• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.94-103
• /
• 2019

The optimal grasping point of the object varies depending on the shape of the object, such as the weight, the material, the grasping contact with the robot hand, and the grasping force. In order to derive the optimal grasping points for each object by a three fingered robot hand, optimal point and posture have been derived based on the geometry of the object and the hand using the artificial neural network. The optimal grasping cost function has been derived by constructing the cost function based on the probability density function of the normal distribution. Considering the characteristics of the object and the robot hand, the optimum height and width have been set to grasp the object by the robot hand. The resultant force between the contact area of the robot finger and the object has been estimated from the grasping force of the robot finger and the gravitational force of the object. In addition to these, the geometrical and gravitational center points of the object have been considered in obtaining the optimum grasping position of the robot finger and the object using the artificial neural network. To show the effectiveness of the proposed algorithm, the friction cone for the stable grasping operation has been modeled through the grasping experiments.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.1 s.232
• /
• pp.1-13
• /
• 2005

Kinematics of grasping and manipulation by a multi-fingered robotic hand where multi-fingertip surfaces are in contact with an object is solved. The surface of the object was represented by B-spline surfaces in order to model the objects of various shapes. The fingers were modeled by cylindrical links and a half ellipsoid fingertip. Geometric equations of contact locations have been solved for all possible contact combinations between the fingertip surface and the object. The simulation system calculated joint displacements and contact locations for a given trajectory of the object. Since there are no closed form solutions for contact or intersection between these surfaces, kinematics of grasping was solved by recursive numerical calculation. The initial estimate of the contact point was obtained by approximating the B-spline surface to a polyhedron. As for the simulation of manipulation, exact contact locations were updated by solving the contact equations according to the given contact states such as pure rolling, twist-rolling or slide-twist-rolling. Several simulation examples of grasping and manipulation are presented.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.2
• /
• pp.127-134
• /
• 2004

In this paper, human motor behaving model based sensory motor coordination(SMC) algorithm is implemented on robotic grasping task. Compare to conventional SMC models which connect sensor to motor directly, the proposed method used biologically inspired human behaving system in conjunction with SMC algorithm for fast grasping force control of robot arm. To characterize various grasping objects, pressure sensors on hand gripper were used. Measured sensory data are simultaneously transferred to perceptual mechanism(PM) and long term memory(LTM), and then the sensory information is forwarded to the fastest channel among several information-processing flows in human motor system. In this model, two motor learning routes are proposed. One of the route uses PM and the other uses short term memory(STM) and LTM structure. Through motor learning procedure, successful information is transferred from STM to LTM. Also, LTM data are used for next moor plan as reference information. STM is designed to single layered perception neural network to generate fast motor plan and receive required data which comes from LTM. Experimental results showed that proposed method can control of the grasping force adaptable to various shapes and types of greasing objects, and also it showed quicker grasping-behavior lumining time compare to simple feedback system.

• The Journal of Korea Robotics Society
• /
• v.15 no.2
• /
• pp.197-204
• /
• 2020

In this paper, we present a learning platform for robotic grasping in real world, in which actor-critic deep reinforcement learning is employed to directly learn the grasping skill from raw image pixels and rarely observed rewards. This is a challenging task because existing algorithms based on deep reinforcement learning require an extensive number of training data or massive computational cost so that they cannot be affordable in real world settings. To address this problems, the proposed learning platform basically consists of two training phases; a learning phase in simulator and subsequent learning in real world. Here, main processing blocks in the platform are extraction of latent vector based on state representation learning and disentanglement of a raw image, generation of adapted synthetic image using generative adversarial networks, and object detection and arm segmentation for the disentanglement. We demonstrate the effectiveness of this approach in a real environment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.22-27
• /
• 2012

This paper presents a ball screw-driven robotic gripper mechanism which is possible to grasp an object and analyzes its kinematic feature for grasping by simulation. For the purpose of identifying the feature of the robot gripper, we try to confirm the kinematics relating the joint space of the driving actuator to the gripper's tip space. To be specific, the proposed robot gripper employs one actuator and a symmetrical closed-chain structure. As a result, the specified robot gripper has an advantage of robustness to external forces structurally, and it is easy to implement simple grasping operations. Also the gripper has a useful squeezing effect for power grasping.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.568-576
• /
• 1998

In this thesis discuss with a flexible robotic finger design and controller which is used for the micro flexible robotic finger. So, miniaturization, precision, controller for the control of grasping force and actuator were needed. And, even if we develop a new actuator and controller, in order to use on real system, we must considerate of a many side problem. In a force control of micro flexible finger for grasping an object, the fingertip's vibration was more important task of accuracy control. And, controller were adopt the PD/PI mixed type fuzzy controller. The controller were consist of two part, one is a PD type fuzzy controller for increase the rising time response, the other is a PI type fuzzy controller for decrease of steady-state error. Especially, in a PD type fuzzy controller, we used only seven rules. And, for a PI controller, we adopt a reset factor for the control of input values. so, we have overcome the exceed of controller's input range. For the estimate of ontroller's utility and usefulness, we have experiment and computer simulation of three cases. First, we consider of unit force grasping control for a task object, which is 0.03N. Second, bounding grasping force control which is add to a sinusoidal force on the unit force. At this cases the task force is (0.03+0.01 sin wt N). And consider of following of rectangular forces.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.16-22
• /
• 2024

Robotic grasping in unstructured environments poses a significant challenge, demanding precise estimation of gripping positions for diverse and unknown objects. Generative Grasping Convolution Neural Network (GG-CNN) can estimate the position and direction that can be gripped by a robot gripper for an unknown object based on a three-dimensional depth map. Since GG-CNN uses only a depth map as an input, the precision of the depth map is the most critical factor affecting the result. To address the challenge of depth map precision, we integrate the Segment Anything Model renowned for its robust zero-shot performance across various segmentation tasks. We adjust the components corresponding to the segmented areas in the depth map aligned through external calibration. The proposed method was validated on the Cornell dataset and SurgicalKit dataset. Quantitative analysis compared to existing methods showed a 49.8% improvement with the dataset including surgical instruments. The results highlight the practical importance of our approach, especially in scenarios involving thin and metallic objects.

• The Journal of Korea Robotics Society
• /
• v.18 no.4
• /
• pp.419-426
• /
• 2023

Assembly tasks are difficult to fully automate due to uncertain errors occurring in unstructured environments. When assembling parts such as electrical connectors, advances in grasping and assembling technology have made it possible for the robot to assemble the connectors without the aid of humans. However, some parts with tight assembly tolerances should be assembled by humans. Therefore, task sharing with human-robot interaction is emerging as an alternative. The goal of this concept is to achieve shared autonomy, which reduces the efforts of humans when carrying out repetitive tasks. In this study, a task-sharing robotic system for assembly process has been proposed to achieve shared autonomy. This system consists of two parts, one for robotic grasping and assembly, and the other for monitoring the process for robot-human task sharing. Experimental results show that robots and humans share tasks efficiently while performing assembly tasks successfully.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.15-24
• /
• 1996

This paper presents a new method for visual servoing to control the pose(position and orientation) of the robotic manipulators for grasping the 3-D moving object whose initial pose and moving informations are unknown by using the stereo camera. The stereo camera is mounted on the end-effector of robotic manipulator. In order to track the current pose of robotic manipulator to the desired pose, we use the image Jacobian, which is described by the differential transform, relating the change in image feature point to the change in the object's pose with respect to the camera. In this paper the simple PD controller is adopted for the robotic manipulator to track the desired pose. Finally, the effectiveness of the proposed method is confirmed by some computer simulations.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.322-333
• /
• 2022

The Avatar robot, which is one of the teleoperation robots, aims to enable users to feel the robot as a part of the body to intuitively and naturally perform various tasks. Considering the purpose of the avatar robot, an end-effector identical to a human hand is advantageous, but a robotic hand with human hand level performance has not yet been developed. In this paper we propose a new 3-finger robotic hand with human-avatar hand posture mapping algorithm which were integrated with TOCABI-AVATAR, one of the teleoperation system. Due to the flexible rolling contact joints and tendon driven mechanism applied to the finger, the finger could implement adaptive grasping and absorb the impact force caused by unexpected contacts. In addition, human-avatar hand mapping algorithm using five calibration hand postures propose to compensate physical differences between operators. Using the TOCABI-AVATAR system with the robotic hands and mapping algorithm, the operator can perform 13 out of 16 hand postures of grasping taxonomy and 4 gestures. In addition, using the system, we participated in the ANA AVATAR XPRIZE Semi-final and successfully performed three scenarios which including various social interactions as well as object manipulation.