Systems and methods for sewing and wrinkle removal of fabrics

The automated robotic sewing system addresses labor-intensive garment production by using a dual-arm manipulator and computer vision to adaptively sew along visible or virtual seam lines and remove wrinkles, enhancing precision and efficiency.

JP7948655B2Active Publication Date: 2026-11-11CENT FOR GARMENT PROD LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2025513230
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-09-14
Publication Date
2026-11-11
Estimated Expiration
2042-09-14

Smart Images

  • Figure 0007948655000001
    Figure 0007948655000001
  • Figure 0007948655000002
    Figure 0007948655000002
  • Figure 0007948655000003
    Figure 0007948655000003
Patent Text Reader

Abstract

The automated robotic sewing system includes a sewing device, a work surface on which fabric is sewn by a sewing machine, and a dual-arm manipulator robot equipped with a force / torque sensor and a fabric handling end effector for moving the fabric across the work surface. A vision module is positioned above the work surface and above the robot manipulator. The vision module provides an image of the fabric within at least the area where the fabric is to be sewn, and a controller sequences the sewing device, robot manipulator, and vision module to enable seam line determination, seam line tracking, and wrinkle removal under visual servo control. As a result, freeform sewing and smoothing of the fabric is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present invention relates to the field of garment production, and in particular to an automated sewing system having a dual-arm manipulator robot equipped with an end effector for manipulating fabric pieces to facilitate the sewing process. BACKGROUND ART

[0002] In the field of garment production, fabric pieces or fabric panels are manually handled and transferred to a sewing workstation to perform the intended seaming, edging, or fell seam process. In the conventional garment production industry, the sewing process is mainly carried out in such a manner that the posture or shape of the fabric pieces is controlled by human hands with the aid of prefabricated fixtures or fasteners, so that the fabric can be sewn along a desired stitch line. Such processes are labor-intensive, and the sewing accuracy, uniformity, sewing speed and the like are highly dependent on the ability of the operator themselves.

[0003] Therefore, in conventional sewing processes, workers use their hands to precisely manipulate pieces of fabric and sew them together or backstitched using sewing machines in typical garment production processes. Precise sewing requires skilled techniques acquired after a considerable period of training and practice, and the hand-sewing process is inherently labor-intensive, i.e., not efficient production, and prone to difficulties brought about by the global labor shortage. Some sewing tasks can be automated by machines, but such automated sewing machines require special fasteners and fasteners that need to be custom-designed and manufactured for each shape, size, and material of the fabric. The main purpose of these fasteners and fasteners is to hold the fabric in place and provide a frame or groove suitable for the sewing work to be guided along. Such methods have the potential to automate certain sewing tasks that require little human intervention, but their adaptability is hindered by the fact that the shapes of the fasteners and fasteners are all fixed, and fasteners cannot be adapted to shapes other than those they correspond to. While this automation method is applicable to the mass production of garments with identical structure and style, changing the style requires replacing all fasteners and reconfiguring the machinery. Such a method is impractical for the production of highly customized garments, a market where online retail, in particular, sees significant potential. Therefore, such equipment is labor-intensive and unsuitable for the production of customized garments, thus necessitating a new type of production methodology that enables "high variety, low-volume" manufacturing at a reasonable cost.

[0004] When considering hand-sewing, the worker must not only manipulate the fabric piece against the sewing machine to ensure it follows the desired seam path or line precisely, but also ensure that the fabric piece is properly stretched and, above all, free from undesirable folds or wrinkles in the area to be sewn. Failure to do so will result in interruptions to the sewing process and / or defective products. Therefore, the ability to detect folds and wrinkles and remove them from the fabric as needed represents a crucial function of automated sewing systems that can perform the sewing process in the same intelligent and flexible way as a human worker.

[0005] While some semi-automated systems are available on the market to automate the sewing of specific classes of fabric elements, these systems still rely on the use of fasteners / fixtures, thereby limiting the adaptability of production to broader customization of garment products. Some of these conventional systems use computer vision and robotic arms to manipulate fabric pieces during the sewing process. See, for example, U.S. Patent No. 10,366,175. However, many require the use of frames or fasteners, which limits the types of garments that can be produced with a single device. They may also require 3D body scanning that utilizes ink-referenced marks on the fabric as part of computer vision. Some conventional systems are also capable of finding and smoothing out wrinkles. See, U.S. Patent No. 11,053,618, which uses a motion device to (i) transport fabric pieces in one direction, (ii) rotate the fabric around an axis, or (iii) twist / stretch / bend the fabric to reduce wrinkles. [Prior art documents] [Patent Documents]

[0006] [Patent Document 1] U.S. Patent No. 10,366,175 [Patent Document 2] U.S. Patent No. 11,053,618 [Overview of the project] [Problems that the invention aims to solve]

[0007] The present invention relates to an automated robotic sewing process that uses an intelligent system capable of precisely manipulating fabric materials in order to solve the problems of the prior art, namely (1) a wide range of sewing tasks need to be performed repeatedly by hand, while factories face a global shortage of garment workers, and (2) mechanical fasteners / fasteners are essential to today's sewing systems and need to be designed and manufactured based on each and every different shape and material of the fabric pieces. [Means for solving the problem]

[0008] The conceptual model of the automated robotic sewing system of the present invention has several main mechanisms, including (i) a sewing device, (ii) a dual-arm manipulator robot equipped with force / torque sensors and fabric handling end effectors, (iii) a vision module, and (iv) a sequence that enables seam line determination, seam line tracking, and wrinkle removal. This sewing robot system is a universal sewing automation system that does not require any auxiliary fasteners and fixtures that are otherwise essential to conventional automated equipment to assist the sewing process. The present invention can be applied to sewing one or more pieces of fabric along pre-set seam lines of various shapes, ranging from substantially straight lines to complex lines with diverse curvatures.

[0009] The seam lines to be sewn may be visible or invisible lines. If they are visible lines, they may be lines marked / printed directly onto the fabric material, or projected as an image onto the fabric material. If they are invisible lines, they may be virtual lines offset by a distance (i.e., margin) from the physical edge or boundary of the fabric material in question, or they may be any other freeform lines as determined by the corresponding computer-aided design (CAD) model.

[0010] In the robotic manipulator-based system of the present invention, once a piece of fabric is brought under the robotic system's field of view, the system can automatically manipulate the fabric and sew along a desired seam using a sewing device. The seam can be either a visible line marked on the surface of the fabric or a virtual line determined by computer-processed data such as a CAD model. By utilizing a dual-arm manipulator configuration, the robot can perform coordinated movements of two robotic arms, functioning similarly to the upper limbs of a human worker during the fabric manipulation process. The system's computer vision can accurately track the seam and analyze images of the fabric in relation to surface irregularities. When wrinkles or folds are detected, the robot takes corrective actions to flatten the fabric. Automated sewing using the present invention can effectively replace manual processes and enable the flexible and customized production of garments without the use of any fasteners or other devices.

[0011] With this invention, computer vision guidance and wrinkle detection can be achieved using only 2D video from a monochrome camera that provides grayscale images.

[0012] This patent and application file includes at least one color drawing. Copies of this patent and patent application publication containing the color drawing are available from the Japan Patent Office upon request and payment of the necessary fees.

[0013] The above-mentioned and other objects and advantages of the present invention will become more apparent when considered in relation to the accompanying drawings in which similar references are shown in the following detailed description and various figures. [Brief explanation of the drawing]

[0014] [Figure 1] This is a diagram illustrating an exemplary mechanism of a robotic sewing and wrinkle-removing system according to the present invention. [Figure 2] This is a structural diagram of the robotic sewing and wrinkle-removing system according to the present invention. [Figure 3] This is a diagram of the base sequence of an example of a robotic sewing and wrinkle-removing system according to the present invention. [Figure 4] This is a diagram illustrating an example of a seam line determination sequence according to the present invention. [Figure 5] This is a diagram illustrating an exemplary mechanism for automated sewing under visual stitch line tracking control according to the present invention. [Figure 6] This figure shows an example of a visual seam line tracking control sequence according to the present invention. [Figure 7] This is an example of a piece of fabric sewn by the system developed in the present invention. Figure 7A is a diagram of straight lines. Figure 7B is a diagram of an arc line. Figure 7C is a diagram of a wavy line. [Figure 8] This is a diagram illustrating an exemplary mechanism for automated wrinkle smoothing under visual wrinkle prevention control according to the present invention. [Figure 9] This is a diagram illustrating an example of a visual wrinkle prevention control sequence according to the present invention. [Figure 10] This shows the removal of wrinkles on fabric by a robotic system using the visual wrinkle prevention control according to the present invention. Figure 10A shows the initial state of the wrinkled fabric. Figure 10B shows the final state after the wrinkles have been removed. [Modes for carrying out the invention]

[0015] Figure 1 illustrates one embodiment of the present invention for automated free-form sewing and wrinkle smoothing under visual servo control. The system consists of two robot manipulators 11 (i.e., a dual-arm manipulator), each equipped with a force / torque sensor 13 and an end effector 15 for moving the fabric material 10 over the work surface 12. The system further comprises a camera (vision sensor) 14, a projector (pattern generator) 16, and a sewing machine 18. The operation of the system is controlled by a controller 17, for example a computer as further described below.

[0016] The end effectors 15 are used to move the fabric material 10, and may have different designs and mechanisms depending on the complexity of the task. For example, they may be grippers with multiple fingers, special end effectors for free-form folding and / or pick-and-place processes (such as the F-FOLD end effector disclosed in PCT / CN2022 / 090459), vacuum heads, or pads made of soft / elastic materials. In this embodiment, a simple flexible foam pad or sponge that does not include an internal actuator is used as the end effector for manipulating the fabric.

[0017] When the process starts, the fabric is pressed down by two end effectors whose movement is controlled by the robot manipulators. The force / torque sensor between the robot manipulator and the end effector senses the pressing force, and assists in adjusting the force, position and posture of the end effector relative to the work surface. As a result, the end effector is prevented from slipping while the fabric is held down and translated on the surface. It should be noted that the present system can operate with a single robot manipulator, but a dual-arm manipulator robot as depicted in Figure 1 is a preferred configuration that brings improved efficiency in performing the same task, such as smoothing or stretching the fabric, through the coordinated movement of the robot arms.

[0018] A sewing device or sewing machine 18 is an integral part of the present system. The sewing machine utilized in the present embodiment is a programmable sewing machine whose operation can be synchronized with a robot and which can be comprehensively controlled by the central controller of the system. Nevertheless, the use of a programmable sewing machine is not essential, and most existing sewing machines can be configured with the present robot system. Modern sewing machines generally feature a sewing needle, a presser foot, and a feed dog. The function of the presser foot is to apply pressure to the top of the fabric to press the fabric against the feed dog, while the purpose of the feed dog is to grip the bottom portion of the fabric and help advance the fabric through the sewing machine.

[0019] Since the movement of the fabric is sufficiently controlled by the robot in the present system, the presser foot and the feed dog of the sewing machine are not necessary and may simply be detached or removed. For example, most modern sewing machines allow the feed function to be stopped by lifting the presser foot and lowering the feed dog. In doing so, these sewing machines can be integrated with the present robot system to perform automated sewing on a work surface at approximately the same height as the needle plate of the sewing machine. As a more preferable configuration, the sewing device in the present invention is a programmable sewing machine in which the central controller 17 of the system (for example, a computer equipped with an x86-based multi-core processor, memory, an image processing device, I / O ports, and a network interface) can independently control the speed of the sewing needle. In a programmable sewing machine, the main advantage is that the needle speed can be changed in response to any change in the translational speed of the end effector that feeds the fabric, thereby ensuring a uniform stitching pitch along the stitch line. In the absence of real-time control of the needle speed, as in the case of non-programmable sewing machines, the fabric feed speed must be kept constant by the robot.

[0020] Above the end effector 15 is a vision module comprising a camera unit 14 and a projector unit 16 having an illumination source. The camera is responsible for image acquisition, while the projector brings an illumination pattern onto a surface area that covers all or part of the fabric in question. An illustrative mechanism of the robotic system is provided in Figure 2. The system may include one or more of each type of system components as shown, including a robotic manipulator 11, a force / torque sensor 13, an end effector 15, a sewing device (e.g., a sewing machine) 18, a camera 14, a projector 16, and an auxiliary actuator 20. The auxiliary actuator 20 can be used to assist in handling fabric pieces or to switch / buttons to operate additional machinery. A central controller 17 connects the system components and performs several algorithms 22, including “seam line determination,” “visual seam line tracking control,” and “visual wrinkle prevention control.” In this context, the term "seam line" is equivalent to "sewing path" or "sewing route," and it should be noted that it is not limited to the process of sewing together multiple pieces of fabric. It can also be applied to embroidery processes in which only a single piece of fabric is being worked on.

[0021] The basic sequence of the robotic sewing and wrinkle-removing workflow is illustrated in Figure 3. After initializing the system components (step 301), the central controller 17 analyzes images of the target fabric 10 captured or acquired by the camera 14 (step 302) to verify whether a visible seam exists on the fabric (step 303). If no seam is found, the system performs a seam determination sequence (step 304) to derive the seam path by referring to a corresponding CAD model (or numerical data) for the current orientation and position of the fabric. Once a seam is identified, the system performs automated sewing along that seam under visual seam tracking control (step 306) and visual wrinkle prevention control (step 305) until the work is completed (end). The key features of the present invention are: (1) independent control of internal and external forces acting on the fabric using force sensors; (2) no depth images (3D) are required; (3) only grayscale images are needed; and (4) a feedback control scheme is used for both wrinkle removal and seam line tracking.

[0022] If there are no visible seam lines, for example, no manually marked, printed, or projected lines, the seam line determination sequence enables the calculation of the desired seam lines on the fabric material in question. Figure 4 illustrates an example of such a sequence, which begins with initialization (step 401) and acquisition of a fabric image (step 402). A set of data points, such as a point cloud, is formed from the image in space (step 403) and compared to those of the corresponding CAD model of the fabric piece in question (step 404). In doing so, the actual position and orientation of the fabric piece (fabric orientation) is determined (step 405), and a virtual seam line, i.e., sewing path, can be calculated for the fabric piece (step 406). A coordinate transformation is performed when a change in the fabric orientation is detected and the seam line remains in the same location relative to the fabric piece. Once the seam is sewn, the program or algorithm returns to the base sequence (step 407). In contrast to the prior art U.S. Patent No. 11,053,618, this sequence does not require the acquisition of depth information or color (RGB) images, resulting in more relaxed requirements for the camera used with the present invention.

[0023] Figure 5 illustrates the mechanism for an automated sewing process under visual seam line tracking control. Visual seam line tracking control visualizes the fabric piece and controls the operation of actuators in the robot system and sewing device to ensure that the fabric is sewn steadily along a preset seam line. Sensing devices included in this control method include a camera 14 and force / torque sensors connected to each end effector 15. The function of the force / torque sensor 13 is to monitor, by the end effector, the forces exerted (i) vertically on the work surface and (ii) along a plane parallel to the work surface, i.e., laterally, on the fabric material. These forces are controlled by closed-loop servo control, which adjusts the torque of each joint of the robot manipulator 11 to achieve the desired force output.

[0024] During operation, images captured by camera 14 are analyzed in real time to calculate the trajectory of the needle for each end effector and sewing device. The zone imaged by camera 24 should cover the needle drop point 25 and at least a portion of the fabric material. Here, camera 14 may be a digital camera having a monochrome (e.g., grayscale) or color image sensor, regardless of its depth sensing capability. The preset seam line may be a visible line on the fabric, or it may be an invisible line as determined by the seam line determination sequence. Referring to position data corresponding to the preset seam line, the system calculates the passing points where the needle drop point 25 coincides with the seam line. In doing so, the angular velocity of the manipulator joints is determined, and the movement of the robot manipulator and the movement of the sewing needle are simultaneously controlled until the sewing operation along the sewing line 26 is completed.

[0025] In another embodiment, the system can operate with a conventional sewing machine in which the system's controller cannot program its needle speed. In this case, motion control is applied only to the joints of the robot manipulator arm. The feedback control scheme can adapt to physical disturbances and errors related to calculated joint velocities, and can continuously track the stitch line relative to the needle drop point. An example sequence of visual stitch line tracking control is illustrated in Figure 6.

[0026] In Figure 6, the sequence begins with initialization (step 601) and acquisition (capture) of a fabric image (step 602). Step 603 calculates the passing point where the needle drop point 25 coincides with the stitch line. Next, the angular velocity of the manipulator joints is calculated in step 604. Based on the calculation of the passing point and joint angular velocity, motion control is determined in step 605. Step 606 determines whether the sewing operation is complete. If not, the sequence returns to the beginning of step 603. If the operation is complete, the program or algorithm returns to the base sequence (step 607).

[0027] Figure 7 shows a series of sample fabric pieces (approximately 20cm x 30cm in size) sewn along pre-defined seam lines under visual seam line tracking control. In this example, the predetermined seam lines are printed on the fabric pieces for illustrative purposes. The results demonstrate that the sewing system is capable of automatically sewing fabric pieces along different pre-defined shapes, including straight lines (left) (Figure 7A), curved lines (center) (Figure 7B), and wavy lines (right) (Figure 7C), with high positional accuracy.

[0028] Figure 8 illustrates an exemplary mechanism for visual wrinkle prevention control that enables automatic removal of wrinkles on fabric. For a smooth sewing process, appropriate measures should be taken to ensure that the fabric is free of creases and wrinkles before it is sewn. Therefore, in conventional manual sewing processes, the fabric is frequently stretched or pulled by a human operator to flatten it before it is fed through the sewing machine. The visual wrinkle prevention control of the present invention is an algorithm that allows the end effector 15 to apply tension to the fabric in the appropriate direction to remove creases and wrinkles. The sensing devices included in this control module include a camera 14 and a force / torque sensor 13 connected to each end effector 15. Here, the camera may be a digital camera having an RGB (color) image sensor or a monochrome (e.g., grayscale) image sensor, regardless of its depth sensing capability. The zone imaged by the camera (image zone 24) should cover at least a portion of the fabric 10 in question where wrinkles have been detected. The projector 16 may be any device capable of projecting a lighting pattern onto the surface. The force / torque sensor 13 monitors the force exerted on the work surface vertically by the end effector, and the force exerted on the fabric material along a plane parallel to the work surface. In particular, the force data is used as input to a visual servo control algorithm, which plays a crucial role in improving the stability, positional accuracy, and convergence range of the control system.

[0029] Figure 9 shows a sequence illustrating a visual wrinkle prevention control method. It begins with the initialization of the module execution in step 901. Since fabric ridges and depressions are difficult to recognize in a single image without triangulation, a pattern, preferably a structured pattern, is further projected onto the surface of the fabric in question in step 902, creating additional contrast, and is captured by a camera (step 903). The image data captured by camera 14 is processed in real time and analyzed for any deviation from a flat surface. To improve the field of view, the camera is preferably positioned such that its optical axis is tilted at a certain angle (preferably 45 ± 20 degrees) from the perpendicular to the surface of the fabric in question. Wrinkles are identified by analyzing visual features from the image without using three-dimensional topology data of the fabric that would require distance or depth measurements (as in the prior art U.S. Patent No. 11,053,618). Data from force / torque sensors are also captured in step 903, which measure various forces acting on the end effector.

[0030] When the sequence determines that one or more wrinkles are present on the fabric, the angular velocity of each robot manipulator joint is calculated (step 904), and the robot is operated to manipulate the fabric according to a visual servo method to flatten the wrinkles in step 905. The stretching process includes pulling or stretching actions. When performing these actions, forces are measured to avoid excessive tension on the fabric, which could cause unintended damage. In addition, data collected from force / torque sensors is associated with the tension generated within the fabric structure and used as a feedback signal. If the force measured along the stretching direction changes rapidly, for example, when the fabric is sufficiently stretched, the stretching operation is stopped. The above process is repeated until the system no longer detects any wrinkles on the fabric in step 906. The sequence then checks in step 907 whether the sewing is complete, and if so, returns to the base sequence (step 908). If not, the sequence returns to the beginning of step 906.

[0031] Figure 10 shows the process by which a piece of cloth (approximately 25cm x 25cm) is flattened by a robot under visual wrinkle prevention control. In this example, a camera captured images of the cloth illuminated with a checkerboard pattern by a projector. The checkerboard pattern serves as an example of a structured pattern. Other patterns are also possible, provided that the computer vision module is trained on these patterns. Force sensors attached to the end effector provide information on whether the fabric has been sufficiently stretched. The results demonstrate that wrinkles present on the cloth (left) were stretched out by the coordinated movement of the end effector (right).

[0032] While the invention is described in relation to a specific embodiment, it should be understood that various modifications thereof will become apparent to those skilled in the art when reading the specification. Therefore, it should be understood that the invention disclosed herein is intended to cover such modifications as well, those falling within the scope of the appended claims.

Claims

1. An automated robotic sewing system, Sewing machines and, The work surface on which the fabric is sewn by the aforementioned sewing machine, At least one robotic manipulator, each comprising at least one force / torque sensor and at least one end effector for moving the fabric on the work surface, A vision module positioned above the robot manipulator on the work surface, the vision module providing images of the fabric in at least the area where the fabric is to be sewn, An automated robotic sewing system comprising a controller that sequences the sewing machine, the robotic manipulator, and the vision module to enable seam line determination, seam line tracking, and wrinkle removal under visual servo control, thereby achieving freeform sewing and wrinkle removal of the fabric.

2. The automated robotic sewing system according to claim 1, wherein the end effector is at least one of a gripping device having multiple fingers, a special end effector for freeform folding or pick-and-place, a vacuum head, or a pad made of a soft / elastic material.

3. The automated robotic sewing system according to claim 1, wherein the end effector is a simple flexible foam pad or sponge and does not include an internal actuator.

4. The automatic robotic sewing system according to claim 1, wherein the vision module includes a camera that performs the function of acquiring images and a projector having a lighting source that provides a lighting pattern on a surface area covering the fabric, both of which are part of the visual servo control.

5. The automatic robot sewing system according to claim 4, wherein the camera is a monochrome camera that generates a grayscale image.

6. The automated robotic sewing system according to claim 1, further comprising an auxiliary actuator which may be positioned to assist in handling the fabric or to switch / button when additional machine operation is required.

7. The automated robot sewing system according to claim 1, wherein the controller connects system components and performs a plurality of control algorithms.

8. The control algorithm, including the base algorithm, The steps include analyzing an image of the fabric captured by a camera, The steps include verifying whether a visible seam exists on the fabric, and if not, executing a seam determination sequence to determine the path of the seam by referring to a model corresponding to the current orientation and position of the fabric, The automated robotic sewing system according to claim 7, further comprising the step of, once the seam line is identified, performing automated sewing along that seam line under a visual seam line tracking control sequence and a visual wrinkle prevention control sequence until the work is completed.

9. The seam lines are manually marked, printed, or projected from the projector of the vision module, and the seam line determination sequence is The steps include obtaining an image of the aforementioned fabric, The steps include forming a set of data points in space from the aforementioned image, The steps include determining the actual position and orientation of the fabric by comparing the data points with those of the corresponding model of the fabric, A step of calculating a virtual seam line or virtual sewing path for the aforementioned fabric, A step of performing a coordinate transformation when a change in the position and orientation of the fabric is detected and the seam line remains in the same location relative to the fabric, The automated robotic sewing system according to claim 8, further comprising the step of sewing the aforementioned fabric.

10. The aforementioned visual seam line tracking control sequence is: The steps include obtaining an image of the aforementioned fabric, A step of calculating the point through which the needle drop point of the sewing machine coincides with the stitch line, The steps include: calculating the angular velocity of the joints of the robot manipulator; The steps include determining motion control based on the calculation of the angular velocity of the passing point and the joint, The automated robotic sewing system according to claim 8, further comprising the step of determining whether the sewing operation is complete.

11. The aforementioned visual wrinkle prevention control sequence is: When it is determined that wrinkles exist on the fabric, the steps include calculating the angular velocity of the joints of the robot manipulator, The steps of controlling the robotic manipulator to manipulate the fabric according to a visual servo technique to flatten the wrinkles by pulling or stretching actions, A step of measuring the force of the pulling action or stretching action in order to avoid excessive stress on the fabric which could cause damage, An automated robotic sewing system according to claim 8, comprising the step of checking to determine whether the wrinkles still exist and repeating the step until the wrinkles are no longer present.

12. The automated robotic sewing system according to claim 11, wherein during the measurement step, data collected from the force / torque sensor is associated with the tension generated within the fabric structure and used as a feedback signal, thereby causing the force measured along the stretching direction to change rapidly.

13. The automatic robotic sewing system according to claim 12, wherein the stretching operation is stopped when the fabric has been sufficiently stretched.

14. The automated robotic sewing system according to claim 1, further comprising a second robotic manipulator having a force / torque sensor and a fabric handling end effector for moving the fabric on the work surface.

15. The automatic robotic sewing system according to claim 1, wherein the sewing machine has at least one motor.

16. The automatic robotic sewing system according to claim 15, wherein the motor can be controlled by a controller to actuate a sewing needle and adjust the stitch pitch.

17. A method for automatically sewing fabric, The steps include analyzing an image of the fabric taken by a camera placed on a work surface on which at least one piece of the fabric is located, The steps include verifying whether a visible seam exists on the fabric, executing a seam determination sequence if one exists, and if one does not exist, deriving the path of the seam by referring to a model corresponding to the current orientation and position of the fabric, A method for automatically sewing fabric, comprising the steps of: once the seam line is identified, performing automated sewing along that seam line under a visual seam line tracking control sequence and a visual wrinkle prevention control sequence until the work is completed.

18. The aforementioned seam line determination sequence is: The steps include forming a set of data points in space from the aforementioned image, The steps include determining the actual position and orientation of the fabric by comparing the data points with those of the corresponding model of the fabric, A step of calculating a virtual seam line or virtual sewing path for the aforementioned fabric, A method for automatically sewing fabric according to claim 17, comprising the step of detecting a change in the position and orientation of the fabric and performing a coordinate transformation when the seam line remains in the same location relative to the fabric.

19. The aforementioned visual seam line tracking control sequence is: A step of calculating the point through which the needle drop point of the sewing machine coincides with the stitch line, The steps include calculating the angular velocity of the joints of the robot manipulator, The steps include determining motion control based on the calculation of the angular velocity of the passing point and the joint, A method for automatically sewing fabric according to claim 17, comprising the step of determining whether the sewing work is completed.

20. The aforementioned visual wrinkle prevention control sequence is: When it is determined that wrinkles exist on the fabric, the steps include calculating the angular velocity of the joints of the robot manipulator, The steps of controlling the robotic manipulator to manipulate the fabric according to a visual servo technique to flatten the wrinkles by pulling or stretching actions, A step of measuring the force of the pulling action or stretching action in order to avoid excessive stress on the fabric which could cause damage, A method for automatically sewing fabric according to claim 17, comprising the step of checking to determine whether the wrinkles still exist and repeating the step until the wrinkles no longer exist.

Citation Information

Patent Citations

  • Robot sewing method based on machine vision

    CN109629122A

  • Robot flexible fabric flattening method and system based on heuristic mode

    CN114723831A

  • Sewing machine for home use

    DE202018103728U1

  • Sewing device and sewing method

    JP2017200575A

  • US10,366,175