Development of 5 D.O.F Robot Hand for an Android robot

Dongwoon Che,HyunSub Park,Dong-Wook Lee,Jun-Young Jung,Ho-Gil Lee 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8

In this paper, we propose 5 D.O.F robot hand for an android robot. A robot hand is the most complicated part in robot and it required many functions like grasping, detailed motion and so on. An android robot is one of humanoid robot but it required more similar appearance than one of humanoid robot thus, a hand of an android robot is required human like shape more than a hand of humanoid robot. The hand of android needs human like shape and complication, therefore it is difficult to develop a hand of an android robot. In this research, we develop a hand of an android robot which has 5 D.O.F fingers, human like shape and skin. Each finger has link structure driven by DC motor and worm gear. The finger is designed independent module structure so, hand is only combination of finger modules. This module structure gives small size, easy modification and convenience of maintenance. The skin is made of silicon complex material and it designed based on real human hand. The size of this hand based on standard size of Korean woman.

안정 파지를 위한 16자유도 역구동 관절을 가지는 인간형 로봇 손 개발

양현대,박성우,박재한,배지훈,백문홍 한국로봇학회 2011 로봇학회 논문지 Vol.6 No.3

This paper focuses on a development of an anthropomorphic robot hand. Human hand is able to dexterously grasp and manipulate various objects with not accurate and sufficient, but inaccurate and scarce information of target objects. In order to realize the ability of human hand, we develop a robot hand and introduce a control scheme for stable grasping by using only kinematic information. The developed anthropomorphic robot hand, KITECH Hand, has one thumb and three fingers. Each of them has 4 DOF and a soft hemispherical finger tip for flexible opposition and rolling on object surfaces. In addition to a thumb and finger, it has a palm module composed the non-slip pad to prevent slip phenomena between the object and palm. The introduced control scheme is a quitely simple based on the principle of virtual work, which consists of transposed Jacobian, joint angular position, and velocity obtained by joint angle measurements. During interaction between the robot hand and an object, the developed robot hand shows compliant grasping motions by the back-drivable characteristics of equipped actuator modules. To validate the feasibility of the developed robot hand and introduced control scheme, collective experiments are carried out with the developed robot hand, KITECH Hand.

Development of an Anthropomorphic Robot Hand with Size and Motion Range Identical to a Human Hand

강형석,신동헌 한국정밀공학회 2013 International Journal of Precision Engineering and Vol. No.

The anthropomorphic robot hand with the linear actuators consisting of a motor and a lead screw has the stronger grasping power than the hand actuated by motors and insufficient gear reduction. This paper presents the UPS/RPS-RR parallel mechanism to use the linear actuators effectively for the robot hand. It enables us to get the forward/inverse kinematic solutions, while the previous mechanism for the linear actuator failed. Since the grasping motion of the developed hand is composed of the active motion of the proximal phalange and the passive motions of the middle and the distal phalanges, the linkage mechanism is designed to make the motion range of the phalanges the same as that of a human hand. Then, all the phalanges of each finger are bent gradually in the whole motion range from a completely opened hand to a closed hand as a human hand does. This robot hand has four fingers including a thumb. Each finger has 2-DOF and each proximal phalange is actuated by two linear actuators. The palm itself has 2-DOF to make the motion of the thumb and the small metacarpi similar to the natural palm arch of a human hand. Finally, instead of using specially manufactured actuators, the usage of commercial store-bought actuators enables our hand to be a cheaper candidate for the educational robot hand.

손 제스처 기반의 애완용 로봇 제어

박세현(Se-Hyun Park),김태의(Tae-Ui Kim),권경수(Kyung-Su Kwon) 한국산업정보학회 2008 한국산업정보학회논문지 Vol.13 No.4

본 논문에서는 애완용 로봇에 장착된 카메라로부터 획득된 연속 영상에서 사용자의 손 제스처를 인식하여 로봇을 제어하는 시스템을 제안한다. 제안된 시스템은 손 검출, 특징 추출, 제스처 인식, 로봇제어의 4단계로 구성된다. 먼저 카메라로부터 입력된 영상에서 HSI 색상공간에 정의된 피부색 모델과 연결성분 분석을 이용하여 손 영역을 검출한다. 다음은 연속 영상에서 손 영역의 모양과 움직임에 따른 특징을 추출한다. 이때 의미 있는 제스처의 구분을 위해 손의 모양을 고려한다. 그 후에 손의 움직임에 의해 양자화된 심볼들을 입력으로 하는 은닉 마르코프 모델을 이용하여 손 제스처는 인식된다. 마지막으로 인식된 제스처에 대응하는 명령에 따라 애완용 로봇이 동작하게 된다. 애완용 로봇을 제어하기 위한 명령으로 앉아, 일어서, 엎드려, 악수 등의 제스처를 정의하였다. 실험결과로 제안한 시스템을 이용하여 사용자가 제스처로 애완용 로봇을 제어 할 수 있음을 보였다. In this paper, we propose the pet robot control system using hand gesture recognition in image sequences acquired from a camera affixed to the pet robot. The proposed system consists of 4 steps; hand detection, feature extraction, gesture recognition and robot control. The hand region is first detected from the input images using the skin color model in HSI color space and connected component analysis. Next, the hand shape and motion features from the image sequences are extracted. Then we consider the hand shape for classification of meaning gestures. Thereafter the hand gesture is recognized by using HMMs (hidden markov models) which have the input as the quantized symbol sequence by the hand motion. Finally the pet robot is controlled by a order corresponding to the recognized hand gesture. We defined four commands of sit down, stand up, lie flat and shake hands for control of pet robot. And we show that user is able to control of pet robot through proposed system in the experiment.

강력 정밀 파지를 할 수 있는 로봇 손의 기구 설계

이민규(Min Gyu Lee),이용훈(Yong Hoon Lee),임홍재(Hong Jae Yim),최우석(Wooseok Choi),이용권(Yong Kwun Lee) 대한기계학회 2007 대한기계학회 춘추학술대회 Vol.2007 No.10

Recently, robots have begun to perform various tasks on replacing the human in the daily life such as cleaning, entertainments etc. In order to accomplish the effective performance of intricate and precise tasks, robot hand must have special capabilities, such as decision making in given condition, autonomy in unknown situation and stable manipulation of object In this study, we addresses the development of a 3-fingered humanoid robot hand system We execute static analysis and vibration analysis to reserve stability at the design. We propose a fust and efficient grasp by the robot hand. Grasp motion of the finger uses a linear actuator and gears. Motion can be distinguished into four parts depending on the grasping thin paper, sphere, and column A new robot is manufactured and feasibility of the hand is validated through preliminary experiments.

Analysis Grasp Stability for Multi-fingered Robot Hand

Eun-Hye Kim,Myo-Taeg Lim,Yong-Kwun Lee 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

This paper describes grasp stability for a multi-fingered robot hand, called the KIST hand. The robot hand has controlled by four under-actuated fingers with totally nine DOFs, which are controlled by two linear actuators and linkage knuckles. This mechanism is able to generate high power compare to common robot hands that use rotary actuators. The robot hand has four tactile sensors which are attached to the fingertips on the each finger. The each tactile sensor can independently measure the contact force between the robot hand and an object. Using the tactile sensors, various objects can be grasped, such as a small tennis ball, a plastic ball and a rubber ball. In the former part of the paper, the mechanical design of the robot hand is presented. In the latter part of the paper, the control algorithm is described, and the analysis of grasp stability is confirmed by the experimental result.

Hand Gesture Recognition Framework for Indoor Wheeled Mobile Robots Using Hand Shape and Pose

Seungho Yun,Haeun Park,Hui Sung Lee 제어로봇시스템학회 2024 제어로봇시스템학회 국제학술대회 논문집 Vol.2024 No.10

In this paper, we propose a hand gesture recognition framework to control an indoor wheeled mobile robot. Our method combines hand shapes and arm poses to recognize human upper body gestures across various operation scenarios for a wheeled mobile robot. The YOLOv8m model is utilized for hand shape recognition, and a YOLOv8mpose model is used to mitigate misrecognition. An algorithm based on arm length ratios and angles distinguishes a person’s upper body posture. The hand gesture recognition framework is deployed on a Jetson Orin Nano environment using an Intel RealSense D455f camera. The results of the recognized gestures are sent to the wheeled mobile robot, and the robot is implemented to move based on the information from the recognized gestures. This approach offers high accessibility, enabling mobile robot control using hand gestures without any physical user interface.

Application of DSD Mechanism to Robot Hand

Chiharu Ishii,Yosuke Nishitani,Hiroshi Hashimoto 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8

Recently, the development of a versatile robot hand aiming at the application to an artificial arm or a humanoid robot is in demand. In this paper, omni-directional bending mechanism which is called “double-screw-drive mechanism” was applied to a robot hand. The robot hands with two fingers and three fingers were built. For the robot hand with three fingers, each fingertip was controlled so as to track the elliptical orbit and experiment was carried out.The DSD robot hand succeeded in rotating the cap of the PET bottle and removing the cap from the bottle.

2015개정 교육과정 중학교 기술교과 로봇 체험활동과제 개발

이미소,이경택 한국교원대학교 뇌기반교육연구소 2020 Brain, Digital, & Learning Vol.10 No.3

The purpose of this study is to develop a robot hands-on activity task for the ‘manufacturing technology’ section of the middle school technology subject of the 2015 revised curriculum. The study procedure proceeded to the preparation-development-improvement phases. In the preparation stage, the textbook of the 2015 revised curriculum was analyzed to suggest the necessity of robot education, and commercial education robots were analyzed to supplement the weak points. In the development stage, a robot education kit that differentiates it from the existing robots was developed, and teaching and learning materials that can be used together were developed to construct a robot hands-on activity task. in the improvement phase, expert verification was first conducted, and the robot hands-on activity task including the robot education kit and teaching and learning materials were preliminary tested to correct and supplement them. The results obtained in this study are as follows. First, a robot education kit was developed that can learn the components, operation principles, etc. of the robot, including all of the components of them, the driving unit, the control unit, the sensor unit, and the power unit. Second, some parts of the robot education kit were designed and manufactured by the students themselves, so that students can show their creativity in the assembly process of the robot education kit. Third, in order to construct the robot hands-on activity task with the robot education kit, teaching and learning materials on the robot’s operation principle, robot type, and robot components were developed.

손 재활을 위한 로봇 시스템 기술 동향

민지영,문효정,신화희,이용찬 한국재활복지공학회 2023 재활복지공학회논문지 Vol.17 No.4

본 논문은 손 재활 로봇에 대한 연구 동향과 발전 방향을 이해하기 위해 조사하고 요약하는 것을 목표로한다. 최근 손 재활의 수요가 증가함에 따라 손 재활 로봇에 대한 연구는 활발하게 수행되고 있다. 손 재활은 다른 부위에 비해 높은 자유도와 복잡성을 가지며, 이를 효과적으로 치료하기 위해 다양한 형태의 로봇과 손 재활 방법이 연구되고 있다. 다양한 형태의 손 재활 로봇 분석을 위해 착용 형태, 사용자 의도 파악방식, 구동 방식으로 분류하여 정리하였다. 또, 손 재활 방법의 이해를 위해 제어 알고리즘, 재활 동작, 사용자-로봇 상호작용 내용으로 분류하였다. 결과적으로 손 재활 로봇의 최고 수준과 각 시스템의 성능을 분석하고 생체 데이터의 딥러닝, 재활 시스템에 인공지능 적용 등 향후 연구 방향을 제시하고자 한다. This paper aims to investigate and summarize to understand the research trends and development directions for hand rehabilitation robots. Recently, as the demand for hand rehabilitation increases, research on hand rehabilitation robots is being actively conducted. Hand rehabilitation has a higher degree of freedom and complexity compared to other parts, and various types of robots and hand rehabilitation methods are being studied to treat this effectively. To analyze various types of hand rehabilitation robots, they were categorized and organized into wearing type, user intention identification method, and driving method. In addition, to understand the hand rehabilitation method, it was classified into control algorithm, rehabilitation movement, and user-robot interaction content. As a result, we want to analyze the state-of-the-art of hand rehabilitation robots and the performance of each system and suggest future research directions, such as deep learning of biometric data and application of artificial intelligence to rehabilitation systems.