• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권10호
• /
• pp.910-917
• /
• 2007

인간-로봇 상호작용에서 접촉은 인간에게 정서적 안정을 줄 수 있는 중요한 상호작용 방법 중 하나이다. 그러나 지금까지 음성과 영상을 기반으로 인간-로봇 상호작용이 이루어지는 연구가 대부분이었다. 본 논문에서는 접촉을 통한 인간-로봇 상호작용을 위해 인간의 접촉행동을 인식하는 방법을 제안한다. 제안한 인식 방법에서 인식 과정은 전처리 단계와 인식 단계로 나뉜다. 전처리 단계는 접촉감지부에서 생성된 데이타로부터 인식할 수 있는 특징들을 계산하는 단계이고 인식 단계는 인식기를 통해 접촉행동으로 분류하는 단계이다. 접촉감지부는 힘 센서인 FSR 센서를 이용하여 제작하였고 인식기는 신경망 모델인 다층퍼셉트론을 사용하였다. 실험은 남자 여섯 명에 의해 생성된 세 가지 접촉행동; '때리다', '쓰다듬다', '간질이다' 데이타를 가지고, 사람별로 인식기를 생성하여 cross-validation으로 평가한 결과 82.9%의 평균인식률을 보였고, 사람별 구분 없이 한 개의 인식기로 실험한 결과는 74.5%의 평균 인식률을 보였다.

• 한국군사과학기술학회지
• /
• 제18권3호
• /
• pp.309-315
• /
• 2015

This paper presents a lower-limb exoskeleton testbed and its control method. An exoskeleton is a wearable robotic system that can enhance wearer's muscle power or assist human's movements. Among a variety of its applications, especially for military purpose, a wearable robot can be very useful for carrying heavy loads during locomotion by augmenting soldiers' mobility and endurance. The locomotion test on a treadmill was performed up to maximum 4km/h walking speed wearing the lower-limb exoskeleton testbed with a 45kg backpack load.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1188-1203
• /
• 2020

The human expression contains a lot of information that can be used to detect complex conditions such as pain and fatigue. After deep learning became the mainstream method, the traditional feature extraction method no longer has advantages. However, in order to achieve higher accuracy, researchers continue to stack the number of layers of the neural network, which makes the real-time performance of the model weak. Therefore, this paper proposed an expression recognition framework based on densely concatenated convolutional neural networks to balance accuracy and latency and apply it to humanoid robots. The techniques of feature reuse and parameter compression in the framework improved the learning ability of the model and greatly reduced the parameters. Experiments showed that the proposed model can reduce tens of times the parameters at the expense of little accuracy.

• 인터넷정보학회논문지
• /
• 제17권3호
• /
• pp.67-73
• /
• 2016

모바일 서비스와 교육 보조 로봇이 발달함에 따라, 로봇은 우리의 삶의 일부가 되었고 교육 보조 로봇은 선생님을 보조해 학생들의 교육과 학습에 참여하고 있다. 본 논문은 교육 보조 로봇의 자율성의 정도를 표시하는 자율성 지수를 측정하기 위한 방법을 규정한다. 자율성은 사람의 개입 없이 현재 상태 및 센서 값을 기반으로 주어진 작업을 수행하는 능력이다. 교육 보조 로봇의 자율성 지수는 작업 수준과 사람의 개입 수준으로 구성되며 1단계에서부터 10단계로 정의한다. 제안 방식은 지능형로봇표준포럼(KOROS) 표준으로 채택이 되었으며 해당 표준은 자율적으로 학생들을 지도하는데 활용이 가능하다. 향후 교육 보조 로봇을 활용한 교육 서비스에 큰 혜택을 가져올 것으로 예상하며 그 활용 분야 역시 교육 발전에 크게 이바지할거라 기대한다.

• 제어로봇시스템학회논문지
• /
• 제20권2호
• /
• pp.223-231
• /
• 2014

Humanoid robot is the most suitable robot platform for effective human interaction and various intelligent services. The present work addresses development of real time wireless control application of humanoid robot's forward and backward walks, and turning in walking. For convenience of human users, the application is developed on Android OS (Operating System) working on his or her smartphone. To this end, theoretic background on various-directional biped walking is proposed based on joint trajectories for forward walking, which have been shaped with a global optimization method. In this paper, backward walking is scheduled by interchange of angles and angular velocities and additional change of signs in angular velocities at all the via-points connecting cubic polynomial trajectories. Turning direction in walking is also implemented by activating the transversal hip joint initially located in the support leg in two stages. After validation of the proposed walking schemes with Matlab simulator, a smartphone application for the omnidirectional walking has been developed to control a humanoid robot platform named DARwIn-OP interconnected via Wi-Fi. Experiment result of the present wireless control of a humanoid robot with smartphone is successful, and the application will be released in application market near future.

• 제어로봇시스템학회논문지
• /
• 제15권3호
• /
• pp.315-322
• /
• 2009

This paper explains a control and navigation algorithm of a 6-DOF gait rehabilitation robot, which can allow a patient to navigate in virtual reality (VR) by upper and lower limbs interactions. In gait rehabilitation robots, one of the important concerns is not only to follow the robot motions passively, but also to allow the patient to walk by his/her intention. Thus, this robot allows automatic walking velocity update by estimating interaction torques between the human and the upper limb device, and synchronizing the upper limb device to the lower limb device. In addition, the upper limb device acts as a user-friendly input device for navigating in virtual reality. By pushing the switches located at the right and left handles of the upper limb device, a patient is able to do turning motions during navigation in virtual reality. Through experimental results of a healthy subject, we showed that rehabilitation training can be more effectively combined to virtual environments with upper and lower limb connections. The suggested navigation scheme for gait rehabilitation robot will allow various and effective rehabilitation training modes.

• 정보처리학회논문지D
• /
• 제14D권6호
• /
• pp.657-664
• /
• 2007

URC(Ubiquitous Robotic Companion)이라는 개념은 로봇은 다양한 서비스를 어느 곳에서나 어느 때나 사용자가 제공 받을 수 있도록 네트워크 기반으로한 로봇 시스템을 일컫는다. 이는 로봇에 네트워크를 활용하여 로봇이 제공할 수 있는 응용서비스를 확장하고 로봇이 모든 기능을 자체적으로 가짐으로써 안게 되는 기술적, 비용적 문제를 네트워크를 통해 기능을 분담하는 것이다. URC 소프트웨어 컴포넌트는 크게 HRI, 로봇액션 등으로 구분되는데 본 논문에서는 URC 컴포넌트의 시험평가를 위하여 품질모델 분석과 컴포넌트 시험 성능 평가 기준서를 설계한다. 또한 품질 프로세스 정의, 테스트케이스 설계 및 URC 컴포넌트 테스팅과 평가 사례를 제안한다.

• 제어로봇시스템학회논문지
• /
• 제20권1호
• /
• pp.78-86
• /
• 2014

This paper proposes a method of tracking an object for a person-following mobile robot by combining a monocular camera and a laser scanner, where each sensor can supplement the weaknesses of the other sensor. For human-robot interaction, a mobile robot needs to maintain a distance between a moving person and itself. Maintaining distance consists of two parts: object tracking and person-following. Object tracking consists of particle filtering and online learning using shape features which are extracted from an image. A monocular camera easily fails to track a person due to a narrow field-of-view and influence of illumination changes, and has therefore been used together with a laser scanner. After constructing the geometric relation between the differently oriented sensors, the proposed method demonstrates its robustness in tracking and following a person with a success rate of 94.7% in indoor environments with varying lighting conditions and even when a moving object is located between the robot and the person.

• 로봇학회논문지
• /
• 제10권2호
• /
• pp.70-78
• /
• 2015

The purpose of this study was to investigate how young children recognize the image of robots, and how they understand the relationship between themselves and robots based on school experience. 20 children from kindergarten A had no direct experience with educational robots, whereas 20 children from kindergarten B had experience in using educational robots in their classroom. Total 40 children from age group 5 class participated in this study. We collected data using interview and drawing test. The findings of the study are as follows: First, participating children recognized robots as having both the character of a machine and a human. But children with previous robot experience provided description of robots as a machine-tool. Both groups were not able to explain the structure of robots in details. Second, participating children understood that they can develop a range of social relationships with robots, including simple help to family replacement. There were mixed views on robots among the children with previous experience, but children with no experience described robots as taking the role of peers or family members. These findings could contribute to the development of robots and related programs in the field of early childhood education.

• 유통과학연구
• /
• 제22권2호
• /
• pp.103-113
• /
• 2024

Purpose: With the popularity of artificial intelligence (AI) in the service industry and occurrence ofservice failures in AI-based services, understanding human-robot interaction issues in service failure situations is especially important. Some issues which deserve further empirical investigation are whether consumers can develop the same tolerance for chatbots after service failure as they have for human agents, and the relationship between agent type and tolerance is mediated by the mechanisms of perceived warmth and perceived competence. Research Design, Data, and Methodology: This research experimentally collected and analyzed data from 119 university students who had experienced chatbots service failures. Differences in tolerance towards human agents and chatbots after experiencing service failures were explored, with a further examination of the mediating pathways between this relationship via perceived warmth and perceived competence. Results: Consumers are more tolerant ofservice failure with chatbots compared to service failure with human agents. Significant mediation of the relationship between service agent and service failure tolerance by perceived competence, while perceived warmth has no significant mediating effect. Conclusions: This research enhances our understanding of AI-assisted services, human-computer interaction, improves the service functionality of existing smart devices, and deepens the understanding of the relationship between consumer responses and behaviors.