• The Journal of Korea Robotics Society
• /
• v.12 no.4
• /
• pp.411-418
• /
• 2017

During the intramedullary nailing procedure, surgeons feel difficulty in manipulation of the X-ray device to align it to axes of nailing holes and suffer from the large radiation exposure from the X-ray device. These problems are caused by the fact the surgeon cannot see the hole's location directly and should use the X-ray device to find the hole's location and direction. In this paper, we proposed the robotic guidance of the distal screwing using an optical tracking system. To track the location of the hole for the distal screwing, the reference marker is attached to the proximal end of an intramedullary nail. To guide the drill's direction robustly, the 6-degree-of-freedom robotic arm is used. The robotic arm is controlled so as to align the drill guiding tool attached the robotic arm with the obtained the hole's location. For the safety, the robot's linear and angular velocities are restricted to the predefined values. The experimental results using the artificial bones showed that the position error and the orientation error were 0.91 mm and $1.64^{\circ}$, respectively. The proposed method is simple and easy to implement, thus it is expected to be adopted easily while reducing the radiation exposure significantly.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.10
• /
• pp.1029-1036
• /
• 2011

An energy-efficient reference walking trajectory generation algorithm is suggested utilizing allowable ZMP (Zero-Moment-Point) region, which maxmizes the energy efficiency for cyclic gaits, based on three-dimensional LIPM (Linear Inverted Pendulum Model) for biped robots. As observed in natural human walking, variable ZMP manipulation is suggested, in which ZMP moves within the allowable region to reduce the joint stress (i.e., rapid acceleration and deceleration of body), and hence to reduce the consumed energy. In addition, opimization of footstep planning is conducted to decide the optimal step-length and body height for a given forward mean velocity to minimize a suitable energy performance - amount of energy required to carry a unit weight a unit distance. In this planning, in order to ensure physically realizable walking trajectory, we also considered geometrical constraints, ZMP stability condition, friction constraint, and yawing moment constraint. Simulations are performed with a 12-DOF 3D biped robot model to verify the effectiveness of the proposed method.

• 한국HCI학회:학술대회논문집
• /
• 2008.02c
• /
• pp.19-24
• /
• 2008

This paper presents a physically-based haptic rendering algorithm for a deformable object based on visual information about the intervention between a tool and a real object in a remote place. The physically-based model of a deformable object is created from the mechanical properties of the object and the captured image obtained with a CCD camera. When a slave system exerts manipulation tasks on a deformable object, the reaction force for haptic rendering is computed using boundary element method. Snakes algorithm is used to obtain the geometry information of a deformable object. The proposed haptic rendering algorithm can provide haptic feedback to a user without using a force transducer in a teleoperation system.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.1
• /
• pp.66-75
• /
• 2016

Stereoscopic image generated by depth image-based rendering(DIBR) for surveillance robot and camera is appropriate in a low bandwidth network. The image is very important data for the decision-making of a commander and thus its integrity has to be guaranteed. One of the methods used to detect manipulation is to check if the stereoscopic image is taken from the original camera. Sensor pattern noise(SPN) used widely for camera identification cannot be directly applied to a stereoscopic image due to the stereo warping in DIBR. To solve this problem, we find out a shifted object in the stereoscopic image and relocate the object to its orignal location in the center image. Then the similarity between SPNs extracted from the stereoscopic image and the original camera is measured only for the object area. Thus we can determine the source of the camera that was used.

• Journal of Powder Materials
• /
• v.28 no.6
• /
• pp.509-517
• /
• 2021

Smart materials capable of changing their characteristics in response to stimuli such as light, heat, pH, and electric and magnetic fields are promising for application to flexible electronics, soft robotics, and biomedicine. Compared with conventional rigid materials, these materials are typically composed of soft materials that improve the biocompatibility and allow for large and dynamic deformations in response to external environmental stimuli. Among them, smart magnetic materials are attracting immense attention owing to their fast response, remote actuation, and wide penetration range under various conditions. In this review, we report the material design and fabrication of smart magnetic materials. Furthermore, we focus on recent advances in their typical applications, namely, soft magnetic actuators, sensors for self-assembly, object manipulation, shape transformation, multimodal robot actuation, and tactile sensing.

• Journal of the Ergonomics Society of Korea
• /
• v.15 no.2
• /
• pp.165-176
• /
• 1996

Hand posture and force, which define aspects of the way an object is grasped, are features of robotic manipulation. A means for specifying these grasping "flavors" has been developed that uses an instrumented glove equipped with joint and force sensors. The new grasp specification system is being used at the Pennsylvania State University (Penn State) in a Virtual Reality based Point-and-Direct (VR-PAD) robotics implementation. In the Computer Integrated Manufacturing (CIM) Laboratory at Penn State, hand posture and force data were collected for manipulating bricks and other items that require varying amounts of force at multiple pressure points. The feasibility of measuring desired grasp characteristics was demonstrated for a modified Cyberglove impregnated with FSR (Force Sensitive Resistor) pressure sensors in the fingertips. A joint/force model relating the parameters of finger articulation and pressure to various lifting tasks was validated for the instrumented "wired" glove. Operators using such a modified glove may ultimately be able to configure robot grasping tasks in environments involving hazardous waste remediation, flexible manufactruing, space operations and other flexible robotics applications. In each case, the VR-PAD approach improved the computational and delay problems of real-time multiple- degree-of-freedom force feedback telemanipulation.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.3
• /
• pp.104-111
• /
• 2014

In this paper, we deal with robotic automation for assembling car brake modules. A car brake module is comprises of a torque member, two brake pads, and two pad liners. In the assembly process, brake pads and pad liners are needed to be inserted in a torque member. If we use a typical robotic hand for the assembly, task time takes too long. So, we propose two methods. The first method is to use an end effector that has five grippers capable of gripping five assembly parts. In the first method we attached the implemented end effector to a conventional 6 degrees of freedom industrial manipulator and performed the bake module assembly task. Experimental results show that the task time is remarkably reduced. The brake module assembly task needs the robot to change its orientation frequently, so, in the second method, we added one degree of freedom to the end effector that is used in the first method. By attaching it to a conventional 6 degrees of freedom industrial manipulator, we composed a 7 degrees of freedom redundant manipulator. A redundant manipulator has the advantage of flexible manipulation so the robot can change its orientation easily and can perform assembly task very fast. Experimental results show that the second method dramatically reduce whole task time for brake module assembly.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.854-857
• /
• 2020

최근 사람형(Anthropomorphic)로봇손의 사물조작 지능을 개발하기 위하여 행동복제(Behavior Cloning) Deep Reinforcement Learning(DRL) 연구가 진행중이다. 자유도(Degree of Freedom, DOF)가 높은 사람형 로봇손의 학습 문제점을 개선하기 위하여, 행동 복제를 통한 Human Demonstration Augmented(DA)강화 학습을 통하여 사람처럼 사물을 조작하는 지능을 학습시킬 수 있다. 그러나 사물 조작에 있어, 의미 있는 파지를 위해서는 사물의 특정 부위를 인식하고 파지하는 방법이 필수적이다. 본 연구에서는 딥러닝 YOLO기술을 적용하여 사물의 특정 부위를 인식하고, DA-DRL을 적용하여, 사물의 특정 부분을 파지하는 딥러닝 학습 기술을 제안하고, 2 종 사물(망치 및 칼)의 손잡이 부분을 인식하고 파지하여 검증한다. 본 연구에서 제안하는 학습방법은 사람과 상호작용하거나 도구를 용도에 맞게 사용해야하는 분야에서 유용할 것이다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.858-861
• /
• 2020

로봇이 사람과 같이 다양하고 복잡한 사물 조작을 하기 위해서 휴먼형 로봇손의 사물 파지 작업이 필수적이다. 자유도 (Degree of Freedom, DoF)가 높은 휴먼형(anthropomorphic) 로봇손을 학습시키기 위하여 사람 데모(human demonstration)가 결합된 강화학습 최적화 방법이 제안되었다. 본 연구에서는 강화학습 최적화 방법에 사람 데모가 결합된 Demonstration Augmented Natural Policy Gradient(DA-NPG)와 NPG 의 성능 비교를 통하여 행동 복제의 효율성을 확인하고, DA-NPG, DA-Trust Region Policy Optimization (DA-TRPO), DA-Proximal Policy Optimization (DA-PPO)의 최적화 방법의 성능 평가를 위하여 6 종의 물체에 대한 휴먼형 로봇손의 사물 조작 작업을 수행한다. 그 결과, DA-NPG 와 NPG를 비교한 결과를 통해 휴먼형 로봇손의 사물 조작 강화학습에 행동 복제가 효율적임을 증명하였다. 또한, DA-NPG 는 DA-TRPO 와 유사한 성능을 보이면서 모든 물체에 대한 사물 파지에 성공하여 가장 안정적이었다. 반면, DA-TRPO 와 DA-PPO 는 사물 조작에 실패한 물체가 존재하여 불안정한 성능을 보였다. 본 연구에서 제안하는 방법은 향후 실제 휴먼형 로봇에 적용하여 휴먼형 로봇 손의 사물조작 지능 개발에 유용할 것으로 전망된다.