This paper proposes a method for modeling the dynamic motion of the fabric using the oriented bounding box (OBB) and applies it to the collision avoidance between the fabric and the obstacle. The dynamic motion of the fabric cannot be modeled accurately because the fabric motion and deformation are affected by many hard-to-estimate factors. In the proposed method, the fabric state is represented by the OBB instead of a detailed fabric model. The fabric motion is represented by a time series of OBBs and modeled by the proposed OBB-LSTM. Using the OBB-LSTM, a simple dynamic collision avoidance method is designed to plan a robot endpoint trajectory that connects the start point and the goal point without collision between the fabric attached to the robot end-effector and the obstacle. The effectiveness of the proposed method is demonstrated in collision avoidance experiments under different obstacle settings using a real robot system.

In this paper, we propose a Passive Actuator-Less Gripper (PALGRIP) for picking a piece of fabric from a stack of fabric parts and placing the picked fabric part. The picking of a piece of fabric from a stack is a simple but difficult process to automate. The proposed gripper can pick a piece of fabric from the stack by simply pressing the fingertips of the gripper against the stack. The fingers are closed and opened by the relative motion between the fingers and the housing of the gripper. The grasping motion of the gripper is generated by two mechanisms: a passive pinching mechanism and a selflocking mechanism. These mechanisms allow the fingers to perform open and close movements and to maintain the fingers in either open or closed state. The kinematics of the mechanisms are analyzed to design the gripper. The relation between the movement of the fingers and the force required to operate the gripper is also investigated through static force analysis and the experiment. Finally, experiments using PALGRIP are conducted, and the experimental results illustrate how the pick-and-place operations are carried out using the prototype of PALGRIP. The proposed gripper allows the robot to automate fabric pick-andplace operations easily by attaching it to the robot's endpoint.

In this paper, we propose a robot end-effector for fabric folding of a fabric part of a garment along a straight line. In the garment production process, some of the edges of fabric parts of a garment need to be folded before sewing. Conventional automated folding system has a fixture designed for each folding fabric part and operation. The fixture is not universal and needs to be redesigned when the shape of the folded fabric part changes. In this paper, we consider performing fabric folding without using a fixture. We propose a concept of a robot end-effector for fabric folding of a fabric part along a straight fold line and develop a prototype of an end-effector referred to as“ F-FOLD ”(Free-form FOLDing). Folding of the edge of a fabric part is achieved by moving FFOLD along the desired straight fold line. Experimental results illustrate how F-FOLD works to fold a fabric part along a straight line. *The complete version of this preprint paper is published in  IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics . Please refer to “https://ieeexplore.ieee.org/document/10196184”.

This paper proposes CNN-based visual servoing for simultaneous positioning and flattening of a soft fabric part placed on a table by a dual manipulator system. We propose a network for multimodal data processing of grayscale images captured by a camera and force/torque applied to force sensors. The training dataset is collected by moving the real manipulators, which enables the network to map the captured images and force/torque to the manipulatorâ\euro™s motion in Cartesian space. We apply structured lighting to emphasize the features of the surface of the fabric part since the surface shape of the non-textured fabric part is difficult to recognize by a single grayscale image. Through experiments, we show that the fabric part with unseen wrinkles can be positioned and flattened by the proposed visual servoing scheme.  *The complete version of this preprint paper is in proceedings of ICRA 2023. Please refer to “https://ieeexplore.ieee.org/document/10160635”.Â

This paper proposes a deep learning-based fast grasp detection method with a small dataset for robotic bin-picking. We consider the problem of grasping stacked up mechanical parts on a planar workspace using a parallel gripper. In this paper, we use a deep neural network to solve the problem with a single depth image. To reduce the computation time, we propose an edge-based algorithm to generate potential grasps. Then, a convolutional neural network (CNN) is applied to evaluate the robustness of all potential grasps for bin-picking. Finally, the proposed method ranks them and the object is grasped by using the grasp with the highest score. In bin-picking experiments, we evaluate the proposed method with a 7-DOF manipulator using textureless mechanical parts with complex shapes. The success ratio of grasping is 97%, and the average computation time of CNN inference is less than 0.23[s] on a laptop PC without a GPU array. In addition, we also confirm that the proposed method can be applied to unseen objects which are not included in the training dataset.

We propose a CNN based visual servoing scheme for precise positioning of an eye-to-hand manipulator in which the control input of a robot is calculated directly from images by a neural network. In this paper, we propose Difference of Encoded Features driven Interaction matrix Network (DEFINet), a new convolutional neural network (CNN), for eye-to-hand visual servoing. DEFINet estimates a relative pose between desired and current end-effector from desired and current images captured by an eye-to-hand camera. DEFINet includes two branches of the same CNN that share weights and encode target and current images, which is inspired by the architecture of Siamese network. Regression of the relative pose from the difference of the encoded target and current image features leads to a high positioning accuracy of visual servoing using DEFINet. The training dataset is generated from sample data collected by operating a manipulator randomly in task space. The performance of the proposed visual servoing is evaluated through numerical simulation and experiments using a six-DOF industrial manipulator in a real environment. Both simulation and experimental results show the effectiveness of the proposed method. *The complete version of this preprint paper is published in IEEE Access. Please refer to “https://ieeexplore.ieee.org/abstract/document/9464907”.