• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.2005-2010
• /
• 2004

As robots become more prevalent in human daily life, situations requiring interaction between humans and robots will occur more frequently. Therefore, human-robot interaction (HRI) is becoming increasingly important. Although robotics researchers have made many technical developments in their field, intuitive and easy ways for most common users to interact with robots are still lacking. This paper introduces a new approach to enhance human-robot interaction using a semantic symbol language and proposes a method to acquire the intentions of robot users. In the proposed approach, each semantic symbol represents knowledge about either the environment or an action that a robot can perform. Users'intentions are expressed by symbolized multimodal information. To interpret a users'command, a probabilistic approach is used, which is appropriate for interpreting a freestyle user expression or insufficient input information. Therefore, a first-order Markov model is constructed as a probabilistic model, and a questionnaire is conducted to obtain state transition probabilities for this Markov model. Finally, we evaluated our model to show how well it interprets users'commands.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2009년도 학술대회
• /
• pp.418-421
• /
• 2009

본 논문은 표면 근전도 신호(sEMG)를 이용해 상지부의 동작을 실시간으로 예측하고 이를 기반으로 한 인간-기계 상호작용(Human-machine interaction)에 관한 것이다. 사용자의 상지부에 위치한 5 곳의 근육에서 수집하는 근전도 신호와 인공신경회로망(arfiticial neural network) 알고리즘을 이용하여 상지부 동작을 실시간으로 예측하였고, 기계팔(manipulator)이 예측된 동작을 좇아 움직이도록 제어되었다. 이때, 사용자가 기계팔의 끝단(end-effector)과 접촉해 있는 상태에서 상지부 동작은 2 차원 평면 위에서 이루어지도록 제한된다. 본 논문이 제안하는 동작 예측 방법과 인체 각도계(goniometer)를 이용한 경우의 상호 작용 실험을 통해, 동작 예측을 통한 인간-기계 상호 작용의 성능을 알아보았다. 실험 결과로부터, 제안된 실시간 동작 예측 방법을 이용하여 사용자와 기계의 상호 작용 시스템을 구현할 수 있음을 알 수 있다.

• The Journal of the Acoustical Society of Korea
• /
• 제23권2E호
• /
• pp.56-67
• /
• 2004

Despite abundant research outcomes of blind source separation (BSS) in many types of simulated environments, their performances are still not satisfactory to be applied to the real environments. The major obstacle may seem the finite filter length of the assumed mixing model and the nonlinear sensor noises. This paper presents a two-step speech enhancement method with multiple microphone inputs. The first step performs a frequency-domain BSS algorithm to produce multiple outputs without any prior knowledge of the mixed source signals. The second step further removes the remaining cross-channel interference by a spectral cancellation approach using a probabilistic source absence/presence detection technique. The desired primary source is detected every frame of the signal, and the secondary source is estimated in the power spectral domain using the other BSS output as a reference interfering source. Then the estimated secondary source is subtracted to reduce the cross-channel interference. Our experimental results show good separation enhancement performances on the real recordings of speech and music signals compared to the conventional BSS methods.

• 로봇학회논문지
• /
• 제17권4호
• /
• pp.447-454
• /
• 2022

This paper presents the psychomotorik-based play activities executed by the social robot at home which helps children's social and emotional development. Based on the theory and practice of the psychomotorik therapy, the play activities were implemented in the close collaboration between psychmotorik experts, service designers and robotics engineers. The designed play activities are classified into four categories depending on the main areas of child development. The robotic system that can express verbal and nonverbal behaviors was developed in order to play games with children and but also to make children have continuous interest during the play activities with it. Finally, the psychomotorik-based play service scenario and interactive robot system were validated by the expert group from the domain of child psychotherapy. The evaluation results showed that the play service and the robot system were appropriately developed for children from the experts point of view.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.263-266
• /
• 2021

근래의 드론 산업은 다양한 분야에서 사용이 확대되고 있으나 규제 등 여러 가지 사회적 진입장벽으로 시장 진입에 애로사항이 도출되고 있다. 본 논문에서는 드론 산업의 여러 제약 중 배터리의 제한적인 용량으로 장시간 비행이 어려운 문제를 개선하고자 승강식 드론스테이션을 개발하였다. 승강식 드론스테이션은 드론의 비행 중 배터리가 방전될 시 충전 및 정비를 할 수 있고, 드론 간의 통신 중계기 역할을 수행한다. 본 논문에서는 스테이션에 드론이 접근 시 슬라이딩 도어를 개폐하기 위하여 초광대역 통신을 이용한 거리 측정과 위치 인식 시스템에 대한 내용을 기술하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1630-1648
• /
• 2021

Owing to the unprecedented COVID-19 pandemic, the pharmaceutical industry has attracted considerable attention, spurred by the widespread expectation of vaccine development. In this study, we collect relevant topics from news articles related to COVID-19 and explore their links with two South Korean pharmaceutical indices, the Drug and Medicine index of the Korea Composite Stock Price Index (KOSPI) and the Korean Securities Dealers Automated Quotations (KOSDAQ) Pharmaceutical index. We use generalized Dirichlet-multinomial regression (g-DMR) to reveal the dynamic topic distributions over metadata of index values. The results of our analysis, obtained using g-DMR, reveal that a greater focus on specific news topics has a significant relationship with fluctuations in the indices. We also provide practical and theoretical implications based on this analysis.

• Genomics & Informatics
• /
• 제1권1호
• /
• pp.7-19
• /
• 2003

The latest measure of the relative evolutionary age of protein structure families was applied (based on taxonomic diversity) using the protein structural interactome map (PSIMAP). It confirms that, in general, protein domains, which are hubs in this interaction network, are older than protein domains with fewer interaction partners. We apply a hypothesis of 'biological network evolution' to explain the positive correlation between interaction and age. It agrees to the previous suggestions that proteins have acquired an increasing number of interaction partners over time via the stepwise addition of new interactions. This hypothesis is shown to be consistent with the scale-free interaction network topologies proposed by other groups. Closely co-evolved structural interaction and the dynamics of network evolution are used to explain the highly conserved core of protein interaction pathways, which exist across all divisions of life.

• 한국안전학회지
• /
• 제29권1호
• /
• pp.86-92
• /
• 2014

This paper provides an integrated view on human and system interaction in advanced and automated systems, which adopting computerized multi-functional artifacts and complicated organizations, such as nuclear power plants, chemical plants, steel and semi-conduct manufacturing system. As current systems have advanced with various automated equipments but human operators from various organizations are involved in the systems, system safety still remains uncertain. Especially, a human operator plays an important role at the time of critical conditions that can lead to catastrophic accidents. The knowledge on human error helps a risk manager as well as a designer to create and control a more credible system. Several human error theories were reviewed and adopted for forming the integrated perspective: gulf of execution and evaluation; risk homeostasis; the ironies of automation; trust in automation; design affordance; distributed cognition; situation awareness; and plan delegation theory. The integrated perspective embraces human error theories within three levels of human-system interactions such as affordance level, psychological logic level and trust level. This paper argued that risk management process should dealt with human errors by providing (1) reasoning improvement; (2) support to situation awareness of operators; and (3) continuous monitoring on harmonization of human system interaction. This approach may help people to understand risk of human-system interaction failure characteristics and their countermeasures.

• 로봇학회논문지
• /
• 제14권1호
• /
• pp.22-30
• /
• 2019

For effective human-robot interaction, robots need to understand the current situation context well, but also the robots need to transfer its understanding to the human participant in efficient way. The most convenient way to deliver robot's understanding to the human participant is that the robot expresses its understanding using voice and natural language. Recently, the artificial intelligence for video understanding and natural language process has been developed very rapidly especially based on deep learning. Thus, this paper proposes robot vision to audio description method using deep learning. The applied deep learning model is a pipeline of two deep learning models for generating natural language sentence from robot vision and generating voice from the generated natural language sentence. Also, we conduct the real robot experiment to show the effectiveness of our method in human-robot interaction.

• Journal of Mechanical Science and Technology
• /
• 제18권11호
• /
• pp.1900-1908
• /
• 2004

A human-friendly interactive system that is based on the harmonious symbiotic coexistence of human and robots is explored. Based on interactive technology paradigm, a robotic cane is proposed for blind or visually impaired travelers to navigate safely and quickly through obstacles and other hazards faced by blind pedestrians. Robotic aids, such as robotic canes, require cooperation between human and robots. Various methods for implementing the appropriate cooperative recognition, planning, and acting, have been investigated. The issues discussed include the interaction between humans and robots, design issues of an interactive robotic cane, and behavior arbitration methodologies for navigation planning.