• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.517-522
• /
• 1991

In this paper, robot's grasping poses are classified into three cases, and force/torque information in each grasping pose is analyzed. In the grasping process, error between the desired and the actual grasping poses can be generated because of uncertainty in the environment. A systematic algorithm is presented, that uses the force/torque information generated by grasping pose error to estimate robot's actual grasping pose.

• Journal of the Ergonomics Society of Korea
• /
• v.20 no.3
• /
• pp.11-25
• /
• 2001

AS human movements have the inherent property of anticipating target and can be coordinated to realize a given schedule, finger movements have stereotyped patterns during hand grasping. Finger movements have been studied in the past to find out the coordination pattern of hand joint angular movement. These studies analyzed only a few finger joints for a limited number of hand postures. This study investigated fourteen joint angles during eight hand-grasping motions to analyze the angular correlations between finger joints and to suggest motion factors which represent hand grasping. Hand grasping motions including forward arm motion were examined in ten healthy volunteers. Eight objects were used to represent real hand grasping tasks. $CyberGlove^{TM}$ and $Fasreack^{TM}$ measured hand joint angles and wrist origin. Joint angle correlations between PIJ(proximal interphalangeal joint) and MPJ(metacarpophalangeal joint) at one finger, between neighboring PIJs and MPJs were four factors related to the fast phase of hand grasping motions and eight factors related to the slow phase of hand grasping motions.

• The Journal of Korea Robotics Society
• /
• v.16 no.2
• /
• pp.130-136
• /
• 2021

In recent years, much study has been conducted in robotic grasping. The grasping algorithms based on deep learning have shown better grasping performance than the traditional ones. However, deep learning-based algorithms require a lot of data and time for training. In this study, a grasping algorithm using an artificial neural network-based graspability estimator is proposed. This graspability estimator can be trained with a small number of data by using a neural network based on the residual blocks and point clouds containing the shapes of objects, not RGB images containing various features. The trained graspability estimator can measures graspability of objects and choose the best one to grasp. It was experimentally shown that the proposed algorithm has a success rate of 90% and a cycle time of 12 sec for one grasp, which indicates that it is an efficient grasping algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.3
• /
• pp.300-307
• /
• 2013

This paper describes the development of a cylindrical-object grasping force measuring system applied haptic technology to measure the grasping force of strokes patients' fingers and other patients' paralyzed fingers. Because the cylindrical-object and the force measuring device of the developed cylindrical-object grasping force measuring system are connected with the electrical wires, patients and their families have difficulty not only measuring the patients' grasping force using the system but also knowing their rehabilitation extent when using it. In this paper, the cylindrical-object grasping force measuring system applied haptic technology was developed, and the cylindrical-object grasping force measuring device sends data to the rehabilitation evaluating system applied haptic technology by wireless communication. The grasping force measurement characteristic test using the system was carried out, and it was confirmed that the rehabilitation extent of the patients' paralyzed fingers and normal people fingers can be evaluated.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.2
• /
• pp.187-193
• /
• 1998

This paper proposes an advanced visual tracking algorithm for the stable grasping of a moving target(2D). This algorithm is programmed to find grasping points of an unknown polygonal object and execute visual tracking. The Kalman Filter(KF) algorithm based on the SVD(Singular Value Decomposition) is applied to the visual tracking system for the tracking of a moving object. The KF based on the SVD improves the accuracy of the tracking and the robustness in the estimation of state variables and noise statistics. In addition, it does not have the numerical unstability problem that can occur in the visual tracking system based on Kalman filter. In the grasping system, a parameterized family is constructcd, and through the family, the grasping system finds the stable grasping points of an unknown object through the geometric properties of the parameterized family. In the previous studies, many researchers have been studied on only 'How to track a moving target'. This paper concern not only on 'how to track' but also 'how to grasp' and apply the grasping theory to a visual tracking system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.24-27
• /
• 2003

This paper discusses practical strategies for transition from a pinching to a power grasping, where a multi-fingered hand mounted on a robotic arm envelops a cylindrical object on a table. When the manipulation system grasps a cylindrical object like a pen on a desk, a complete enveloping is not impossible in the initial configuration. The system firstly pinches the object only with two or three fingers and then grasp it with fingers and a palm after regrasping. In this pinching-grasping transition maneuver, human unconsciously selects proper strategy according to some conditions including object dimensions and initial pinching positions. In this paper we therefore develop six possible strategies for this pinching-grasping transition and then investigate their performances for some objects with various dimensions and various grasping positions, using numerical simulations. Based on their results, effective strategies are implemented by using a hand-arm system.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1993.10a
• /
• pp.601-610
• /
• 1993

With the purpose of labour reduction in tea plucking operation with portable type machine, the influence of frame angles and tea leaves weight on the grasping forces of each finger were investigated. At the measurement of the grasping force of each finger except for thumb, grip strength dynamometers were attached at the grasping position of the frame instead of handle grips. A series of measurement was carried out changing frame angles of the tea plucking machine and the weight of tea leaves. With the obtained results of the experiments , the influences of the frame angles and the weight of the tea leaves on the grasping forces of each finger were analyzed. Some reasonable suggestions for the labour reduction in the tea plucking operation with portable type machine were obtained in the aspect of normalizing the balance of the grasping force on each finger and these suggestions are expected to contribute the labour reduction of the tea plucking operation.

• Proceedings of the ESK Conference
• /
• 1997.04a
• /
• pp.85-89
• /
• 1997

We used a three-dimensional motion capture method to measure the grasping reach of Korean. This method was applied well to the grasping reach measurement with low measurement error and high efficiency. We measured the grasping reach of 29 males and 21 females at the different height from seat reference level; -10, 0, 30, 60, and 90cm. The grasping reach data were summarized at each 15 .deg. in polar corrdinates to compare with the former researches. If the number of subjects increases in the supplement research, the grasping reach data will be used in the ergonomic design of the driver's cabin or workstations in industry.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.543-546
• /
• 1996

We propose a new visual tracking system for grasping which can find grasping points of an unknown polygonal object. We construct the system with the image prediction technique and Extended Kalman Filter algorithm. The Extended Kalman Filter(EKF) based on the SVD can improve the accuracy and processing time for the estimation of the nonlinear state variables. By using it, we can solve the numerical unstability problem that can occur in the visual tracking system based on Kalman filter. The image prediction algorithm can reduce the effect of noise and the image processing time. In the processing of a visual tracking, we can construct the parameterized family and can found the grasping points of unknown object through the geometric properties of the parameterized family.