Method and device for processing components of a sporting article using a robot

Abstract

The present invention relates to a method (100) for processing a component for a sporting article, in particular a shoe sole, by means of a robot, the method comprising: (a.) creating (110) a first path (240) with respect to the component to be processed, comprising a list of points or a predetermined trajectory; (b.) determining (120) a 3D scan (610) of the component to be processed by means of a 3D scanner; (c.) calculating (130) a global offset between the first path (240) and the 3D scan (610) of the component to be processed; (d.) calculating (150) a plurality of local offsets between the first path (240) and the 3D scan (610) of the component to be processed; (e.) creating (160) a second path (810) based on the first path (240), the calculated global offset, and the calculated local offsets; and (f.) Transmitting (170) the second path (810) to the robot, which performs the processing of the component based on the second path (810).

Description

1. Technical FieldThe present invention relates to a method and a device for processing a component of a sports article, in particular a shoe sole and / or an upper part of a shoe, by means of a robot, based on a 3D scan of the component to be processed.2. Prior ArtThe production of sports articles, in particular shoe soles and / or an upper part of a shoe, comprises a plurality of processing steps in which components of the sports article are processed. Such processing steps may include trimming, trimming, decorating, grinding, gluing or gluing such components. Due to material inconsistencies of the components, which among other things leads to shrinkage, warping, curving or bending of the components, such processing steps are difficult to automate and are often carried out manually. Manual processing or post-processing causes higher production costs as compared to automated methods and may not ideally process components, leading to defective parts and, in turn, an increase in costs.Previously automated methods for processing components of sports articles by means of a robot are based on the so-called "best-fit" principle. First, a computer-aided design (CAD) model of the ideal components is created. Furthermore, an ideal processing path is created, along which the processing of the components is carried out. This ideal processing path can have been brought to the system either by means of learning techniques or can be explicitly specified, for example by means of a sequence program. The predetermined ideal path is then applied to the CAD model. In both cases, the path typically contains a list of points that are approached by a robot. Furthermore, a camera system is used which captures the position and orientation of the entire real components to be processed, for example by a scan. The data and information thus obtained are processed by the system and are used to calculate a global offset (offset) by matching the scan with the CAD model. This global offset may include both translation and rotation and allows the system to accurately determine the location and orientation of the components to be processed. The offset thus obtained is valid for the entire machining path of the robot, and the machining path is corrected, i.e., rotated and / or shifted, according to the global offset. This allows the system to correct an erroneous position of the components as a whole.Deviations between real components and CAD model, which are due to material inconsistencies of the components, which lead to, among other things, shrinkage, distortion, bending or bending of the components, cannot be corrected. Since the real components to be machined no longer correspond to the CAD model due to the material inconsistencies, even after a correction of a global offset between real components and CAD model, but the robot continues to follow the ideal machining path related to the CAD model, the actually executed robot movement does not correspond to the optimum real machining path. This results in inaccurately machined parts which may degrade the quality of the final product. Depending on the magnitude of the deviation, the components after processing may even be unusable and must be excluded from further processing or must be processed manually. This leads to increased manufacturing costs, a higher working time per component and possibly a poorer quality of the components or of the final product.US 2002 / 0 157 588 A1 relates to a method for sewing a workpiece together with another workpiece or for sewing a decorative stitch line along a workpiece. In one embodiment, the method includes providing a first workpiece having a first edge along which a stitch is to be made and providing a template having an edge generally corresponding to at least a portion of the first edge of the first workpiece. The stencil consists of a material whose color contrasts with the color of the first workpiece. The first workpiece is then placed against the template such that the first edge of the workpiece abuts at least a portion of the edge of the template. Then, sewing is performed by a computer-controlled sewing machine having an image processing function along a path substantially corresponding to a boundary between the first edge of the first workpiece and the edge of the template. If necessary or appropriate, the computer controlled sewing machine may adjust its sewing path in response to the recognition of the template. Subsequently, after the completion of the sewing operation, the first workpiece is separated from the template.US 2022 / 0 245 293 A1 describes a tool path for machining a shoe upper. The tool path can be generated such that substantially only the surface of the shoe that is bounded by a bite line is machined. The bite line can be defined to correspond to the connection between the shoe upper and a shoe bottom unit. Bite line data and three dimensional profile data representing at least a portion of a surface of a shoe upper bounded by a bite line may be used in combination to create a tool path for working the surface of the shoe upper, such as automatically applying adhesive to the surface of a shoe upper bounded by a bite line.3. SUMMARY OF THE INVENTIONTherefore, the object of the present invention is to provide a method and a device which enable the automation of the processing of components of a sports item by the use of a robot.This object is achieved by a method for processing a component of a sports article by means of a robot, comprising the steps of: a) creating a first path with respect to the component to be processed, comprising a list of points or a predefined trajectory; b) determining a 3D scan of the component to be processed by means of a 3D Sanner; c) calculating a global offset between the first path and the 3D scan of the component to be processed; d) calculating a plurality of local offsets between the first path and the 3D scan of the component to be processed; e) creating a second path based on the first path, the calculated global offset and the calculated local offsets; and f) transmitting the second path to the robot performing the processing of the component based on the second path.The method according to the invention minimizes the deviation of the real component to be processed of a sports item from an ideal, computer-generated model, maximizes the individual adaptation of a path and thus optimizes the quality of the automatically processed component. In the context of the invention, a component of a sports article is understood to mean a spatially delimitable section of the sports article. The method can be used for processing a plurality of such components of a sports article. In addition, a component according to the invention can also be understood to mean the entire sports article. This applies in particular when it cannot be divided into spatially demarcate sections. The sports article may be a sports shoe and the component may be a sole or a part of a sole of the sports shoe. Furthermore, the component can also be an upper part of the shoe.For individually adapting a path for processing a component of a sports item, a first path is first created with respect to the component. This path relates to an ideal component and may be given by a list of points or by a curve through which the robot is to pass. The list of points or the curve is defined with respect to the robot coordinate system and serves as the starting point for the processing of the component, regardless of its individual properties.In the next step, a 3D scanner is used for scanning or detecting the component to be processed. This enables the recording of individual properties and features of the component to be processed, on which the individual adaptation of the second path is based. These individual characteristics and features may include deviations from the ideal component and may include shrinkage, warping, curving, bending, or the like thereof.In the next step, a global offset between the first path and the 3D scan of the component to be operated is calculated. This global offset can include a translation or rotation of the first path and serves for a first adaptation of the path defined with respect to an ideal component and the real component.In the next step, a plurality of local offsets between the first path and the 3D scan of the component to be processed is calculated. This allows, in addition to the inclusion of global properties of the real component in the preceding method step, the inclusion of individual local properties. Based on these local offsets, a second path is then calculated, starting from the first path and the determined global offset, which takes into account the local individual properties and features of the real component. This second path thus minimizes the deviation of the real component from the first path created with respect to an ideal component.In the last step, the second path is transmitted to a robot or robot system. On the basis of this second path, the robot carries out the processing of the component previously detected by means of 3D scanning. The processing may include, for example, trimming the component, e.g., the sole or a part of the sole. Further, the processing may include polishing the component or applying adhesive to the component. Decorative elements can also be applied to the component during processing, e.g. colored layers.The first path can be determined based on a CAD (computer-aided design) model of the component to be processed. CAD offers the advantage that the component to be machined can be developed on the computer in a cost-effective and quick manner. If CAD data of the components to be processed are available, these can be incorporated directly into the method according to the invention. In this way, the CAD data is used not only for designing the component but also for manufacturing it.The component to be processed can be detected or scanned by an optical 3D scanner. This enables fast imaging and a high level of detail.The calculation of the global offset can be carried out on the basis of a feature of the component to be processed that can be detected by the 3D scanner. This feature is component dependent and may be, for example, a depression, ridge or chamfer. The selection of the feature may depend on the level of detail of the 3D scanner used.The component to be processed can be divided into a plurality of spatial sections on the basis of the CAD model on which the first path is based, and the calculation of the local offsets with respect to the plurality of spatial sections of the component to be processed can be carried out. A higher number of spatial sections thus leads to a higher number of local offsets and consequently to a more accurate or more individual creation of a second robot path.The plurality of spatial sections which have been created with respect to the CAD model on which the first path is based can be cuboids. These allow simple and clear partitioning of the CAD model and thus of the first path. Cuboids are mathematically simple to handle and promote rapid numerical processing.The first path and the second path may include a plurality of spatial points. By means of a higher number of spatial points, inter alia a curvature of the component to be machined can be taken into account.There may be a bijective correspondence between the points of the first path and the points of the second path. This means that there is a one-to-one correspondence between points of the first and second paths. The bijective correspondence between the points of the first and second paths ensures that the curvature of the component to be processed can also be taken into account in the second path. Furthermore, the bijective correspondence limits the geometric complexity of the second path and thus the runtime of the robot with respect to the second path. Consequently, the runtime of the robot can be influenced already before creating the second path, namely by creating the first path.A further aspect of the present invention relates to a device which is configured to carry out the method described herein. It is understood that what applies herein with respect to the method for processing a component of a sports item by means of a robot also applies to the device, in particular with respect to the functions, features, embodiments and advantages of the last and the method. These are therefore not mentioned separately here again.4. Brief Description of the FiguresExemplary embodiments of the invention are described below with reference to the figures. The figures show: FIG. 1 : Flow diagram of a possible embodiment of the method according to the invention; FIG. 2 : CAD model of the sole, the gripper and the flange as well as the first robot path created on the basis of the CAD model of the sole; FIG. 3 : CAD model of the calibration adapter, consisting of a calibration flange, a calibration plate and three calibration balls, which serve to define a coordinate system; FIG. 4 : Construction of the coordinate system on the basis of the three calibration balls; FIG. 5 : CAD model of the calibration adapter and 3D scan of the manufactured calibration adapter and the transformation of the 3D scan data to the calibration adapter; FIG. 6 : Area of a unique feature of the shoe sole, which is defined with respect to the CAD model; FIG. 7 : Subdivision of the CAD model of the shoe sole into 3D box regions; FIG. 8 : The first robot path created with respect to the CAD model and a second robot path defined on the basis of the local offsets; FIG. 9 : Illustration of the processing of a shoe sole by means of a trimming tool, wherein the shoe sole is fastened to a robot arm by means of a gripper; and5. DETAILED DESCRIPTION OF PREFERRED EMBODIMENTSOnly a few possible embodiments of the invention are described in detail below. It should be understood that these example embodiments may be modified and combined in various ways whenever compatible, and that certain features may be omitted as long as omitted.It is to be understood that not all features of the described aspects / embodiments need be present to realize the technical advantages of the present disclosure defined by the subject matter of the claims. The disclosed aspects / embodiments may be modified by combining certain features of one aspect / embodiment with one or more features of another aspect / embodiment. In particular, those skilled in the art will understand that features and / or functional elements of one aspect / embodiment can be combined with technically compatible features and / or functional elements of any other aspect / embodiment of the present disclosure, provided the resulting combination falls within the definition of the present disclosure.In the present figures and the description, the same reference numerals refer to the same elements. For purposes of clarity and brevity, certain aspects of components or steps of certain embodiments will be presented without undue detail if such details are implicit to those skilled in the art in light of the teachings herein and / or if such details would obscure understanding of relevant aspects of the embodiments.In the sense of the person skilled in the art and / or in order to avoid redundancies, reference is also made to the explanations in the preceding sections, which also apply to the following detailed description. Furthermore, for the sake of brevity and clarity, not all features, parts, elements, aspects, components, and / or steps are expressly denoted by reference numerals. This applies in particular when the skilled person recognizes that such features, parts, elements, aspects, components and / or steps are present in a plurality.As already stated, a method according to the invention or a device according to the invention, as explained below with reference to some embodiments, can be used in particular for trimming or trimming shoe soles. However, the invention is not limited to the processing of shoe soles or components thereof.One possible exemplary embodiment of a method 100 for processing a component of a sports item by means of a robot or robot system is the trimming of one or more discharges of a shoe sole by means of a computer-controlled robot arm using an optical 3D scanner. Such discharges of components can be caused by the escape of material through openings or gaps which result between two or more molded bodies. Ports may be provided to vent a mold during molding or injection molding.Shoe soles are mass-produced articles and must therefore be produced to a great extent. This includes in particular the multiple production of a specific sole model in a specific size. In a first method step 110, a CAD model 200 of the shoe sole 210 is created, which serves as a reference model in the subsequent steps. This model represents the shape of an ideally shaped shoe sole. In the exemplary embodiment shown here, the created CAD model 200 furthermore includes a gripper 220, which can be mounted on the robot arm, not depicted, by means of a flange 230. This gripper serves for fastening or receiving the shoe sole and thus forms the connection between the shoe sole and robot. In another embodiment, the created CAD model can also consist only of a CAD model of the shoe sole.With respect to this CAD model of the shoe sole 210, an ideal robot path 240 is now defined, which is either generated by the aid of learning techniques or is directly predefined. The data associated with the ideal robot path 240 is a list of points defined with respect to the robot system that define a trajectory to which the robot is to follow. This predefined trajectory in the CAD model 200 of the shoe sole 210 including the gripper 220 corresponds exactly to the real gripper model. If this were not the case, deviations would necessarily occur during later method steps, inter alia during the calculation of the corrected trajectory. The number of points in this list can be automatically calculated depending on the path curvature. The actual robot path is then the polygon train of the points contained in the list. Alternatively, the robot path can also be derived from the predetermined list of points by means of polynomial interpolation, spline interpolation or another interpolation technique.In a second, optional method step 115, a calibration phase is first run through. This calibration phase serves to align the coordinate system of the 3D scanner with the robot coordinate system. For this purpose, a calibration adapter 300 was designed as a CAD model and manufactured accordingly. This calibration adapter 300 consists of a clamping flange 310, a calibration plate 320 and three optical calibration balls 330 a- 330 c. These three optical calibration balls 330 a- 330 cfixed on the calibration plate 320 define a coordinate system 400 which can be returned to the robot flange, i.e. the connecting element of robot arm and calibration adapter 300 or gripper 220, and thus to the origin of the robot coordinate system. This coordinate system 400 is defined by the two vectors X 410 and Y 420 which are defined by the center points of the balls 330 and 330 and 330 and 330, respectively. These two vectors have the same origin 440, namely the center of the sphere 330a, and thus define a plane in three-dimensional space. The third coordinate axis Z 430 is then a vector perpendicular to this plane, which also has the center of the sphere 330 aas a base point.The step of calibrating 115 is optional and does not need to be performed each time a component is processed. It would be sufficient, for example, to carry out the calibration only once during the setting-up of the system or at specific time intervals. Therefore, the optional calibration step 115 is explained here merely for the sake of completeness.For calibration, the calibration adapter 300 is now optically captured using the 3D scanner. In this case, the calibration adapter 300 is presented to the scanner at the same spatial position and orientation as the sole to be processed, mounted on the gripper. By means of this optical detection of the calibration adapter, the ball centers and the calibration plate can be detected. By means of the CAD model of the calibration adapter 300 and on the basis of the nominal positions of the ball centers relative to the robot flange, a transformation matrix can then be calculated by a computer system. This transformation matrix now allows the position and orientation of the robot flange to be calculated relative to the 3D scanner. The transformation matrix obtained is stored on the computer system for later sole evaluation.FIG. 500 shows the optical 3D scan of the calibration adapter 510 from the perspective of the 3D scanner, and the CAD model of the calibration adapter 300. The transformation matrix can be calculated on the basis of the identification of the sphere centers and the calibration plate 320, so that the optically captured calibration adapter 510 can be returned to the CAD model of the calibration adapter 300. In a further method step, which takes place after the calibration, the generation and storage of the transformation matrix, the calibration adapter is replaced by a gripper, which can be attached to the robot flange. The sole to be machined is now mounted or placed on this gripper. The robot arm or robot flange is already in the initial position, i.e. the position in which the calibration scan has been carried out, or moves to this position after mounting or placing the sole on the gripper. In a next method step, a 3D scan of the real shoe sole 610 is then determined 120 by means of an optical 3D scan.Due to the extending regions 640 which may have been produced during the production of the sole and due to material inconsistencies, the real sole does not exactly correspond to the ideal sole model. In particular, the 3D scan of the real sole 610 may deviate from the sole in the stored CAD model 210.In a next method step 130, a global prealignment of the CAD model of the sole 210 including the gripper 220 and the obtained optical 3D scan 610 of the real sole mounted on the gripper occurs. This global prealignment serves to register the scan data to the CAD model 210. Depending on the shoe sole to be treated, this may be assigned unique features 620 that can be detected by the 3D scanner and that can be associated with an area 630. In the exemplary embodiment shown here, this is a depression 620 in the region 630 around the center of the sole.In a first pre-alignment step 130, a coarse alignment occurs between 3D scan 610 of the real sole and CAD model 210 based on the selected area 630 containing one of the unique features 620. In a particular embodiment, the data of the 3D scan 610 and the CAD model 210 are given as point clouds. A transformation is now calculated which minimizes the distance between the two point clouds in a global sense. This may include minimizing a distance metric between the point clouds with respect to the set of all transformation matrices. The result of this first global pre-alignment step is thus a transformation matrix.In a second prealignment step 130, the so-called global fine alignment or "ICP registration algorithm" (iterative closest point registration), the transformation already determined in the first prealignment step 130 is further optimized. This new alignment or registration once again improves the global alignment of the 3D scan 610 of the real shoe sole to the CAD model 210.After the global alignment of the 3D scan 610 of the real shoe sole and of the CAD model 210, and thus in particular the global alignment of the ideal robot path with respect to the 3D scan 610 of the real shoe sole, a local correction now occurs in a further method step 140. This local correction allows for accurate alignment between 3D scan 610 and CAD model 210 beyond mere translation or rotation of the models as a whole.For the local alignment or correction 140, the sole is divided into spatial sections 710 along the sole on the basis of the CAD model. Furthermore, the sections are divided transversely to the sole. This results in a subdivision of the shoe sole into rectangular rectangular rectangular sections 710, which are referred to below as 3D boxes. The spatial extent of the respective 3D boxes 710 may be individually adjustable or may be the same for all 3D boxes 710. The data of the 3D scan 610 of the real shoe sole are now assigned to these spatial sections and with respect to these sections the scan data are extracted from the point clouds.The scan data defined with respect to the sections are now registered again against the CAD model 210 of the sole, in a further method step 150, taken per se in the regions defined with respect to the sections. For this purpose, the individual regions in the 3D boxes 710 are projected onto the CAD model 210 of the sole by surface mapping. For this purpose, a local compensation plane is determined in each case both in the CAD model 210 and in the 3D scan 610 of the sole within the 3D box 710. These two compensation planes, which are determined separately for each 3D box 710, are then projected onto one another via the center of gravity. This projection results in a local transformation matrix for each 3D box.This local correction of the robot path makes it possible to react locally to section-wise deviations and to locally correct the robot path. This leads to a more accurate adaptation of the 3D scan 610 of the sole and the CAD model 210 and thus to a more accurate adaptation of the ideal robot path 240 defined with respect to the CAD model 210 to the individual properties of the real sole. This in turn leads to the trimming of the drive-out regions 640 being carried out more accurately, as a result of which the quality of the trimmed sole is increased. This allows automation of trimming of output areas 640 in shoe soles and leads to a reduction in labor costs and an improvement in product quality.After the determination of the local transformations, the path points of the ideal robot path 240 of the CAD model 210 are transformed back 160 to the 3D scan 610 of the real sole. For this inverse transformation, the 3D box areas 710 are again used, so that the relevant path points can be determined for each subsection. In each 3D box 710, the path points are then transformed back to the calibrated data of the 3D scanner. This provides a list of corrected path points 810 and thus a corrected robot path.The calculated transformed path points are stored including the new orientation. This data can then be sent 170 to the robot or robot system. Based on the obtained data, the latter can then guide 170 the sole 930 gripped by the gripper around a trimming tool 900 that is immovable with respect to the robot. In this case, the sole is guided along a stop 230. This stop 230 forms the counterpart, against which the oscillating knife 920 runs, which severs the drive. In this case, the hold-down device 910 brings the drive out into the correct position in the event that it projects upwards.In another embodiment, the sole 930 may have been attached at a fixed position relative to the robot arm and the robot arm carries a trimming tool 900 around it for machining the sole 930.

Claims

Method (100) for processing a component for a sports article, in particular a shoe sole, by means of a robot, wherein the method comprises: (a) creating (110) a first path (240) with respect to the component to be processed, comprising a list of points or a predefined trajectory; (b) determining (120) a 3D scan (610) of the component to be processed by means of a 3D Sanner; (c) calculating (130) a global offset between the first path (240) and the 3D scan (610) of the component to be processed; (d) calculating (150) a plurality of local offsets between the first path (240) and the 3D scan (610) of the component to be processed; (e) creating (160) a second path (810) based on the first path (240), the calculated global offset and the calculated local offsets; and (f) transmitting (170) the second path (810) to the robot performing the processing of the component based on the second path (810).The method of claim 1, wherein the first path (240) is determined based on a CAD model (210) of the component to be machined.Method according to one of claims 1 to 2, wherein the determination (120) of the 3D scan is carried out by means of an optical 3D scanner.Method according to one of Claims 1 to 3, wherein the calculation (130) of the global offset is carried out on the basis of a feature (620) of the component to be processed that can be detected by the 3D scanner.Method according to one of Claims 2 to 4, wherein the component to be processed is divided into a plurality of spatial sections (710) on the basis of the CAD model (210) on which the first path (240) is based, and the calculation (150) of the local offsets with respect to the plurality of spatial sections of the components to be processed is carried out.The method of claim 5, wherein the spatial portions (710) are defined by cuboids.The method of any one of claims 1 to 6, wherein the first path (240) and the second path (810) comprise a plurality of spatial points.The method of claim 7, wherein there is a bijective correspondence between the points of the first path and the points of the second path.Device which is designed to carry out a method according to one of Claims 1-8.A computer program comprising instructions that cause a computer to perform a method according to any of claims 1-8 when said computer program is executed on said computer.

Images