• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2014년도 제50차 하계학술대회논문집 22권2호
• /
• pp.17-18
• /
• 2014

현대사회와 미래사회는 가속화되어지는 IT기술에 의해서 융합되어진 작업의 효율 및 성능의 발전이 이슈화되고 있다. 따라서 1990년대부터는 군사 및 재활분야와 함께 제조업 및 유통업 등 전반적인 산업 모두에서 근력보조기구에 대한 연구가 활발히 진행되고 있다. 과거에는 일반인이 무거운 짐을 운반하는 것을 완전한 로봇이 대체하거나 몸이 불편한 사회적 약자가 휠체어 및 지팡이 또는 전동 휠체어와 같은 보조 개념이 아닌 완전한 대체의 개념을 가지고 있었다. 그러나 웨어러블이 대두됨에 따라 기계와 인체가 합쳐지는 상호작용 근력보조기구가 탄생했다. 근력보조기구는 힘/토크 센서를 통한 인간과 로봇간의 상호작용에 의해 인간의 다양한 상지 및 하지 동작을 구현할 수 있는 근력 강화용 웨어러블 로봇 등이 있다.

• 로봇학회논문지
• /
• 제16권2호
• /
• pp.79-85
• /
• 2021

Soft fluidic actuators (SFAs) are widely utilized in various areas such as wearable systems due to the inherent compliance which allows safe and flexible interaction. However, SFA-driven systems generally require a large pump, multiple valves and tubes, which hinders to develop a miniaturized system with small range of motion. Thus, a highly integrated soft actuator needs to be developed for implementing a compact SFA-driven system. In this study, we propose an electro-hydraulic soft zipping actuator that can be used as a miniature pump. This actuator exerts tactile force as a dielectric liquid contained inside the actuator pressurized its deformable part. In addition, the proposed actuator can estimate the internal dielectric liquid thickness by using its self-sensing function. Besides, the electrical characteristics and driving performance of the proposed system were verified through experiments.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.824-825
• /
• 2023

본 연구는 동물을 위한 웨어러블 로봇을 개발하고, 이를 상황에 따라 적절한 보행을 제어할 수 있도록 강화학습(DQN 알고리즘)을 적용한다. 다양한 센서를 동물에 부착하여 얻은 데이터를 DQN 알고리즘에 입력으로 사용한다. 이 알고리즘은 수집된 데이터를 분석하여 어떤 상황에서 어떤 종류의 보행이 가장 적절한지를 판단하고, 이를 로봇에 적용하여 동물의 보행을 자연스럽게 구현한다

• Physical Therapy Rehabilitation Science
• /
• 제11권4호
• /
• pp.478-487
• /
• 2022

Objective: This study was conducted to analyze the effect of wearable complex muscle support system on energy efficiency during walking in elderly. Design: Cross sectional study Methods: Twenty healthy elderly participated in this study. All subjects performed a 6 minuteswalk test(6MWT) and stair climbing test in dual, slack and no suit conditions. In each condition, oxygen consumption(VO₂), metabolic equivalents(METs), energy expenditure measures(EEm), physiological cost index(PCI), walking velocity and heartrate were measured. Through repeated measured ANOVA, it was investigated whether there was a statistically significant difference in the measurement results between the three conditions. Results: In over-ground walking, VO₂, METs and EEm showed significant differences between no suit and slack conditions(p<0.05). In stair climbing, VO₂ showed significant difference between slack and dual conditions(p<0.05). Also, METs and EEm showed significant differences between no suit and slack, and between slack and dual conditions(p<0.05). Conclusions: Wearing the wearable complex muscle support system for elderly does not have much benefit in energy metabolism efficiency in over-ground, but there is a benefit in stair walking.

• 제어로봇시스템학회논문지
• /
• 제18권12호
• /
• pp.1106-1114
• /
• 2012

To achieve synchronized motion between a wearable robot and a human user, the redundancy must be resolved in the same manner by both systems. According to the seven DOF (Degrees of Freedom) human arm model composed of the shoulder, elbow, and wrist joints, positioning and orientating the wrist in space is a task requiring only six DOFs. Due to this redundancy, a given task can be completed by multiple arm configurations, and thus there exists no unique mathematical solution to the inverse kinematics. This paper presents analysis on the kinematic and dynamic aspect of the human arm movement and their effect on the redundancy resolution of the human arm based on a seven DOF manipulator model. The redundancy of the arm is expressed mathematically by defining the swivel angle. The final form of swivel angle can be represented as a linear combination of two different swivel angles achieved by optimizing different cost functions based on kinematic and dynamic criteria. The kinematic criterion is to maximize the projection of the longest principal axis of the manipulability ellipsoid for the human arm on the vector connecting the wrist and the virtual target on the head region. The dynamic criterion is to minimize the mechanical work done in the joint space for each two consecutive points along the task space trajectory. As a first step, the redundancy based on the kinematic criterion will be thoroughly studied based on the motion capture data analysis. Experimental results indicate that by using the proposed redundancy resolution criterion in the kinematic level, error between the predicted and the actual swivel angle acquired from the motor control system is less than five degrees.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 추계학술대회
• /
• pp.868-871
• /
• 2016

최근 IoT를 활용한 웨어러블 기기 및 무인 이동체에 관한 연구가 활발히 진행되고 있다. 그 중 무인 이동체는 IT 기술들의 집약체라고 할 수 있다. 로봇, 자율 주행, 장애물 회피, 데이터 통신, 전력, 영상 처리 등의 기술들이 합쳐진 것을 무인 이동체 또는 무인 로봇이라고 부른다. 무인 이동체의 최종 목표는 수동이 아닌 자율 주행을 하여 목적지까지 안전하고 신속하게 도달하는 것을 목표로 한다. 본 논문에서는 무인 이동체의 기술들 중 하나인 영상 처리 분야를 다루고자 한다. 현재 배터리의 기술로는 무인 이동체가 최대 1시간까지 주행할 수밖에 없다는 것을 감안하여, 전력 소비를 최소한으로 줄이기 위해 소형 컴퓨터인 라즈베리 파이3를 사용하여 영상 인식 시스템을 설계하고자 한다. 제안하고자 하는 시스템은 카메라로부터 받는 영상의 모든 것을 인식하는 시스템을 목표로 한다.

• 사물인터넷융복합논문지
• /
• 제9권6호
• /
• pp.37-44
• /
• 2023

인터스트리4.0의 주요 기술인 인간-로봇 협업은 작업자의 안전을 보장하기 위한 추가적인 조치들이 필요하다. 협동로봇과 작업자간 충돌을 회피하는 기존 방식은 주로 로봇에 부착된 센서와 카메라를 기반으로 총돌을 탐지한다. 이러한 방식은 로봇, 사람 물체를 지속적으로 추적하고 충돌회피를 위한 복잡한 알고리즘이 필요하며, 작업 환경 변화에 빠르게 대응하지 못하는 단점이 있다. 본 논문은 인간과 로봇이 협업하는 과정에서 작업자가 위험을 느낄 때의 감정을 인식하여 협동로봇과의 충돌을 방지할 수 있는 웹 기반 플랫폼을 개발하였다. 이를 위해 웨어러블 뇌파장치를 이용하여 감정 관련 뇌파를 수집하고 저장하는 웹 기반 애플리케이션을 개발하였으며, 중립/긍정/부정 감정의 특징을 추출하고 분류하는 딥러닝 모델을 제안하였다. 또한 분류된 감정에 따라 모터동작을 제어하는 사물인터넷 인터페이스 프로그램을 개발하였다. 구현된 시스템의 성능분석을 위해 공개 데이터세트와 실제 수집된 데이터 세트를 사용하여 제안한 딥러닝 모델의 성능을 분석하였다. 공개 데이터 세트의 경우 정확도는 96.8%이며, 실제 수집 데이터세트의 경우 정확도는 70.7%이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.1201-1216
• /
• 2017

In this study, we described the development of a methodology to measure tip-pinch strength on the paretic hand rehabilitation device and aimed to investigate reliability of the device. FSR sensors were embedded on the device, and tip pinch strength was estimated with data collected from the sensors using a developed equation while participants were demonstrating tip pinch. Reliability tests included inter-rater, test-retest, and inter-instrument reliability. B&L Engineering pinch gauge was utilized for the comparison. Thirty-seven healthy students participated in the experiment. Both inter-rater and test-retest reliability were excellent as Intraclass Correlation Coefficients (ICCs) were greater than 0.9 (p<0.01). There were no statistically significant differences in tip-pinch strengths. Inter-instrument reliability analysis confirmed good correlation between the two instruments (r = 0.88, p < 0.01). The findings of this study suggest that the two instruments are not interchangeable. However, the tip-pinch mechanism used in the paretic hand rehabilitation device is reliable that can be used to evaluate tip pinch strength in clinical environment and can provides a parameter that monitors changes in the hand functions.

• 로봇학회논문지
• /
• 제15권3호
• /
• pp.240-247
• /
• 2020

This paper presents a novel knitted data glove system for pattern classification of hand posture. Several experiments were conducted to confirm the performance of the knitted data glove. To find better sensor materials, the knitted data glove was fabricated with stainless-steel yarn and silver-plated yarn as representative conductive yarns, respectively. The result showed that the signal of the knitted data glove made of silver-plated yarn was more stable than that of stainless-steel yarn according as the measurement distance becomes longer. Also, the pattern classification was conducted for the performance verification of the data glove knitted using the silver-plated yarn. The average classification reached at 100% except for the pointing finger posture, and the overall classification accuracy of the knitted data glove was 98.3%. With these results, we expect that the knitted data glove is applied to various robot fields including the human-machine interface.

• 로봇학회논문지
• /
• 제18권2호
• /
• pp.182-188
• /
• 2023

Due to the acceleration of an aging society, the need for lower limb exoskeletons to assist gait is increasing. And for use in daily life, it is essential to have technology that can accurately estimate gait phase even in the walking environment and walking speed of the wearer that changes frequently. In this paper, we implement an LSTM-based gait phase estimation learning model by collecting gait data according to changes in gait speed in outdoor level ground and stair environments. In addition, the results of the gait phase estimation error for each walking environment were compared after learning for both max hip extension (MHE) and max hip flexion (MHF), which are ground truth criteria in gait phase divided in previous studies. As a result, the average error rate of all walking environments using MHF reference data and MHE reference data was 2.97% and 4.36%, respectively, and the result of using MHF reference data was 1.39% lower than the result of using MHE reference data.