• 한국산업정보학회논문지
• /
• 제26권4호
• /
• pp.11-18
• /
• 2021

강화 학습을 통한 실내 자율주행을 위해 가상 환경과 실제 환경에서 학습을 병행하는 방법을 제안한다. 실제 환경에서만 학습을 진행했을 경우 80시간 정도의 소요 시간이 필요하지만, 실제 환경과 가상 환경을 병행하며 학습을 진행했을 경우 50시간의 소요 시간이 필요하다. 가상 환경과 실제 환경에서 학습을 병행하면서 빠른 학습으로 다양한 실험을 거쳐 최적화된 파라미터를 얻을 수 있는 이점이 있다. 실내복도 이미지를 이용하여 가상 환경을 구성한 후 데스크톱으로 선행학습을 진행하였고 실제 환경에서의 학습은 Jetson Xavier를 기반으로 다양한 센서와 연결하여 학습을 진행하였다. 또한, 실내복도 환경의 반복되는 텍스처에 따른 정확도 문제를 해결하기 위해 복도 벽의 아랫선을 강조하는 특징점 검출을 학습하여 복도 벽 객체를 판단하고 정확도를 높일 수 있었다. 학습을 진행할수록 실험 차량은 실내복도 환경에서 복도 중앙을 기준으로 주행하며 평균 70회의 조향명령을 통해 움직인다.

• 한국산학기술학회논문지
• /
• 제12권12호
• /
• pp.5486-5492
• /
• 2011

본 연구는 언제 어디서나 교육이 가능하도록 하는 유비쿼터스 컴퓨팅 기술의 개념에 기반하여 유비쿼터스 학습 환경의 모형을 제안한다. 유비쿼터스 학습 환경은 환경 친화적 학습 스킴이며, 지리학적으로 떨어져있는 환경에서 디지털 매체를 사용하여 학생의 학습을 지원하는 것이다. U-Learning 모형은 웹 기반의 E-Learning 시스템이며, 학습자들이 유비쿼터스 학습 환경및 시스템과의 상호작용을 통해 지식과 기술을 습득하도록 하는 것이다. 교육은 학생 중심이지만, 학생은 학습 프로세스를 인지하지 못할 수도 있다. 소스 데이터는 내재된 객체로 존재하게 되지만, 학생들은 학습하기 위해 아무것도 할 필요가 없으며, 학생들이 움직이거나 학습 환경에 접할 때 장비 및 임베디드 컴퓨터들은 통신을 통해 학습 자료를 제공하게 된다.

• Asia pacific journal of information systems
• /
• 제16권1호
• /
• pp.1-21
• /
• 2006

e-Learning can be seen as not only one of Internet-based information technologies which can provide education services but also one of teaching-learning methods which can implement self-directed learning. Thus, for evaluation of e-Learning effectiveness, both information-technology-based learning environment and learners' abilities in self-learning and computer-using should be considered simultaneously. This study suggests a research model for evaluating the effectiveness of e-Learning, which is theoretically based on information systems success model, constructivism and self-efficacy. The model is composed of three parts: effectiveness, learning environment, and learners' self-efficacy. Effectiveness is a part of dependent variables: satisfaction and academic performance. Learning environment and learners' self-efficacy can be considered as two sets of explanation variables for effectiveness. The former consists of learning management system, learning contents, and interactions that are provided bye-Learning and the latter means learners' self-regulated efficacy and computer self-efficacy. We show validity of the model empirically by surveying the college students who have experienced e-Learning. In result, most of all hypotheses suggested in this model are accepted in low significant level.

• 한국보육지원학회지
• /
• 제15권5호
• /
• pp.113-138
• /
• 2019

Objective: This study aimed to determine the effect of a teacher professional learning environment at workplace day care centers on the professionalism of beginning teachers and also to verify the mediating effects of the beginning teachers'work task motivation on that relationship. Methods: The participants were 129 new teachers currently employed at workplace day care centers. The Current Status for Professional Competence was used to measure the teachers' professionalism. The Professional Learning Environment Inventory assesses the professional learning environment of day care centers. To measure the work task motivation, the Work Tasks Motivation Scale for Teachers was used. Results: Firstly, positive relationships were identified between a professional learning environment and their intrinsic motivation and identified motivation. However, there were also negative relationships between the professional learning environment and their introjected motivation and amotivation. Secondly, this study partially verified the mediating effects of the beginning teachers'work task motivation on the relationship between the professional learning environment and teachers' professionalism. Conclusion/Implications: The relationship between the professional learning environment and the professionalism of beginning teachers was mediated by the teachers'own intrinsic motivations, identified motivations, and amotivation.

• Journal of the Korean Data and Information Science Society
• /
• 제17권2호
• /
• pp.345-353
• /
• 2006

Over the past few years, training professionals have become more pragmatic in their approach to technology-based media by using it to augment traditional forms of training delivery, such as classroom instruction and text-based materials. This trend has led to the rise of the term blended learning. Blended learning, an environment of e-learning, is a powerful learning solution created through a mixture of face-to-face and online learning delivered through a mix of media and superior learning experiences. In this article we design and implement an e-learning environment for blended learning. The environment focused on following factors: learning activity and participation of learners, and real time feedback of instructor.

• 지식경영연구
• /
• 제9권4호
• /
• pp.17-33
• /
• 2008

This study proposes University 2.0 as a model case of open, flexible, and distributed learning environment for higher education based on theoretical foundations and perspectives. As web 2.0 technologies emerge into the field of education, ways of generating and disseminating information and knowledge have been drastically changed. Professors are no longer the only source of knowledge. Students using internet often become prosumers of knowledge who search and access information through the web as well as publish their own knowledge using the web. A concept and framework of University 2.0 is introduced for implementing the new interactive learning paradigm with an open, flexible and distributed learning environment for higher education. University 2.0 incorporates online and offline learning environments with various educational media. Furthermore, it employs various learning strategies and integrates formal and informal learning through learning communities. Both instructors and students in University 2.0 environment are expected to be active knowledge generators as well as creative designers of their own learning and teaching.

• Educational Technology International
• /
• 제13권1호
• /
• pp.101-144
• /
• 2012

Students mostly precede their learning without any direct support of instructor in e-learning and mobile educational environment. Many useful strategies and tools to facilitate self-regulated learning behaviors in e-learning environment have been introduced, yet, the limit has been reached by only suggesting self-regulated strategies with visual information in the most researches. Accordingly, this research is intent to propose the sound design strategies that facilitate learner's self-regulated learning behaviors in mobile learning environment. To achieve the objective of the research, two research questions are presented. First, what are the sound design strategies that facilitate the self -regulated learning behaviors in mobile learning environment?. Second, what are the results of evaluating the developed sound design strategies in terms of facilitating self-regulated learning behaviors?. To solve these research questions, the literature reviews on characteristics of mobile learning, concepts and features of self-regulated learning and sound were done to establish the sound design strategies. Through formative research method targeting instructional designers, sound design strategies were modified and supplemented. The research to validate these was performed and to verify the effect of the derived sound design strategies, the usability test aimed at instructional designer and learners was conducted. The final sound design strategies through this research process were six general design strategies and the sixteen detailed strategies. This research is meaningful because this offers the basic research on sound information design which has been lacking and help upgrade the upper limit of instructional design which mainly focused on visual information in mobile learning environment that shows information in a small screen.

• 한국정보처리학회논문지
• /
• 제6권3호
• /
• pp.633-640
• /
• 1999

Reinforcement learning performs learning through interacting with trial-and-error in dynamic environment. Therefore, in dynamic environment, reinforcement learning method like Q-learning and TD(Temporal Difference)-learning are faster in learning than the conventional stochastic learning method. However, because many of the proposed reinforcement learning algorithms are given the reinforcement value only when the learning agent has reached its goal state, most of the reinforcement algorithms converge to the optimal solution too slowly. In this paper, we present COMREL(COMpressed REinforcement Learning) algorithm for finding the shortest path fast in a maze environment, select the candidate states that can guide the shortest path in compressed maze environment, and learn only the candidate states to find the shortest path. After comparing COMREL algorithm with the already existing Q-learning and Priortized Sweeping algorithm, we could see that the learning time shortened very much.

• 정보교육학회논문지
• /
• 제17권3호
• /
• pp.243-252
• /
• 2013

본 논문에서는 스마트러닝 환경에서 프로젝트 학습을 적용하여 프로젝트 학습 전략 및 특징을 분석하였다. 스마트러닝 환경은 기존의 이러닝 환경과 다르며, 이에 따라 프로젝트 학습 전략도 차별화가 필요하다. 본 연구에서는 스마트러닝 환경에서 초등학생을 대상으로 프로젝트 학습을 실시한 후, 설문조사 및 관찰, 인터뷰를 통하여 기존의 프로젝트 학습과의 차이점, 교육특징 및 시사점을 도출하였다. 나아가 스마트러닝 환경에서 프로젝트 학습 만족도에 영향을 주는 요인이 무엇인지 분석하였다. 연구결과, 스마트러닝 환경에서의 프로젝트 학습은 기존의 프로젝트 학습과 기술과 기기 측면, 소프트웨어, 학습참여 측면에서 차이가 있다고 인식되었다. 또한 스마트 환경에서 프로젝트 학습 만족도에 영향을 주는 요인은 기술과 기기, 상시성이 유의미한 요인으로 확인되었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.149.5-149
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent´s dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless ...