• 로봇학회논문지
• /
• 제9권4호
• /
• pp.258-263
• /
• 2014

An adaptive robot hand (AR-Hand) has a stable grasp of different objects in unstructured environments. In this study, we propose an AR-Hand based on a tendon-driven mechanism which consists of 4 fingers and 12 DOFs. It weighs 0.5 kg and can grasp an object up to 1 kg. This hand based on the adaptive grasp mechanism is able to provide a stable grasp without a complex control algorithm or sensor system. The fingers are driven by simple tendon structures with each finger capable of adaptively grasping the objects. This paper presents a method to decide the joint stiffness. The adaptive grasping is verified by various grasping experiments involving objects with different shapes and sizes.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.694-697
• /
• 1996

The aim of this work for 5 years from 1994 is to develop a multi-fingered robot hand and its control system for grasp and manipulation of objects dexterously. Since the robot hand is still being developed, a commercialized robot hand from Barrett Company is utilized to implement a hand controller and control algorithm. For this, VME based motion control and interface boards are developed and multi-sensors such as encoder, force/torque sensor, dynamic sensor and artificial skin sensor are partly developed and employed for the grasping control algorithm. In oder to handle uncertainties such as mechanical idleness and backlash, a fuzzy rule based grasping algorithm is also considered and tested with the developed control system.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2012년도 추계학술대회 논문집
• /
• pp.217-218
• /
• 2012

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2011년도 춘계학술대회 논문집
• /
• pp.443-444
• /
• 2011

• Journal of Biosystems Engineering
• /
• 제25권5호
• /
• pp.399-408
• /
• 2000

This study is final focused on developing fruit harvesting robot can distinguish fruit type and status accurately. Multi-joint robot is able to discriminate tree shape and select mature fruit by image processing. The multi-joint robot consists of (a) rotating base, (b)turning first joint-arm, (c)rotating and turning second joint-arm, (d)rotating and turning third joint-arm, (e)rotating and turning last joint and (f)picker hand. The operational ranges of the robot are: horizontal 860~2,220mm, vertical 1,440~2,260mm, 270 degrees’rotation angle, 90 or 270 degrees’turning angle. The robot weighs 330kg. The multi-joint robot was designed in high accuracy and efficiency by getting as close as the movements of human arms and waist.

• 제어로봇시스템학회논문지
• /
• 제18권4호
• /
• pp.328-336
• /
• 2012

In this paper, we propose a robust fingertip extraction and extended Continuously Adaptive Mean Shift (CAMSHIFT) based robust hand gesture recognition for natural human-like HRI (Human-Robot Interaction). Firstly, for efficient and rapid hand detection, the hand candidate regions are segmented by the combination with robust $YC_bC_r$ skin color model and haar-like features based adaboost. Using the extracted hand candidate regions, we estimate the palm region and fingertip position from distance transformation based voting and geometrical feature of hands. From the hand orientation and palm center position, we find the optimal fingertip position and its orientation. Then using extended CAMSHIFT, we reliably track the 2D hand gesture trajectory with extracted fingertip. Finally, we applied the conditional density propagation (CONDENSATION) to recognize the pre-defined temporal motion trajectories. Experimental results show that the proposed algorithm not only rapidly extracts the hand region with accurately extracted fingertip and its angle but also robustly tracks the hand under different illumination, size and rotation conditions. Using these results, we successfully recognize the multiple hand gestures.

• 센서학회지
• /
• 제23권2호
• /
• pp.127-133
• /
• 2014

This paper describes a design and manufacture of a two-axis force sensor and a single-axis force sensor for the fingers of an intelligent robot's hand. The robot's finger is composed of a two-axis force sensor, a first knuckle, a single-axis force sensor, a second knuckle, a spring, a motor of first knuckle, a motor of second knuckle, and so on. The two-axis force sensor attached to the first knuckle and the single-axis force sensor attached to the second knuckle were designed and manufactured, and the characteristics test of two sensors was carried out. As a test results, the interference error of the two-axis force sensor was less than 0.68%, the repeatability error of each sensor was less than 0.02%, and then the non-linearity was less than 0.03%. It is thought that the sensors can be used for the fingers of the intelligent robot's hand for rehabilitation exercise of finger patients.

• 한국지능시스템학회논문지
• /
• 제27권2호
• /
• pp.126-131
• /
• 2017

본 논문에서는 손짓을 이용하여 로봇에게 명령을 내릴 때, 사용자의 여러 가지 손짓 중 의미 있는 동작을 추출하기 위한 방법을 제시한다. 로봇에게 명령을 내릴 때, 사람들의 손짓은 준비동작, 본 동작, 마무리 동작으로 구분할 수 있다. 여기에서 본 동작이 로봇에게 명령을 전달하는 의미 있는 동작이고 다른 동작은 그 동작을 위한 의미 없는 보조 동작이다. 따라서 연속적인 손짓에서 본 동작만을 추출해야 한다. 또한 사람들은 무위식적으로 손을 움직일 수 있는데 이러한 동작들 역시 의미가 없는 동작으로 로봇이 판단하여야 한다. 본 연구에서는 키넥트 센서를 이용하여 획득한 거리영상에서 사람의 골격자료를 획득하여 손을 추출하고, 칼만필터를 이용하여 손의 위치를 추적하면서 의미 있는 손동작과 의미 없는 손동작을 구분하고 은닉 마코프 모델을 이용하여 손짓을 인식한다.

• 한국산업융합학회 논문집
• /
• 제16권4호
• /
• pp.141-145
• /
• 2013

This paper is the development of industrial robotic hand system and the design methods of industrial robot hand that can mimic human fingers motion. In order to overcome problems incurred during the reduction of the mobility, this study focuses on analyzing human hand structure and finger movements from an anatomical point of view. As a result, distinctive features that improve the discovered stability in constraints for range of motion in the fingers is reflected in this design concept. A 4-bar Linkage is used in robot finger structure. Lastly, there were experiments to inspect the developed robot hands performance. The developed robot hand has many potential applications and can be in many different fields.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.83.1-83
• /
• 2001

This paper presents a three-fingered robot hand, called the KIST hand, Which have one active joint and one passive joint. The thumb is fixed on the palm, and the index and the middle take lateral motions symmetrically. A mechanical clutch and an embedded force sensor, attached on the distal link of the fingers, enable the KIST hand to perform human-like functions. A result of experiment shows reliable grasping performance of the hand which maintain stable grasp under disturbances.