• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권5호
• /
• pp.363-369
• /
• 2010

데모-기반 학습은 사용자가 직접 작업을 시연함으로써 로봇에게 쉽게 새로운 작업지식을 가르칠 수 있다는 장점이 있다. 하지만 기존의 많은 데모-기반 학습법들은 상태공간과 정책들을 표현하기 위해 속성-값 벡터 모델을 이용하였다. 속성-값 벡터 모델의 제한성으로 인해, 이들은 학습과정의 효율성도 낮고 학습된 정책의 재사용성도 낮았다. 본 논문에서는 기존의 속성-값 모델 대신 관계적 모델을 이용하는 새로운 데모-기반 작업 학습법을 제안한다. 이 방법에서는 사용자 데모 기록에서 추출한 훈련 예들에 관계적 개체-기반 학습법을 적용함으로써, 동일 작업영역내의 다른 유사한 작업들에도 활용하기 용이한 관계적 개체-기반 정책을 유도한다. 이 관계적 정책은 (상태, 목표) 쌍으로 표현되는 임의의 한 상황에 대해 이것에 대응하는 하나의 실행동작을 결정해주는 역할을 한다. 본 논문에서는 데모-기반 관계적 정책 학습법에 대해 자세히 소개한 후, 로봇 시뮬레이터를 이용한 실험을 통해 이 학습법의 효과를 분석해본다.

• 로봇학회논문지
• /
• 제17권1호
• /
• pp.40-47
• /
• 2022

A reward function suitable for a task is required to manipulate objects through reinforcement learning. However, it is difficult to design the reward function if the ample information of the objects cannot be obtained. In this study, a demonstration-based object manipulation algorithm called stochastic exploration guided by demonstration (SEGD) is proposed to solve the design problem of the reward function. SEGD is a reinforcement learning algorithm in which a sparse reward explorer (SRE) and an interpolated policy using demonstration (IPD) are added to soft actor-critic (SAC). SRE ensures the training of the critic of SAC by collecting prior data and IPD limits the exploration space by making SEGD's action similar to the expert's action. Through these two algorithms, the SEGD can learn only with the sparse reward of the task without designing the reward function. In order to verify the SEGD, experiments were conducted for three tasks. SEGD showed its effectiveness by showing success rates of more than 96.5% in these experiments.

• 패션비즈니스
• /
• 제26권1호
• /
• pp.105-118
• /
• 2022

This study investigated the effective pedagogical strategies for sewing by examining the efficacy of sewing videos as supplemental learning materials and demonstration tools. Sewing videos were created for face-to-face apparel construction courses, and students' opinions on sewing videos as an educational tool were collected. Videos with subtitles were offered to Apparel Construction Course 1, whereas videos with narration and subtitles were offered to Apparel Construction Course 2. As "supplemental learning materials," students rated videos as more effective for learning and satisfying than "documents with text and images." The effectiveness and satisfaction scores for Apparel Construction Course 2 were significantly higher than those for Apparel Construction Course 1. Furthermore, videos were utilized significantly more than documents, and most students preferred videos over documents. The main benefits of videos as supplemental learning materials were repetitive learning at the learner's convenience and the detailed presentation of the sewing process. Students regarded narration as more effective and satisfying than subtitles. Narrations were expected to be offered along with subtitles. As "demonstration tools," students rated videos as more effective for learning and satisfying than traditional "sewing samples." Students preferred "demonstration with videos" to "demonstration with sewing samples." The main benefits of video demonstration were a close-up view, presentation of the entire sewing process, and shorter wait time without the need for group teaching. Students wanted more sewing videos and narrations to be offered, and various sewing machine feet to be used in the videos. Educational methods for sewing were suggested based on student opinions.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.485-486
• /
• 2019

Simulated driving behavior is an important aspect of realistic simulation systems. To simulate natural driving behavior, this paper proposes an imitation learning method based on active learning that combines demonstration and experience. Driving demonstrations are collected from human drivers in a driving simulator. A driving behavior policy is learned from these demonstrations. The driving demonstration dataset is augmented with new demonstrations that the original demonstrations did not contain, in the form of behaviors from another driving behavior policy learned from experience. The final driving behavior policy is learned from an augmented demonstration dataset.

• Journal of Information Processing Systems
• /
• 제8권3호
• /
• pp.409-420
• /
• 2012

The decision-making by agents in games is commonly based on reinforcement learning. To improve the quality of agents, it is necessary to solve the problems of the time and state space that are required for learning. Such problems can be solved by Macro-Actions, which are defined and executed by a sequence of primitive actions. In this line of research, the learning time is reduced by cutting down the number of policy decisions by agents. Macro-Actions were originally defined as combinations of the same primitive actions. Based on studies that showed the generation of Macro-Actions by learning, Macro-Actions are now thought to consist of diverse kinds of primitive actions. However an enormous amount of learning time and state space are required to generate Macro-Actions. To resolve these issues, we can apply insights from studies on the learning of tasks through Programming by Demonstration (PbD) to generate Macro-Actions that reduce the learning time and state space. In this paper, we propose a method to define and execute Macro-Actions. Macro-Actions are learned from a human subject via PbD and a policy is learned by reinforcement learning. In an experiment, the proposed method was applied to a car simulation to verify the scalability of the proposed method. Data was collected from the driving control of a human subject, and then the Macro-Actions that are required for running a car were generated. Furthermore, the policy that is necessary for driving on a track was learned. The acquisition of Macro-Actions by PbD reduced the driving time by about 16% compared to the case in which Macro-Actions were directly defined by a human subject. In addition, the learning time was also reduced by a faster convergence of the optimum policies.

• 대한건축학회논문집:계획계
• /
• 제36권3호
• /
• pp.49-58
• /
• 2020

Based on Merrill's instructional theory, this study pursued to develop a demonstration-based architectural design class operation model for the 3^rd year undergraduate students taking a Spring semester design studio class. The model was designed and used particularly to improve architectural thinking abilities of under-motivated learners. Learning effects of the model were examined based on the preliminary data obtained for 3 consecutive years, 2017 through 2019. A total of 52 students were participated in the class and observed by the instructor. Once developed, the model has been continually updated and improved based on results of each class operation. Five types of demo. were used in the model. First, direct contacts of the instructor with under-motivated learners were turned out to be the most preferred demo(demo. 4), while watching and listening of the demo(demo.3) between the instructor and motivated learners taking place in class was ranked at the second place. Belief of under-motivated learners on the instructor as a professional should be highly valued for improving their architectural thinking abilities. Second, motivated peers' direct help for under-motivated ones was placed in the third rank. Social attitudes of under-motivated learners towards accepting motivated ones' helps were determined the particular demo's appropriateness. Third, a set of guidelines for operating the model in undergraduate design studio classes were developed and suggested.

• 패션비즈니스
• /
• 제24권6호
• /
• pp.135-147
• /
• 2020

This study explored students' online fashion studio class experiences, and investigated the factors affecting their class satisfaction. An online survey of college students who were enrolled in online studio classes within apparel and fashion-related departments during the spring of 2020 was conducted in June 2020. Responses from a total of 213 participants were included in the final data. Respondents rated lecture clips as the most useful, followed by teacher demonstration and feedback, PowerPoint (PPT) supplements, and Q&As. Frequently mentioned areas of improvement were online platform stability and video quality. Many respondents also stated that more streamlined teacher-student communication channels, immediate and meticulous teacher feedback, the adoption of course contents developed specifically for an online environment, and provisions for equipment usage would be desirable. Student satisfaction of an online fashion design studio class was significantly affected by teaching presence, social presence, online learning system stability, perceived usefulness of teacher's demonstration, and affective response toward COVID-19. Students satisfaction of an online garment construction studio class was significantly affected by teaching and social presence, online learning system stability, and perceived usefulness of teacher's demonstration. Based on these findings, we recommend developing teaching contents and methods that allow students to feel included in class and establish an online system with various functions to enhance the sense of social connection that can enable two-way communication.

• 한국정밀공학회지
• /
• 제14권4호
• /
• pp.46-55
• /
• 1997

This paper presents the development of intelligent performance management of computer communication networks for larger-scale integrated systems and the demonstration of its efficacy using computer simula- tion. The innermost core of the performance management is based on fuzzy set theory. This fuzzy perfor- mance manager has learning ability by using principles of neuro-fuzzy model, neuralnetwork, genetic algo- rithm(GA). Two types of performance managers are described in this paper. One is the Neuro-Fuzzy Per- formance Manager(NFPM) of which learning ability is based on the conventional gradient method, and the other is GA-based Neuro-Fuzzy Performance Manager(GNFPM)with its learning ability based on a genetic algorithm. These performance managers have been evaluated via discrete event simulation of a computer network.

• 한국콘텐츠학회논문지
• /
• 제19권3호
• /
• pp.466-474
• /
• 2019

본 연구는 '교육방법 및 교육공학' 수업에서 중등예비교사에게 요구되는 창의역량 강화와 학업도전 변화를 확인하는데 목적이 있다. 이를 위해 중등예비교사 94명이 한 학기 동안 융합수업지도안 작성 및 수업시연으로 진행되는 프로젝트 학습에 참여하였다. 설문지는 지은림, 주언희(2012)가 개발한 창의적 인재 역량측정도구와 배상훈 외(2015)의 학부교육 실태조사(K-NSSE)의 학업도전 사전-사후 설문을 실시하였다. 데이터 분석은 IBM SPSS 18.0 프로그램을 이용하여 대응표본 t 검정을 수행하였다. 연구결과는 다음과 같다. 창의역량에서는 '고차적 사고력', '문제해결능력', '호기심', '감수성', '과제집착력', '사회 가치추구', '협동 및 배려'가 유의미하였다. 학업도전에서는 '고차원 학습'과 '학습전략'이 유의미하였다. 이를 바탕으로 융합교육, 융합수업을 일반화하여 수업하기 위해서는 다양한 융합수업설계, 지도안 작성, 실천연구와 반복적인 융합수업의 효과를 검증하며 수정 보완 과정의 필요성에 대한 시사점을 논의하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 춘계학술대회
• /
• pp.327-331
• /
• 2018

본 연구는 대학생들의 SW 교육 핵심역량 중 컴퓨팅 사고력을 신장시키기 위해 역량 교수 학습 모델을 설계하였다. 사전에 소프트웨어 코딩 경험이 없는 학습자의 역량을 분석하고 기존의 SW 중심 교수 학습 5가지 모델 중 시연 중심 모델(DMM)과 개발 중심 모델(DDD) 그리고 CT 요소 중심 모델(DPAA) 등을 재구성하고 실생활 문제를 해결 및 컴퓨팅 사고력을 키우기 위한 Unplugged 활동과 Bebras Challenge 컴퓨팅 사고력 평가 도구 등을 면밀히 분석하여 역량 교수 학습 모델인 UDDPAAP (Unplugged-Demonstration-Decomposition-Pattern Recognition-Abstraction-Algorithm-Progrmming)을 설계하였다. Unplugged 활동 중 일부분을 대학생들 수업에 적합하게 변형하고, Bebras Challenge 컴퓨팅 사고력 평가 도구에서 제시하는 문제를 선별한 후 기존의 교수 학습 모델에 적용하였다. 연구의 효과를 검증하기 위해 코딩 경험이 없는 대학교 1학년 학생들에게 SW 교육 및 컴퓨터 정보 소양 교육 경험에 따른 컴퓨팅 사고력과 자신감 등의 사전 검사를 하고 UDDPAAP 교수 학습 모델을 적용하여 수업을 진행한 후 사후 검사를 하였다. 연구 결과 UDDPAAP 교수 학습 모델을 통해 SW 교육을 경험한 학생들의 컴퓨팅 사고력 관련 역량이 향상됨을 알 수 있었다.