of the sheet product (104) to identify nodes including the top (106), bottom (108), first edge portions (110, 116), second edge portions (112, 118), and the end (102) of the central portion (114, 120); and - Instructs a robotic unit (122) comprising at least two gripping devices (124, 126), a pivotable slender arm (128, 130), and a gripper (134, 136) to systematically grip, deform, and translate at least one of the top end (106) or bottom end (108), thereby aligning and engaging the nodes representing the central portion (114), the first edge portion (110), and the second edge portion (112) of the top end (106) with the central portion (120), the first edge portion (116), and the second edge portion (118) of the bottom end (108) of the end end (102).

11. The method according to claim 10, wherein, One or more touch sensors (152) are deployed in the grippers (134, 136) of the robot unit (122) to detect the force required to deform the sheet product (104) relative to rigidity, which is a function of geometric stiffness and the modulus of one or more materials.

12. The method according to claim 10 or claim 11, wherein, Information is fed into the deformation model via the image processing module. The information includes the force required to rigidify or deform the sheet product (104) and the meshed data defining the nodes including the top (106), bottom (108), first edge portions (110, 116), second edge portions (112, 118), and the end (102) of the central portion (114, 120).

13. The method according to any one of claims 10 to 12, wherein, By using a deformation model to instruct the robot unit (122) to systematically deform and translate the first edge portion (110), the second edge portion (112), and the central portion (114) of the top end (106), thereby aligning and connecting the nodes of the top end (106) to the central portion (120), the first edge portion (116), and the second edge portion (118) of the bottom end (108).

14. The method according to any one of claims 10 to 13, wherein, Weights are first assigned to the nodes representing the central portions (114, 120) to be combined, and then weights are assigned to the nodes representing the first edge portions (110, 116) and the second edge portions (112, 118) of the end portions (102).

Images