• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.800-803
• /
• 2020

실 환경 로봇에 강화학습을 적용하기 위해서는 가상 환경 시뮬레이션이 필요하다. 그러나 가상 환경을 구축하는 플랫폼은 모두 다르고, 학습 알고리즘의 구현에 따른 성능 편차가 크다는 문제점이 있다. 또한 학습을 적용하고자 하는 대상이 실세계의 하드웨어 사양이 낮은 스마트 로봇인 경우, 계산량이 많은 학습 알고리즘을 적용하기는 쉽지 않다. 본 연구는 해당 문제를 해결하기 위해 Unity3D에서 제공하는 강화학습 프레임인 ML-Agents 모듈을 사용하여 실 환경의 저사양 스마트 로봇에 장애물을 회피하고 탐색하는 모델의 강화학습을 적용해본다. 본 연구의 유의점은 가상 환경과 실 환경의 유사함과 일정량의 노이즈 발생 처리이다. 로봇의 간단한 행동은 원만하게 학습 및 적용가능함을 확인할 수 있었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.5
• /
• pp.712-717
• /
• 2008

In swarm robot systems, each robot must act by itself according to the its states and environments, and if necessary, must cooperate with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, reinforcement learning method with SVM based on structural risk minimization and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. By distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning that basis of SVM is adopted in this paper.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.35-41
• /
• 2018

The Q-learning algorithm based on reinforcement learning is useful for learning the goal for one behavior at a time, using a combination of discrete states and actions. In order to learn multiple actions, applying a behavior-based architecture and using an appropriate behavior adjustment method can make a robot perform fast and reliable actions. Q-learning is a popular reinforcement learning method, and is used much for robot learning for its characteristics which are simple, convergent and little affected by the training environment (off-policy). In this paper, Q-learning algorithm is applied to a lamp robot to learn multiple behaviors (human recognition, desk object recognition). As the learning rate of Q-learning may affect the performance of the robot at the learning stage of multiple behaviors, we present the optimal multiple behaviors learning model by changing learning rate.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.191-194
• /
• 2011

본 연구에서는 Atmel사의 AVR 마이크로프로세서에 적합하게 개발된 Java 바이트코드 인터프리터인 NanoVM을 자체 개발한 마이크로로봇에 이식하여 Java 언어 전용 로봇을 구현하였다. 따라서 마이크로프로세서의 구조와 회로를 모르는 학생들도 로봇을 프로그래밍하면서 Java 언어를 효율적으로 학습할 수 있다. 더욱이 최근 학생들의 프로그래밍언어 학습 능력이 떨어지면서 컴퓨터 관련학과의 프로그래밍언어 교육이 많은 어려움을 겪고 있다. 따라서 학생들의 프로그래밍언어 학습 동기를 부여하고 창의 공학적 프로그래밍언어 교육프로그램의 도입이 필요한 시점에서 본 연구에서 개발한 Java 로봇은 많은 기여를 할 것으로 기대된다.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.6
• /
• pp.23-32
• /
• 2005

Dolittle is a educational programming language that helps students learning principles and concepts of computer science with programming. Learning programming with robot improve learning achievements robot motivate to be interest with programming. However, Dolittle robot programming is a different from Dolittle programming in process of interpretation and execution mechanism. Therefore, students have virtually to learn two languages to control robot and it would reduce the worth of Dolittle as educational programming language. In order to solve this problem, we tried to Unify Dolittle and robot control language using parser that Dolittle program with turtle object convert robot program. But this try couldn't overcome completely this problem because attributes of turtle object is different from robot. In this research we unified Dolittle programming and Dolittle robot programming as a way of adding new robot object in dolittle standard object group. it would improve educational effect of learning programming with robot in Dolittle.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.164-170
• /
• 2004

This paper proposes a Distributed Autonomous Robotic System(AIS) based on Artificial Immune System(AIS) and Distributed Genetic Algorithm(DGA). The behaviors of robots in the system are divided into global behaviors and local behaviors. The global behaviors are actions to search tasks in environment. These actions are composed of two types: dispersion and aggregation. AIS decides one among above two actions, which robot should select and act on in the global. The local behaviors are actions to execute searched tasks. The robots learn the cooperative actions in these behaviors by the DGA in the local. The proposed system is more adaptive than the existing system at the viewpoint that the robots learn and adapt the changing of tasks.

• Journal of The Korean Association of Information Education
• /
• v.12 no.2
• /
• pp.195-202
• /
• 2008

The programming learning by using a robot may be one of the most appropriate learning methods for enabling students to experience the creative learning of future society by avoiding the existing stereotyped style educational environment, and understand and improve algorithm which is the basic fundamental of mathematics and science. This study proposed four types of items of errors which may occur during robot programming by elementary school students, and made elementary school students in the fifth and sixth grades learn robot programming after developing the curriculum for the robot programming. Then, the study collected and classified errors that had occurred during the process of learning, and conducted a comparative analysis of computer-based programming language which had been previously studied. This study identified that robot programming in elementary school was shown superior to existing computer-based programming language as a creative learning method and tool through the field experience.

• Journal of The Korean Association of Information Education
• /
• v.16 no.4
• /
• pp.419-427
• /
• 2012

This paper presents the effect of a interactive learning experience and student's response to technological components We develop the interactive learning environment and learning model in lessons relying on educational robots and augmented reality in the school classroom. The developed learning model is based on the problem-based learning model. The experiments of the study conduct with 18 students, the $5^{th}$ and $6^{th}$ graders of an elementary school for 8 weeks using developed system. We find out the interactive learning experiences have an influence on the creative ability of children. We know that students who scored lower on the school exam scored higher on the score of creativity compared to top students through educational robots and augmented reality.

• Journal of The Korean Association of Information Education
• /
• v.13 no.2
• /
• pp.205-214
• /
• 2009

The vocal language which is a symbolic vocal language described external sounds or expressed shape of things in nature, phenomenon, movement, shape of state provided images which can be envisioned in minds and created the mood for the whole writings. As the instructive ways of symbolic vocal language, the activities which refrain one-way translation for lexicon definition and stimulate the thoughts of students and interesting activities such as songs and comic books which students can understand by themselves are needed. Therefore, in this study, these symbolic vocal language is to be developed as the contents of robot for Symbolic Vocal language learning activities and after study activities, the possibility of using robot for education is to be reviewed, comparing changes in definitive areas and achievement after study activities. After the Symbolic Vocal language learning activities using robot and computer, as results of testing three achievement types of words simulated sound, shape, and movement, in study on words simulating sound and shape there was no significant difference. But The study activities simulating words used robot showed significant difference in terms of interest, confidence, and understanding.

• Proceedings of the KAIS Fall Conference
• /
• 2009.12a
• /
• pp.144-147
• /
• 2009

본 연구에서는 21세기 지식정보사회에 학생들의 창의력 향상을 위하여 MSRDS에서 제공하는 에디터인 VPL(Visual Programming Language)를 이용한 로봇 프로그래밍 학습이 창의력에 미치는 효과를 연구하였다. VPL은 로봇 애플리케이션 개발을 프로그래머가 아닌 학생들도 쉽게 사용할 수 있도록 MSRDS에서 제공하는 프로그램이며, 이를 시뮬레이션과 연결시켜 로봇 하드웨어가 없이 손쉽게 학습을 할 수 있게 하였다. 이를 위하여 VPL에서 사용하는 기본 Activity를 이용하여 프로그래밍의 구문을 자연스럽게 학습할 수 있는 수업 내용을 개발하였으며, 연구 대상은 충청남도 B군에 위치한 B공고 3학년의 컴퓨터응용관련 학과 1개반을 대상으로 C언어를 이용한 기존의 마이크로 장비 프로그래밍 수업과 VPL을 이용한 로봇 프로그래밍 수업을 상호 비교하려고 한다. 이 연구에서는 VPL을 통하여 손 쉽게 프로그래밍을 하고 흥미가 유발되어 자신이 생각한 대로 로봇의 동작을 구현하는 과정에서 자연스럽게 문제해결능력이 신장된 것을 확인하고자 한다.