System for the automatic repair of tyre surface damage using a robot and 3D vision sensor

Abstract

The invention relates to a method for repairing the carcass of a tyre identified as damaged during retreading, the method being implemented by at least one processor comprising a processing module which applies, to at least one neural network, data representative of the captured images of the carcass of the identified tyre. The invention also relates to a retreading method comprising the method disclosed. The invention further relates to an automatic repair system for repairing the carcass of an identified tyre during retreading.

Description

[0001] Description

[0002] Automatic tire surface damage repair system using robot and 3D vision sensor

[0003] Technical Field

[0004] The invention relates to a method for repairing a carcass of an identified tire during retreading. More particularly, the invention relates to a repair method used to repair the identified tire in each area of ​​a carcass containing one or more damages to be treated.

[0005] Context

[0006] In the field of tire manufacturing and maintenance, retreading is a known process for restoring a worn tire to serviceable condition by renewing the tread rubber and ply(ies). During the retreading process, old tread products are removed and replaced with new materials. Retreading is a method that is known and regulated in several industries (including, but not limited to, transportation, aviation, mining, and agriculture). Damage could fall into one or a few categories (or "classifications") of damage (including, but not limited to, tread damage, tear damage, cut damage, and puncture damage).

[0007] Regardless of the type of tire being retreaded, the steps in a retreading process are essentially the same from the time a tire enters a retreading facility until it leaves.

[0008] During the retreading process, a repair process is carried out in which the tires intended for retreading are examined so that existing damage can be identified and located. During the repair process, a visual detection of the damage is made (either by manual means or by automatic means (e.g., one or more cameras) or by a combination of both). If we focus on the repair of "tread pattern" type damage, during the repair process, a step of cleaning the damage is carried out using a compressed air blower and a treatment tool (e.g., a soft brush). Then, a step of removing the remaining rubber is carried out using a treatment tool (e.g., a hard brush) to expose the first crown ply.The repair process continues with visual detection of the presence of corrosion on the wire ropes (either by manual means or by automatic means (e.g., one or more cameras) or by a combination of both). If this visual detection confirms the presence of corrosion, a removal step is performed using a processing tool such as a grinding wheel. These corrosion detection / removal steps are repeated on the different successive plies as long as corrosion is detected. After the repair process is completed, the retreading process may continue in a typical order of steps towards the exit of a tire from the retreading facility (the steps including, but not limited to, a tread application step, a curing step, an inspection step and a shipping step). Until now, one or more steps of the damage repair process are performed manually.

[0009] There are ongoing efforts to automate at least part of the repair process. For example, European patent EP2456612B1 discloses a system for automatically spraying a dissolving adhesive during tire retreading. The adhesive spraying occurs after the repair process and just before the tread is installed. The adhesive is sprayed into holes and / or craters automatically detected by acquiring a three-dimensional (or "3D") profile obtained by a profilometer. The sprayed adhesive is finally applied to the holes and / or craters by an automatic applicator. European patent EP3551443B1 discloses a system for automatically repairing damage during tire retreading. The disclosed system includes a remote and fixed laser profilometer that scans the entire tread by rotating the carcass.The system also includes a color camera on board a robot that takes pictures of damage once the rubber covering it has been removed. These color images are used to perform corrosion detection by analyzing the colors in the image (for example, by looking for the color red on cables). The processing algorithm uses the three-dimensional (3D) information from the profilometer to detect damage. The processing used to detect damage includes the construction of an average profile and comparison to this profile. These processing would be sufficient if the carcass could be considered as a rigid body. However, a carcass is rather a deformable body that can present many more or less local deformations (for example, a more or less pronounced out-of-roundness). These deformations can be considered as damages deviated from an average profile.The disclosed system cannot therefore adapt to all possible damages. European patent EP2414153B1 discloses a machine that performs an automatic process for identifying and working on defects on used tires. The disclosed machine comprises a vision system that relies on an infrared projector to obtain 3D information on the damage being analyzed. During the process, an automatic scan of the working surface of the tire allows the morphology of the damage to be identified and a comparison between the identified morphologies and a known damage reference. A selection of the job and a corresponding tool is made to perform the selected job on the identified damage.

[0010] There is nothing in the prior art that proposes establishing a link between the identification and localization of damage and the repair of damage using a processing tool in a completely automated manner. Thus, the disclosed invention relates to the automatic repair of all damage that requires repair on the surface of a carded carcass and / or on the surface of the first metal ply encountered under the rubber. Algorithmic processing relies on training images so that the algorithm learns to recognize the points of the image (three-dimensional and color) belonging to a carcass area of ​​a tire identified for retreading. This approach is scalable and will become increasingly robust because it is possible to integrate images of undetected carcass into the training in order to extend the scope of use of the algorithm.Additionally, carcass repair does not depend on any predefined recipe as the processing path is defined on the fly based on the carcass shape.

[0011] Summary of the invention

[0012] The invention relates to a method for repairing a carcass of an identified tire being retreaded, the repair method being implemented by at least one processor comprising a memory incorporating an image processing module which applies, to at least one neural network, the data representative of the captured images of the carcass of the identified tire, characterized in that the repair method comprises the following steps: a step of providing an automatic repair system of which the processor is a part for automatically recognizing an order of treatment of damage in carcass areas of the identified tire;a step of calibrating a repair device that is part of the automatic repair system, the repair device comprising a processing device supported by a pivoting elongated arm that extends to a free end allowing the installation of a processing tool along a common longitudinal axis; a step of positioning the identified tire in a processing space where the repair device processes it; a step of positioning at least one camera that is part of the automatic repair system at a reference distance relative to a rolling surface of the identified tire; a step of detecting damage comprising a learning phase from which images obtained are annotated to indicate where carcass areas containing damage to be treated are located; a step of classifying each damage to be treated in a classification associated with a corresponding treatment;a step of choosing at least one processing tool adapted to each damage detected and classified in the images obtained; and a step of carrying out a process of repairing the detected and classified damage; such that the repair device is configured on one or more parameters of the identified tire calculated by the image processing module to set the repair device in motion to repair the identified tire in each carcass area containing damage to be treated.;

[0013] In certain embodiments of the automatic repair method of the invention, the damage detection step comprises sector-by-sector processing for the identified tire comprising: for each sector of the identified tire, a step of scanning the sector followed by processing of the scanned sector; a scan of all successive sectors of the identified tire followed by processing of all successive scanned sectors; or a scan of the tire being processed at a station different from that where processing of the scanned sectors is carried out; such that processing of one or more scanned sectors is carried out by the repair device to recover a color and three-dimensional (3D) image of each scanned sector.

[0014] In certain embodiments of the automatic repair method of the invention, the step of calibrating the repair device comprises a calibration phase for estimating the pose of the camera relative to a base of the repair device.

[0015] In some embodiments of the automatic repair method of the invention, the step of calibrating the repair device comprises a step of positioning a calibration target in the processing space, during which the camera implements a process for estimating the pose of the camera in the frame of reference of the repair device. In some embodiments of the automatic repair method of the invention, during the step of positioning the identified tire, the identified tire is positioned in the vicinity of the repair device on a rotating drum arranged in the processing space, so that, during a repair process of a retreading process, the drum rotates the identified tire so that it can be treated sector by sector.

[0016] In certain embodiments of the automatic repair method of the invention, the step of positioning the camera comprises a step of verifying a scan carried out by the camera comprising the following steps: a step of identifying a horizontal central zone of the scan which is used to verify that the distance between the identified tire and the camera is correct; a step of calculating an average distance (D mO y) points inside the horizontal central zone; a step of preserving the 3D points in the form of a carcass mask comprising a binary image representing the points belonging to the carcass of the identified tire; a step of calculating again the average distance (D mO y) by considering only the points of the horizontal central zone which belong to the carcass of the identified tire to obtain a distance (D mO y surface); a distance comparison step (DmOy surface) with the reference distance of the camera; a step of calculating the two vertical lines which delimit the start and the end of the surface mask to make it possible to verify that the camera is centered in relation to the rolling surface of the identified tire; a step of calculating a central vertical line located in the middle of the vertical lines; and where the calculated central vertical line deviates from the center line of the image beyond a predetermined threshold, a step of applying a lateral correction to the position of the camera to recenter it in relation to the rolling surface of the identified tire.In some embodiments of the automatic repair method of the invention: during the step of detecting damage, a first neural network of the automatic repair system takes as input the color and 3D image to determine which points represent the carcass areas containing damage to be treated; during the step of classifying each damage to be treated, a second neural network of the automatic repair system takes as input the images of the carcass areas containing the damage to be treated and outputs a classification of each damage to be treated; and during the step of choosing at least one treatment tool, a third neural network of the automatic repair system takes as input the images of the carcass areas containing the classified damage and outputs at least one identified treatment tool to perform a corresponding repair.

[0017] In some embodiments of the automatic repair method of the invention, the damage repair process comprises the following steps: a step of mounting the treatment tool to be used to repair the identified and classified damage; a step of defining a surface trajectory of the treatment tool based on the identified and classified damage; and a step of repairing the damage to be treated.

[0018] In certain embodiments of the automatic repair method of the invention, the step of defining a surface trajectory of the treatment tool comprises: a step of defining a starting point in a framed region of the carcass containing the damage to be treated and in a direction of travel of the treatment tool; a step of defining the set of 3D points that the treatment tool must follow; such that the orientation of the treatment tool represents angles given by the orientation of the tool reference frame, in which: the X axis is oriented along the direction vector starting from the starting point and directed in the chosen direction of travel; the Z axis is oriented along the normal to the starting point; and the Y axis is automatically fixed according to the choices for the X and Z axes.

[0019] In certain embodiments of the automatic repair method of the invention, during the step of defining the set of 3D points: the framed region of the carcass containing the damage to be treated is cut into strips of a width equal to a width of the treatment tool, each strip being defined by a starting point and an arrival point; and the geometric position of the strips is offset so as to uniformly distribute an overhang on either side of the framed region of the carcass to be repaired; so that the set of starting and arrival points of all the strips is obtained to obtain the surface trajectory of the treatment tool.

[0020] In certain embodiments of the automatic repair method of the invention, during the step of repairing the damage to be treated, the repair device: positions the selected treatment tool on the starting point of the framed region containing the damage to be treated; and continues by moving the treatment tool along the inverse of the normal Z over a distance fixed by an offset comprising a fixed parameter; so that the previously defined surface trajectory is then moved following the movement carried out by the repair device until the starting point of the surface trajectory coincides with the starting point with offset.

[0021] In some embodiments of the automatic repair method of the invention, during the step of the step of repairing the damage to be treated: the initial surface trajectory is moved according to the movement made by the processing tool to superimpose the initial starting point on the starting point with offset; and the processing tool follows the repositioned surface trajectory to repair the repositioned framed region.

[0022] In some embodiments of the automatic repair method of the invention, the step of defining the surface trajectory and the step of repairing the damage of the damage repair process are repeated for all of the damage to be repaired with the selected treatment tool.

[0023] The invention also relates to a retreading method comprising the disclosed repair method.

[0024] Other aspects of the invention will become apparent from the following detailed description.

[0025] Brief description of the drawings

[0026] 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 like reference numerals designate like parts throughout, and in which:

[0027] [Fig 1] Figure 1 shows a schematic cross-sectional view of one embodiment of a known tire.

[0028] [Fig 2] Figure 2 shows a schematic view of one embodiment of a repair device that is part of an automatic repair system of the invention.

[0029] [Fig 3] Figure 3 represents an example of a visualization of a portion of a tire obtained during a repair method of the invention.

[0030] [Fig 4] Figure 4 represents a schematic view of a positioning of a camera of the automatic repair system of the invention relative to a carcass of an identified tire being retreaded.

[0031] [Fig 5] Figure 5 represents a schematic view of inputting color and 3D images to a neural network in determining which points represent areas of carcasses containing damage to be treated.

[0032] [Fig 6] Figure 6 represents a schematic view of inputting color and 3D images containing damage to a neural network in the classification of damage according to the treatment to be performed.

[0033] [Fig 7] Figure 7 represents a schematic view of inputting color and 3D images containing classified damage to a neural network in choosing a processing tool to repair the damage.

[0034] [Fig 8] Figure 8 shows an example of a carcass region containing detected and classified damage to be treated.

[0035] [Fig 9] Figure 9 represents an example of cutting and offsetting a carcass region containing detected and classified damage to be treated.

[0036] [Fig 10] Figure 10 represents an example of a surface trajectory obtained to carry out a movement of a processing tool.

[0037] [Fig 11] Figure 11 shows a front overview of an embodiment of a safety system of the automatic repair system of the invention during a repair process.

[0038] Detailed description

[0039] When considering the characteristics of a tire to be retreaded, its geometry must be taken into account. A tire is an object having a known geometry generally comprising several superimposed layers of rubber (or "layers"), as well as a metal or textile fiber structure constituting a reinforcing carcass of the tire structure. The nature of the rubber and the nature of the reinforcement are chosen according to the desired final characteristics. Figure 1 includes a schematic representation of a tire 10 comprising, in a conventional manner, two circumferential beads intended to allow the tire to be attached to a rim. Each bead comprises an annular reinforcing bead. The constitution of a tire is typically described by a representation of its constituents in a meridian plane, that is to say a plane containing the axis of rotation of the tire.The radial, axial and circumferential directions respectively designate the directions perpendicular to the axis of rotation of the tire, parallel to the axis of rotation of the tire, and perpendicular to any meridian plane. The expressions "radially", "axially" and "circumferentially" mean respectively "in a radial direction", "in the axial direction" and "in a circumferential direction" of the tire. The expressions "radially inward" and "radially outward respectively" mean "closer, respectively further, from the axis of rotation of the tire, in a radial direction.

[0040] The tire 10 also includes a tread 12 intended to contact a ground via a rolling surface 12a. It is reinforced by a reinforcement, or "carcass", which generally includes a plurality of reinforcing plies each having a plurality of reinforcing cords which are embedded in a layer of rubber-based material. More particularly, a crown reinforcement is provided which includes a working reinforcement 14 and a hoop reinforcement 16. The working reinforcement 14 has working layers represented by layers 14a and 14b.

[0041] The tire 10 also comprises two sidewalls (a sidewall 18 being shown in Figure 1) and two fillers 20 reinforced with a bead wire 22. A radial carcass layer 24 extends from one bead to the other, surrounding the bead wire in a known manner. The tread 12 comprises reinforcements consisting, for example, of superimposed layers comprising known reinforcing threads. In embodiments, the tire may include a rubber 26 which evacuates the static electricity produced during rolling.

[0042] The tread 12 is delimited, in the radial direction, by two circumferential surfaces, the most radially outer of which is the tread surface 12a and the most radially inner of which is called the tread base surface. The tread base surface (or “bottom surface”) is defined as the surface translated from the tread surface radially inward by a radial distance equal to the tread depth. It is common for this depth to be decreasing on the most axially outer circumferential portions (called “shoulders”) of the tread 12.

[0043] In addition, the tread of a tire is delimited, in the axial direction, by two lateral surfaces. The tread is further constituted by one or more rubber compounds. The expression "rubber compound" designates a rubber composition comprising at least one elastomer and a filler.

[0044] In order to obtain wet grip performance, cutouts are arranged in the tread 12. A cutout designates either a well, a groove, an incision, or a circumferential furrow and forms a space opening onto the tread surface 12a. The performance of a tread pattern must be sufficiently constant despite the wear of said strip to ensure the durability of the tire. Consequently, it is necessary to maintain a certain thickness of rubber materials between the bottom face of the cutouts (grooves or furrows) and the reinforcing elements to guarantee the endurance of the tire. For example, grooves must have sufficient widths to allow evacuation of the liquid present on the surface of the ground regardless of the stage of wear of the tread (12).

[0045] Referring to the figures, in which like numbers identify like elements, Figure 2 shows an embodiment of a repair device 100 that is part of an automatic repair system (or "system") of the invention. The automatic repair system of the invention implements a method of the invention ("method") for repairing by treatment tool a carcass of an identified tire being retreaded. The disclosed method incorporates a machine learning method that is based on data corresponding to images obtained from the identified tire, the algorithm used to analyze the carcass of the identified tire to place and operate the treatment tool in a treatment area of ​​the identified tire. It is understood that the method of the invention may be part of an existing retreading method to improve its repair process.In one embodiment of the repair device 100 of the system of the invention, the repair device comprises a robot having a processing device 102 supported by a pivotable elongated arm 104. The processing device 102 extends from the elongated arm 104 to a free end 102a which allows the installation of a processing tool 106 along a common longitudinal axis. For example, the processing tool 106 shown in Figure 2 comprises a brush which is selected from commercially available industrial brushes for repairing tires during retreading processes (e.g., industrial rotary brushes made of synthetic or metallic filaments). It is understood that the processing tool 106 may comprise one or more other equivalent processing tools (including, without limitation, brushes, knives, rasps, cards, cutters, grinding wheels and the like).

[0046] The attachment of the processing tool 106 is performed in a manner allowing its rotation relative to the longitudinal axis and also allowing its spinning around a predefined axis of rotation during a repair process. It is understood that the attachment of the processing tool 106 to the free end 102a of the processing device 102 may be performed by one or more known attachment means (including, without limitation, welding, gluing and equivalent means). Thus, the robot facilitates the repair of a variety of carcasses without interruption of the rotation and / or spinning of the processing tool 106.

[0047] The repair device 100 is set in motion so that the processing device 102 can perform the repair of a carcass of an identified tire P (see Figure 2). The repair of a carcass is performed by the repair device during a repair process implemented by the automatic repair system of the invention (as described below). The term "identified tire" (in the singular or plural) is used herein to refer to a tire being retreaded and present in the physical environment of the automatic repair system incorporating the repair device 100 (the physical environment being, for example, a retreading facility incorporating the repair device 100).

[0048] It is understood that the configuration of the repair device 100 is given by way of example. For example, the repair device 100 may comprise a fixed robot installed at a retreading facility, fixed, for example, to a support relative to which the robot extends (for example, a base 110 as shown in Figure 2). In this case, it is understood that the robot may be fixed to a ceiling, a wall, a floor or any support which allows the carrying out of the method of the invention during a retreading process. It is understood that the repair device 100 may comprise at least one roving robot. By "roving", it is understood that the gripping device may be set in motion either by integrated movement means (for example, one or more integrated motors) or by non-integrated movement means (for example, one or more mobile means including autonomous mobile means).It is understood that the repair device 100 may be a conventional industrial robot or a collaborative robot or even a delta or cable robot.

[0049] The carcasses that can be repaired by the repair device 100 during the repair process include grooves and furrows (but it is understood that the repair device is also capable of treating “slick” type tires). The grooves are the cutouts allowing the evacuation of water. A groove has a width such that the facing material walls delimiting it do not come into contact with each other, when the tread passes through the contact patch, when the tire is subjected to recommended inflation and load conditions as defined in particular by the European standards of the “European Tyre and Rim Technical Organization” or “ETRTO” in its “Standards Manual 2020 - Commercial Vehicle Tyres”.The compression and shear deformations of the relief elements delimiting the groove condition the pressures in contact with the ground and therefore the wear.

[0050] A groove is a substantially circumferential groove, and the lateral faces are substantially circumferential in the sense that their orientation can vary locally around plus or minus 45° around the circumferential direction. All the patterns belonging to the groove are found all around the tread, forming a substantially continuous whole (i.e., having discontinuities of less than 10% in length compared to the length of the patterns.) The circumferential grooves delimit ribs, each rib of which is composed of the patterns of the sculpture included between an axial edge of the tire and a neighboring axially outermost circumferential groove, i.e. between two neighboring circumferential grooves.

[0051] The cutout depth is the maximum radial distance between the tire's rolling surface and the bottom of the cutout.

[0052] The repair device 100 of the automatic repair system also includes a sensing system (not shown) for collecting information about the physical environment around the repair device. The sensing system includes one or more sensors (including one or more cameras) configured to perform two-dimensional (2D) and / or three-dimensional (3D) image sensing, 3D depth sensing, and / or other types of sensing of the physical environment around the repair device (it is understood that the terms "sensor" and "camera" are used interchangeably). In embodiments of the repair device 100 of the type shown in Figure 2, the one or more sensors of the sensing system are attached to at least one of the elongated arm 104 and the processing device 102 of the robot.In embodiments of the system of the invention, these sensors could be part of an overall detection system that employs these sensors together with one or more sensors positioned in the physical environment in which the repair device 100 operates.

[0053] In one embodiment of the repair device 100, the detection system includes at least one camera 200 that provides 3D images represented as a set of 3D points with X, Y, Z coordinates, and red, green, blue color values ​​(the "RGB" or "RGB-D" format) (referred to as an "RGB-D camera"). In this embodiment, an RGB-D camera is attached to either the elongated arm 104 or the processing peripheral 102 of the robot (the latter being shown as an example in Figure 2). Two or more RGB-D cameras may be oriented to provide a predetermined overlap between the cameras' fields of view. As used herein, the term "camera" includes one or more cameras.

[0054] RGB-D cameras typically provide depth information using depth maps, which are images where each pixel contains the distance between the camera and the corresponding point in space. Compared to traditional measurement methods such as manual measurement and other electronic device-based measurements, 3D point cloud data from RGB-D cameras has a much higher measurement rate. Using a sparser structure, a point cloud can be constructed from RGB-D images by calculating the real world (e.g., X, Y, Z coordinates) with the intrinsic data of a scanning camera.Thus, the information on the physical environment around the repair device 100 is obtained from 3D point cloud data obtained from sensing technologies that are capable of capturing the 3D surface geometries of the tires accurately and efficiently. These sensing technologies could be selected from commercially available devices (selected, for example, from cameras sold under the brand name PHOTONEO™, cameras sold under the brand name ENSENSO® from IDS, cameras sold under the brand name ZIVID® from Zivid AS, artificial vision systems sold by Cognex Corp., and their equivalents).

[0055] The term "point cloud" (singular or plural) is used here to refer to a collection or collections of data points in space. A camera or cameras (or equivalent device or devices) collects three-dimensional (3D) data and detects the surfaces of objects (e.g., tires identified to be treated during a retreading process of which the repair process is a part) through a series of coordinates. Storing the information as a collection of spatial coordinates can save space, as many objects do not fill a large portion of the environment. Even if the information is not visual, interpreting the data as a point cloud helps to understand the relationship between multiple variables through classification and segmentation.

[0056] It is understood that one or more cameras may include one or more programming modes, including by learning, to feed, modify, and train at least one neural network. Although the embodiments are described herein with respect to the use of one or more neural networks (e.g., convolutional neural networks or CNNs) as a machine learning model, other types of machine learning models may be used.These include, but are not limited to, models using linear regression, logistic regression, decision trees, support vector machines, naive Bayes, nearest neighbor (knn), K stands for clustering, random forest, dimensionality reduction algorithms, gradient-based algorithms, neural networks (e.g., autoencoders, CNNs, RNNs, perceptrons, logarithmic short-term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, generative adversarial (GAN), etc.) and their complements and equivalents. The one or more CNNs may be trained with ground truth data that is generated using sensor data representative of the movement of the repair device 100, including the positioning of the processing device 102 and the processing tool 106.

[0057] In some embodiments of the repair device 100, the camera 200 triggers when a segment of the identified tire enters the field of view of the camera. In cases where a tire portion is not visible in the image obtained by the detection system of the repair device 100 (e.g., the camera 200), a grip point may be placed at a known position relative to the sensor (e.g., at a known horizontal distance and a known vertical distance from the camera position). The detection system of the repair device 100 detects the presence of a carcass damage arrangement within the field of view of the detection system (e.g., the field of view of the camera 200), which triggers it to capture the image of a tread surface of the tire identified for retreading.In all embodiments of the system of the invention, the system "searches", in the image obtained by the detection system, for the presence of the damage "seen" by the repair device 100. If no damage is detected, the detection system continues to obtain the images until the search for the tire is exhausted.

[0058] The sensing system may determine information about the physical environment around the identified tire that may be used by a control system of the automatic repair system of the invention (the control system comprising, for example, software for planning the movements of the repair device 100). The control system could be located on the robot or it could be in remote communication with the robot. In embodiments of the automatic repair system, one or more 2D or 3D sensors mounted on the robot (including, without limitation, 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 obtained data, the control system may cause the robot to move to navigate between positions for taking images of the tires during repair processes.

[0059] To properly manage the handling of the repair device 100 which ensures the clear capture of images of the identified tire (for example, the handling of the robot and the positioning of the treatment tool 106 as shown in Figure 2), it is necessary to identify the tire being retreaded and detect the positioning of the damage concerned. Thus, the detection data refers to a plurality of recordings representative of the positioning of the damage of at least one identified tire or a part of an identified tire tracked over time.For example, the sensing data may include one or more of recordings of the positions of a reference point on a portion of the tire (e.g., the carcass) over time or at defined time intervals; sensor data taken over time; a video stream that has been processed using a computer vision technique; and / or data indicative of the operating status of the repair device 100 over time. In some cases, the sensing data may include data representative of one or more continuous movements of the repair device 100 before it stops to take one or more images of the tires being retreaded. The sensing system is therefore configured to generate the movement data of the repair device 100.

[0060] The detection system of the repair device 100 may receive a CAD file of the identified tire to match the location of a carcass area from the CAD file with the identified carcass area in real time to accurately locate and determine its coordinates. The detection system may receive the CAD file by data transmission methods known to those skilled in the art. The detection system may further include at least one camera and at least one sensor (not shown) to determine the location (i.e., coordinates) of the damage based on the data collected in real time and / or the contour profile of the identified tire.In embodiments of the invention, the detection system of the repair device 100 may also comprise a motion capture device selected from infrared sensors, ultrasonic sensors, accelerometers, gyroscopes, pressure sensors, and / or equivalent devices. In these embodiments, the system (and particularly the repair device 100) learns the movements which perform the taking of images of the tires without intervention of an operator during the retreading processes.

[0061] To implement the method of the invention by computer means, the automatic repair system of the invention comprises a communication network (or "network") which manages the data incoming to the system from various sources (for example, from at least one repair device 100 and its associated detection system). The communication network incorporates one or more communication servers (or "servers") each comprising one or more processors operatively connected to a memory. The memory is configured to store an application for analyzing data representative of the carcass areas of the imaged tires. The one or more processors comprise an analysis execution module which performs the processing of the images, the one or more processors of which are capable of executing programmed instructions stored in the memory to implement the steps of the repair method (as described below).

[0062] The input data to the automated repair system of the invention may include general information regarding the identified tire. The general information includes stored data regarding the identification of the identified tire (including, without limitation, its production origin, distribution and / or storage, production date, retreading history if applicable and mounting position and history). The general information may also include the retread rank (if applicable) of the identified tire. Data corresponding to a retread rank of an identified tire is typically managed by the entity that manages the use of one or more identified tires (e.g., person(s) and / or company(ies)) and / or the manufacturer of such tires.

[0063] The term "processor" (or, alternatively, the term "programmable logic circuit") means one or more devices capable of processing and analyzing data and including one or more software programs for processing them (e.g., one or more integrated circuits known to those skilled in the art to be 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 processor comprises one or more software programs for processing the data captured by the detection system (including the camera 200) of the repair device 100 (and the corresponding data obtained) as well as one or more software programs for identifying and locating variances and identifying their sources to correct them.

[0064] In the system of the invention, the memory may include both volatile and non-volatile memory devices. The non-volatile memory may include solid-state memories, such as NAND flash memory, keep-alive memory (KAM) for saving various operating variables while the processor is powered off, magnetic and optical storage media, or any other suitable data storage device that retains data when the repair device 100 is disabled or loses power. The volatile memory may include static and dynamic RAM that stores program instructions and data, including one or more learning applications.In embodiments of the system of the invention, the processor can configure the repair device 100 (and in particular the processing peripheral 102) on one or more parameters of the identified tire calculated by an image processing module incorporated in the memory of the processor. The image processing module analyzes the images of the identified tire and, more precisely, the images of the damage obtained by the detection system of the repair device 100.

[0065] The processor may also refer to a reference (e.g., a size chart of various tires) to make a final determination of a parameter or parameters of the identified tire. The reference may include known tire parameters corresponding to a plurality of known commercially available tires. For example, after the image processing module calculates one or more identified tire parameters, the processor may compare the calculated parameters with the known parameters stored in the reference. The processor may retrieve the known tire parameters corresponding to the commercially available tires that most closely match the calculated parameters to configure the processing device 102 (and thus place the processing tool 106 in precise position to repair damage in a corresponding carcass area of ​​the identified tire).The tire reference may include measurements corresponding to a plurality of commercially available tires. For example, for a tire of size 225 / 50R17, the number "225" identifies the tire's cross-sectional area in millimeters, the number "50" indicates the sidewall aspect ratio, and the measurement "RI 7" represents the rim diameter in inches (being approximately 43.18 centimeters).

[0066] Referring again to Figure 2, and further to Figures 3 to 10, a detailed description is given by way of example of embodiments of a method of the invention (or "method") for automatically repairing a carcass of a tire being retreaded. The method of the invention is implemented by the automatic repair system of the invention. It is understood that the system can implement the method in any physical environment without prior knowledge of the pattern of damage to be repaired on the tires identified for retreading.

[0067] As used herein, the term “method” or “process” may include one or more steps performed by at least one computer system having one or more processors to execute instructions that perform the steps. Unless otherwise indicated, any sequence of steps is exemplary and does not limit the described methods to any particular sequence.

[0068] In the following description, embodiments of the method of the invention are described which differ in the accuracy of the information obtained by the detection system (e.g., the camera 200).

[0069] In carrying out the method of the invention, the automatic repair system of the invention incorporates a combination of vision and machine learning techniques to correctly and quickly reconstruct the observed scene from three-dimensional (or "3D") scattered point clouds, derived from a view of the tire identified for retreading. The system of the invention therefore achieves continuous improvement in the recognition of carcass damage and its relative positioning along the tread surface of the identified tire.

[0070] By launching an embodiment of the method of the invention, the method comprises a step of calibrating the repair device 100. Prior to this step, the robot is positioned to scan an identified tire. During this step, when a scan of the identified tire is performed with the camera 200, three-dimensional (3D) points are retrieved which are expressed by their positioning relative to the camera. In order to be able to control the repair device 100 (for example, to indicate to it the position of each area to be treated on the carcass of the identified tire), these 3D points must be expressed at the robot base (for example, see the base 110 of the repair device 100 in Figure 2). The step of calibrating the repair device 100 therefore comprises a calibration phase for estimating the pose of the camera 200 relative to its base 110.

[0071] In one embodiment of the method, the step of calibrating the repair device 100 comprises a step of positioning a calibration target in a processing space where the robot will work. In one embodiment, the calibration target comprises a checkerboard which is positioned to allow a plurality of photos to be taken by varying the viewing angle each time. During this step, an optimization algorithm (incorporated, for example, in a processor and remoted by the camera 200) is used to estimate the pose of the camera 200 in the reference frame of the processing peripheral 102. Once the calibration has been carried out, the robot is capable of being brought into a position seen by the camera 200. This calibration is to be carried out as soon as the repair device 100 is installed in the processing space.

[0072] The method further comprises a step of positioning an identified damaged tire in the treatment space where the repair device 100 will treat it. The identified tire is positioned in proximity to the repair device 100 on a rotating drum (as known in the state of the art). During a repair process of the retreading method, the drum rotates the identified tire so that it can be treated sector by sector. It is understood that the identified tire could be positioned on a work table or on an equivalent support so that the system of the invention can treat it. The support can be configured to move in a rotary manner, in an alternating vertical manner and / or in an alternating horizontal manner, thus allowing the treatment of a variety of tires.

[0073] The “sector-by-sector” processing refers to several embodiments of the method of the invention incorporating one or more scans followed by a treatment of the carcasses of the identified tire. In one embodiment of the method of the invention, the sector-by-sector processing comprises, for each sector of the tire being treated, a scan of the sector followed by a treatment of the scanned sector (for example, a treatment of the carcass areas of the scanned sector carried out by the treatment tool 106). In another embodiment of the method of the invention, the sector-by-sector processing comprises a scan of all successive sectors of the tire being treated followed by a treatment (for example, brushing, machining and / or grinding) of all successive scanned sectors.In another embodiment of the method of the invention, the sector-by-sector processing comprises a scan of the tire being processed (either a scan by individual sectors or a scan of all successive sectors) at a station different from that where processing (for example, brushing, machining and / or grinding) of the scanned sectors is performed. In the latter case, at least one additional camera (not shown) would be used at the remote station to perform all the scans. Then, the camera 200 of the repair device 100 would be used to perform a single scan to locate the position of the sector in the field of the camera 200 among the set of scans performed at the remote station. In all these embodiments of the method of the invention, it is understood that processing would be performed on the sectors requiring processing.Thus, if no damage requiring treatment is identified in a scan of a sector, the repair device 100 passes the affected sector to a scanned sector where one or more damages are identified for treatment.

[0074] The method further comprises a step of positioning the camera 200 at a reference distance relative to the carcass of the identified tire (i.e., the damaged carcass portion). During this step, the camera 200 is centered relative to the carcass of the identified tire (being a right / left positioning). For this, the robot begins by positioning the camera 200 in front of the identified tire in a position that allows the camera to see all possible tire dimensions (including diameters and widths). A scan is then carried out by the camera 200, then it is analyzed to verify whether the camera 200 is correctly positioned.

[0075] Referring to Figure 3, the 3D points are expressed relative to a reference frame placed at the center of the lens of the camera 200. If this reference frame is represented in 3D by scanning a portion of a tire (see “3D visualization” in Figure 3), the Y axis is directed toward the ground, and the Z axis is directed toward the identified tire, and the X axis is perpendicular to the Y and Z axes in order to form an orthonormal reference frame. If this reference frame is represented in 2D (see “2D visualization” in Figure 3), the origin of the reference frame is at the center of the image: the X axis is oriented to the right, the Y axis is oriented downwards and the Z axis is oriented toward the tire.

[0076] Referring to Figure 4, the correct positioning of the camera 200 during this step is described. The areas 300 represent the points belonging to the carcass of the identity tire. We first consider a horizontal central area of ​​the scan which is used to verify that the distance between the identified tire and the camera 200 is correct. An average distance D mO y of the points is calculated inside this horizontal central zone, which is represented by the lines 300 A. Then, we keep the 3D points whose distance in Z belongs to an interval [D m oy-mar ge , D m oy+mar ge]. These points represent the points belonging to the carcass of the identified tire (therefore the relative distances vary according to the parameters of the identified tire). All of these points can be represented in the form of a binary image (identified as the "carcass mask" or the "binary mask") where each point kept represents a point belonging to the carcass of the identified tire (these points are represented by the zones 300 in Figure 4). Afterwards, to obtain a distance D mO y surface, we calculate again the distance D mOy by only considering the points of the horizontal central zone that belong to the carcass of the identified tire. By comparing this distance with the reference distance of the camera 200 (because the camera 200 must always be positioned at the reference distance relative to the carcass of the identified tire), we can calculate the frontal correction to be applied to the camera. Then, we calculate the two vertical lines 300B which delimit the beginning and the end of the carcass mask and therefore make it possible to check that the camera 200 is well centered relative to the rolling surface of the identified tire (see Figure 4). We calculate the central vertical line located in the middle of the vertical lines 300B. If this central vertical line deviates too much from the center line of the image, then we will apply a lateral correction to the position of the camera 200 to recenter it relative to the carcass of the identified tire.

[0077] Considering the repair device 100, its initial positioning (and, in applicable cases, the initial orientation of the processing device 102, and thus, the processing tool 106) is determined from the data obtained via the acquisition of the images of the automatic repair system and the physical environment in which the automatic repair system operates (for example, as shown in Figure 2). The analysis execution module of the processor may employ an automatic and adaptive repositioning algorithm to find an ideal starting position of the repair device 100, thus making it possible to execute programmed instructions stored in the memory to perform the taking of the images.The algorithm allows for continuous improvement across all image captures, ensuring that the system (and particularly the repair device 100) improves from the experience it acquires, particularly in the selection of carcass areas to be treated by performing the repair processes during the tire retreading processes. The method further comprises a damage detection step that is performed sector by sector for the identified tire. During this step, for each sector, the repair device 100 positions the 3D camera to scan the sector and retrieve a color and three-dimensional (3D) image (“the color and 3D image”) of the sector (it is recalled that sector-by-sector processing is involved during this step). At each point of the image, the color of the point is known, but also its three-dimensional position relative to the camera 200.

[0078] Once the scan is completed, during the damage detection step, a first neural network of the system (a "detection network") takes as input the color and 3D image to determine which points represent damage to be treated (as used herein, the term "neural network" includes one or more neural networks). Before the first neural network can be used, a training phase is performed to fix its parameters. For this, several input images are annotated (for example, manually annotated by experts in the field). For each input image, the annotation consists of indicating where the carcass areas containing damage to be treated are located (represented as an example in Figure 5 by the boxed regions 5A). This training phase is performed once to fix the parameters of the first neural network, after which the first neural network can be used on new images.

[0079] Once the first neural network outputs the carcass areas containing damage to be treated, the method of the invention further comprises a step of classifying each damage into an associated classification. During this step, a second neural network of the automatic repair system (a "classification network") takes as input the image of the carcass area containing the damage to be treated (for example, the boxed regions 5A of Figure 5), and it outputs a classification of each damage according to the treatment to be done (as used herein, the term "neural network" includes one or more neural networks). The second neural network operates regardless of the number of distinct classifications (represented for example in Figure 6 by classifications c1, c2, . . .cN or N varies depending on the number of distinct classifications identified).The form of damage can be related to its severity with different damage varying according to distinct damage classes (which include, but are not limited to, tread damage, tear damage, cut damage and puncture damage). By coupling the outputs from the first neural network with those from the second neural network, in-depth knowledge is automatically obtained on the location and type of damage present on the casings. This knowledge is then very useful in guiding treatment choices planned for tires being retreaded.

[0080] The method of the invention further comprises a step of choosing the most suitable treatment tool for each damage in the obtained images. During this step, a third neural network of the system (a "tool choice network") takes as input the image of the carcass area containing the classified damage, and outputs one or more treatment tools identified to perform the corresponding repair (represented by way of example in Figure 7 by tools ol . . .oN or N varies depending on the number of distinct tools identified) (as used herein, the term "neural network" includes one or more neural networks). Before the third neural network can be used, a training phase is carried out to fix the parameters of this neural network. For this, several input images have been annotated (for example, manually annotated by experts in the field).For each input image, the annotation consists of indicating the repair tool best suited to the damage present in the image (for example, the repair tool 106 in Figure 2 represented as an example by a brush). This training phase is carried out once to fix the parameters of the tool choice network, after which the third neural network can be used on new images. Thus, the third neural network works regardless of the number of distinct tools intended for the repair of the identified tire.

[0081] The method of the invention further comprises a step of carrying out a process for repairing the detected and classified damage. The damage repair process comprises a step of mounting the treatment tool 106 chosen to repair the damage identified and classified during the previous steps. During this step, one or more tools in the list of tools output by the third neural network are installed on the robot (and particularly on the repair device 100) automatically. The various repair tools (which include, without limitation, cleaning, machining and / or grinding tools) could be installed on a tool holder (not shown). The robot automatically installs the chosen tool at the end of the elongated arm 104 of the treatment device 102. The damage repair process further comprises a step of defining the surface trajectory of the treatment tool.The outputs of the first neural network (the detection network) and the third neural network (the tool selection network) provide a list of damages predicted for treatment by the treatment tool 106 mounted on the robot. Referring to Figure 8, each damage in this list is characterized by a carcass region 8A containing the damage to be treated. The 3D position of the carcass region 8A relative to the base 110 of the repair device 100 is known.

[0082] From this region 8A, we define, during this step, the surface trajectory of the processing tool which corresponds to the set of 3D points that the processing tool must follow to cover the entire region. To do this, we begin by defining a starting point and a direction of travel of the processing tool. As an example, we assume in Figure 8 that the starting point is located at the bottom right of the carcass region 8A and that the direction of travel is from bottom to top. It is understood that another starting point could be considered (i.e., bottom left, top right and top left) and for another direction of travel (i.e., top to bottom, right to left and left to right) depending on the intended orientation of the chosen processing tool. By defining the starting point and the direction of travel of the tool, we define the orientation of the tool over the entire trajectory.

[0083] Referring again to Figure 8 and further to Figure 9, the orientation of the processing tool represents the three (3) angles given to the processing tool, and these angles are given by the orientation of the tool frame of which:

[0084] The X axis is oriented along the direction vector starting from the starting point and directed in the chosen direction of travel (as shown in Figure 8, from bottom to top);

[0085] The Z axis is oriented along the normal to the starting point; and

[0086] The Y axis is automatically set based on the choices for the X and Z axes.

[0087] Once the orientation of the treatment tool 106 is fixed, the step of defining the surface trajectory comprises a step of defining all the 3D points that the treatment tool must follow. During this step, the carcass region 8A containing the damage is cut into strips 9A of a width equal to the width of the treatment tool (this value is known). Referring to Figure 9, each strip 9A is defined by a starting point 9B and an arrival point 9C. The width of the carcass region 8A is not necessarily a multiple of the width of the chosen treatment tool. The last strip of the carcass region 8A can therefore overflow from the region. To limit this overflow, the geometric position of the strips 9A is offset so as to distribute this overflow uniformly on either side of the carcass region to be repaired.Once the cutting and offsetting is done (see Figure 9), it is enough to list all the start and end points of all the 9 A bands to obtain the surface trajectory of the processing tool.

[0088] The damage repair process further comprises a damage repair step during which the repair device 100 positions the selected treatment tool 106 at the starting point of the carcass region containing the damage. The repair device 100 continues by moving the treatment tool along the inverse of the Z normal by a distance fixed by an offset (see Figure 10). This offset is a fixed parameter which depends on the type of repair to be carried out.

[0089] During this step, in addition to this offset, a safety system 400 of the automatic repair system of the invention is used so that the repair device 100 stops its movement where the treatment tool contacts a metal sheet (for example, during rubber removal from the carcass of the identified tire). Referring to Figure 11, an embodiment of the safety system 400 is shown with the treatment device 100 during the repair of an identified tire P' in its treatment space. In embodiments of the automatic repair system incorporating the safety system 400, the safety system comprises: a first electrode 402 which is arranged to be placed opposite the carcass of the identified tire, at a distance from an electrically conductive insert 404 of the identified tire,so as to form with F electrically conductive insert a first dipole of which a first terminal is formed by the first electrode 402 and a second terminal is formed by F electrically conductive insert 404; a second electrode 406 which is associated with the treatment tool 106 (being, for example, a gum removal tool) in such a way that, when the treatment tool 106 comes into contact with the electrically conductive insert 404,an electrical connection is established between the second electrode 406 and the electrically conductive insert 404 forming the second terminal of the first dipole; and a control unit 408 which is arranged to measure an impedance of a detection circuit containing the first dipole and to detect a variation in impedance of the detection circuit 410 caused by the electrical connection of the first dipole with the second electrode 406 caused by the treatment tool 106 coming into contact with the electrically conductive insert 404.,

[0090] Such a safety system is disclosed in the Applicant's application FR2213096. Following the positioning of the treatment tool 106 during the damage repair step, the tool is positioned at a starting point with an offset. The previously defined surface trajectory is then moved following the movement made by the repair device 100 until the starting point of the surface trajectory coincides with the starting point with an offset. Thus, the starting point with an offset becomes the new starting point of the surface trajectory.

[0091] The repair device 100 then executes the repositioned surface trajectory to repair the entire carcass region 8A containing the damage to be treated (see Figure 10). During a repair, the repair device 100 begins by bringing the treatment tool 106 to the starting point of the surface trajectory (see point 10A of Figure 10). The repair device 100 then moves in the opposite direction to the normal (see arrow A of Figure 10) for a distance fixed by an offset parameter or until it touches the first metal layer encountered (the movement of the treatment tool is represented by arrow B of Figure 10). The initial surface trajectory is then moved according to the movement made by the treatment tool (see arrow B of Figure 10) to superimpose the initial starting point (see point 10A of Figure 10) on the starting point with the offset (point 10B of Figure 10).The processing tool 106 then follows the repositioned surface trajectory to repair the carcass region containing the damage (the repositioned carcass region 8A is represented by the dotted region 8A').

[0092] The surface trajectory definition step and the damage repair step of the damage repair process are repeated for all damages to be repaired with the selected processing tool. For the next tool, the processing tool mounting step is repeated. The steps of the damage repair process are repeated for all processing tools output from the tool selection network (the third neural network).

[0093] Those skilled in the art will recognize that numerous image processing techniques may be used to select and determine the parameters of target tires. Several commercially available image processing systems may be used. In a tire retreading facility, a vision system may be used to detect the presence of a tire in the field of view of the camera 200, which triggers the camera to capture the image of the identified tire for processing.

[0094] In embodiments of the method of the invention, one or more steps of the method may further comprise a step of scanning the physical environment containing the repair device 100. In embodiments of the method, this step further comprises a step of measuring the physical environment to arrive at an exact positioning of the treatment tool 106. During this step, one or more sensors may be employed to capture data corresponding to the treatment tools and the tires in order to determine the shapes and / or positions of the individual tires. This information is relevant to enable accurate modeling of the method of the invention in order to optimize the time of an associated retreading process.

[0095] A method of the invention may be carried out by the control of the PLC and may include pre-programming of the management information. For example, a setting of the method may be associated with the parameters of the tire being retreaded, and / or the properties of the tires treated in a retreading installation incorporating the repair device 100 (for example, aircraft tires, heavy-duty tires, etc.). The system of the invention (and / or an installation incorporating this system) may easily repeat one or more steps of the method of the invention in a determined order to ensure the substantially complete repair of the carcass of the treated tire.

[0096] The automatic repair system of the invention (and / or a retreading facility incorporating this system) may include pre-programming of management information. For example, a process setting may be associated with the parameters of the typical physical environments in which the system operates. In embodiments of the invention, the automatic repair system (and / or a retreading facility incorporating this system) may receive voice commands or other audio data representing, for example, a start or stop of the repair and / or a loading / unloading of a drum dedicated to retreading tires. A request may be made that includes a request for the current status of an ongoing retreading process cycle. A generated response may be represented audibly, visually, tactilely (e.g., using a haptic interface), and / or in a virtual and / or augmented manner.

[0097] This response, combined with the corresponding data, can be stored in a neural network.

[0098] For all embodiments of the automatic repair system, a monitoring system could be implemented. At least part of the monitoring system may be provided in a portable device such as a mobile network device (e.g., a mobile phone, a laptop, one or more network-connected wearable devices (including “augmented reality” and / or “virtual reality” devices), network-connected wearable clothing / jewelry, and / or any combinations and / or equivalents). It is envisaged that detection and comparison steps may be performed iteratively.

[0099] In one embodiment, the method of the invention may comprise a step of training the automatic repair system to recognize values ​​representative of the tires to be retreaded (for example, values ​​of the internal diameter and the external diameter) and to make a comparison with targeted values ​​(for example, to carry out an order of tires incorporating the retreaded tires). Each step of the training may include a classification generated by self-learning means. This classification may include, without limitation, the parameters of the selected tires, the durations of the process cycles and the expected values ​​at the end of a process in progress (for example, the number of tires retreaded during a cycle to reach a desired level).

[0100] The wide variety of damage used when training the three neural networks makes the invention's repair system robust to all existing damage. Thus, the three neural networks do not require any advance knowledge of all existing damage to operate.

[0101] All repair treatments are independent of the number and type of damage present on the carcass to be repaired. The repair system of the invention adapts in real time to the damage encountered. No predefined recipes are used. In addition, the number of treatment tools is not limited, which makes the system scalable in case of addition or deletion of certain types of repair.

[0102] The terms "at least one" and "one or more" are used interchangeably. Ranges that are presented as "between a and b" encompass the values ​​"a" and "b".

[0103] Although particular embodiments of the disclosed apparatus have been illustrated and described, it will be understood that various changes, additions, and modifications may be practiced without departing from the spirit and scope of the present disclosure. Accordingly, no limitations should be imposed on the scope of the disclosed invention except those set forth in the appended claims.

Claims

Claims 1. A method of repairing a carcass of an identified tire being retreaded, the repair method being implemented by at least one processor comprising a memory incorporating an image processing module which applies, to at least one neural network, the data representative of the captured images of the carcass of the identified tire, characterized in that the repair method comprises the following steps: a step of providing an automatic repair system of which the processor is a part to automatically recognize an order of treatment of damage in carcass areas of the identified tire;a step of calibrating a repair device (100) which is part of the automatic repair system, the repair device (100) comprising a processing peripheral (102) supported by a pivoting elongated arm (104) which extends to a free end (102a) allowing the installation of a processing tool (106) along a common longitudinal axis; a step of positioning the identified tire in a processing space where the repair device (100) processes it; a step of positioning at least one camera (200) which is part of the automatic repair system at a reference distance from a rolling surface of the identified tire; a step of detecting damage comprising a learning phase from which images obtained are annotated to indicate where there are carcass areas containing damage to be treated;a step of classifying each damage to be treated in a classification associated with a corresponding treatment; a step of choosing at least one treatment tool (106) adapted to each damage detected and classified in the images obtained; and a step of carrying out a process of repairing the damage detected and classified; so that the repair device (100) is configured on one or more parameters of the identified tire calculated by the image processing module to set the repair device (100) in motion to repair the identified tire in each carcass zone containing damage to be treated.; 2. The repair method of claim 1, wherein the damage detection step comprises sector-by-sector processing for the identified tire comprising: for each sector of the identified tire, a step of scanning the sector followed by processing of the scanned sector; a scan of all successive sectors of the identified tire followed by processing of all successive scanned sectors; or a scan of the tire being processed at a station different from that where processing of the scanned sectors is carried out; such that processing of one or more scanned sectors is carried out by the repair device (100) to recover a color and three-dimensional (3D) image of each scanned sector.

3. The repair method of claim 1 or claim 2, wherein the step of calibrating the repair device (100) comprises a calibration phase for estimating the pose of the camera (200) relative to a base (110) of the repair device (100).

4. The repair method of claim 3, wherein the step of calibrating the repair device (100) comprises a step of positioning a calibration target in the processing space, during which the camera (200) implements a process for estimating the pose of the camera (200) in the reference frame of the repair device (102).

5. The repair method of claim 4, wherein, during the step of positioning the identified tire, the identified tire is positioned in proximity to the repair device (100) on a rotating drum arranged in the processing space, so that, in the course of a repair process of a retreading process, the drum rotates the identified tire so that it can be processed sector by sector.

6. The repair method of any one of claims 1 to 5, wherein the step of positioning the camera (200) comprises a step of verifying a scan performed by the camera (200) comprising the following steps: a step of identifying a horizontal central area of ​​the scan which is used to verify that the distance between the identified tire and the camera (200) is correct; a step of calculating an average distance (D mOy) points inside the horizontal central zone; a step of preserving the 3D points in the form of a carcass mask comprising a binary image representing the points belonging to the carcass of the identified tire; a step of calculating again the average distance (D mO y) by considering only the points of the horizontal central zone which belong to the carcass of the identified tire to obtain a distance (D mO y surface); a distance comparison step (D mOy surface) with the reference distance of the camera (200); a step of calculating the two vertical lines (300B) which delimit the start and the end of the surface mask to make it possible to verify that the camera (200) is centered relative to the rolling surface of the identified tire; a step of calculating a central vertical line located in the middle of the vertical lines (300B); and where the calculated central vertical line deviates from the central line of the image beyond a predetermined threshold, a step of applying a lateral correction to the position of the camera (200) to recenter it relative to the rolling surface of the identified tire.

7. The repair method of claim 6, wherein: during the damage detection step, a first neural network of the automatic repair system takes as input the color and 3D image to determine which points represent the carcass areas containing damage to be treated; during the step of classifying each damage to be treated, a second neural network of the automatic repair system takes as input the images of the carcass areas containing the damage to be treated and outputs a classification of each damage to be treated; and during the step of choosing at least one treatment tool (106), a third neural network of the automatic repair system takes as input the images of the carcass areas containing the classified damage and outputs at least one identified treatment tool to perform a corresponding repair.

8. The repair method of claim 7, wherein the damage repair process comprises the following steps: a step of mounting the treatment tool (106) to be used to repair the identified and classified damage; a step of defining a surface trajectory of the treatment tool (106) based on the identified and classified damage; and a step of repairing the damage to be treated.

9. The repair method of claim 8, wherein the step of defining a surface trajectory of the treatment tool comprises: a step of defining a starting point in a framed region (8A) of the carcass containing the damage to be treated and in a direction of travel of the treatment tool (106); a step of defining the set of 3D points that the treatment tool (106) must follow; such that the orientation of the treatment tool represents angles given by the orientation of the tool reference frame, in which: the X axis is oriented along the direction vector starting from the starting point and directed in the chosen direction of travel; the Z axis is oriented along the normal to the starting point; and the Y axis is automatically fixed according to the choices for the X and Z axes.

10. The repair method of claim 9, wherein, during the step of defining the set of 3D points: the framed region (8A) of carcass containing the damage to be treated is cut into strips (9A) of a width equal to a width of the treatment tool, each strip (9A) being defined by a starting point (9B) and an arrival point (9C); and the geometric position of the strips (9A) is offset so as to distribute uniformly an overflow on either side of the framed region (8 A) of the carcass to be repaired; so that all the starting and finishing points of all the strips (9 A) are obtained to obtain the surface trajectory of the treatment tool.

11. The repair method of claim 10, wherein, during the step of repairing the damage to be treated, the repair device (100): positions the selected treatment tool (106) on the starting point of the framed region (8A) containing the damage to be treated; and continues by moving the treatment tool along the inverse of the normal Z over a distance fixed by an offset comprising a fixed parameter; so that the previously defined surface trajectory is then moved following the movement carried out by the repair device (100) until the starting point of the surface trajectory coincides with the starting point with offset.

12. The repair method of claim 11, wherein, during the step of the step of repairing the damage to be treated: the initial surface trajectory is moved according to the movement made by the treatment tool (106) to superimpose the initial starting point on the starting point with offset; and the treatment tool (106) follows the repositioned surface trajectory to repair the repositioned framed region (8A).

13. The repair method of claim 12, wherein the step of defining the surface trajectory and the step of repairing the damage of the damage repair process are repeated for all of the damage to be repaired with the selected treatment tool.

14. A retreading method comprising the repair method of any one of claims 1 to 13.

Images