• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권5호
• /
• pp.300-306
• /
• 2005

In this paper we present a guideline to evaluate how easy the use of personal robots is and how good their learning abilities are, based on the analysis of their built-in commands, user interfaces, and intelligences. Recently, we are living with robots that can be able to do lots of roles; cleaning, security, pets and education in real life. They can be classified as home robots, guide robots, service robots, robot pets, and so on. There we, however, no standards to evaluate their abilities, so it is not easy to select an appropriate robot when a user wants to buy it. Thus, we present, as a guideline that can be a standard for the evaluation of the personal robots, the standards by means of analyzing existing personal robots and results of the recent research works. We will, also, demonstrate how to apply the evaluation method to the cleaning robot as an example.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.59-64
• /
• 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 chose 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 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 it can learn the optimal policy if the agent can visit every state- action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem. we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL)as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2337-2341
• /
• 2005

This paper presents the target detection method using Support Vector Machines(SVMs) and the navigation system using behavior-based fuzzy controller. SVM is a machine-learning method based on the principle of structural risk minimization, which performs well when applied to data outside the training set. We formulate detection of target objects as a supervised-learning problem and apply SVM to detect at each location in the image whether a target object is present or not. The behavior-based fuzzy controller is implemented as an individual priority behavior: the highest level behavior is target-seeking, the middle level behavior is obstacle-avoidance, the lowest level is an emergency behavior. We have implemented and tested the proposed method in our mobile robot "Pioneer2-AT". Comparing with a neural-network based detection method, a SVM illustrate the excellence of the proposed method.

• 한국정보교육학회:학술대회논문집
• /
• 한국정보교육학회 2010년도 하계학술대회
• /
• pp.259-264
• /
• 2010

본 연구는 초등학생들이 창의성 및 문제해결력 향상을 위해 기존의 컴퓨터를 대신하여 로봇을 이용한 새로운 학습방법의 가능성을 탐색하기 위해 현장 교사들이 로봇교육에 대한 성향을 조사 분석하고 이를 기초로 교육과정과 교재를 개발하였다. 로봇교육을 통한 창의성 구성요소를 확인하고 가능성을 탐색하기 위해 초등학생 6학년을 대상으로 방과 후 학습시간에 학습시킨 후 결과산출물을 만들고 이를 평가하였다. 결과로서 초등학교에서 로봇이 창의적인 학습도구로 성공할 수 있는 가능성을 확인하게 되었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국내학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
• /
• pp.58-62
• /
• 1988

Recently many adaptive control schemes for the industrial robot manipulator have been developed. Especially, learning control utilizing the repetitive motion of robot and based on iterative signal synthesis attracts much interests. However, since most of these approaches excludes the boundness of the input torque supplied to the manipulator, its effectiveness may be limited and also the full dynamic capacity of the robot manipulator can not be utilized. To overcome the above-mentioned difficulties and meet the desired performance, we propose an approach which yields the effective learning control schemes in this paper. In this study, some stability conditions derived from applying the Lyapunov theory to the discrete linear time-varying dynamic system are established and also an optimization scheme considering the bounded input torque is introduced. These results are simulated on a digital computer using a three-joint revolute manipulator to show their effectiveness.

• 제어로봇시스템학회논문지
• /
• 제12권10호
• /
• pp.1029-1034
• /
• 2006

In this paper, the tracking control of an automatic pipe cutting robot, called APCROM, with a magnetic binder is studied. Using magnetic force APCROM, a wheeled robot, binds itself to the pipe and executes unmanned cutting process. The gravity effect on the movement of APCROM varies as it rotates around the pipe laid in the gravitational field. In addition to the varying gravity effect other types of nonlinear disturbances including backlash in the driving system and the slip between the wheels of APCROM and the pipe also cause degradation in the cutting process. To maintain a constant velocity and consistent cutting performance, the authors adopt a repetitive learning controller (MRLC), which learns the required effort to cancel the tracking errors. An angular-position estimation method based on the MEMS-type accelerometer is also used in conjunction with MRLC to compensate the tracking error caused by slip at the wheels. Experimental results verify the effectiveness of the proposed control scheme.

• 로봇학회논문지
• /
• 제16권1호
• /
• pp.35-40
• /
• 2021

As the robot industry develops, industrial automation uses industrial robots in many parts of the manufacturing industry. However, rigidity-based conventional robots have a disadvantage in that they are challenging to use in environments where they grab fragile objects or interact with people because of their high rigidity. Therefore, researches on soft robot have been actively conducted. The soft robot can hold or manipulate fragile objects by using its compliance and has high safety even in an atypical environment with human interaction. However, these advantages are difficult to use in dynamic situations and control by the material's nonlinear behavior. However, for the soft robot to be used in the industry, control is essential. Therefore, in this paper, real-time PD control is applied, and the behavior of the soft actuator is analyzed by providing various waveforms as inputs. Also, Iterative learning control (ILC) is applied to reduce errors and select an ILC type suitable for soft actuators.

• 정보처리학회논문지B
• /
• 제9B권2호
• /
• pp.139-146
• /
• 2002

로봇 축구 시뮬레이션 게임은 하나의 동적 다중 에이전트 환경이다. 본 논문에서는 그러한 환경 하에서 각 에이전트의 동적 위치 결정을 위한 새로운 강화학습 방법을 제안한다. 강화학습은 한 에이전트가 환경으로부터 받는 간접적 지연 보상을 기초로 누적 보상값을 최대화할 수 있는 최적의 행동 전략을 학습하는 기계학습 방법이다. 따라서 강화학습은 입력-출력 쌍들이 훈련 예로 직접 제공되지 않는 다는 점에서 교사학습과 크게 다르다. 더욱이 Q-학습과 같은 비-모델 기반의 강화학습 알고리즘들은 주변 환경에 대한 어떤 모델도 학습하거나 미리 정의하는 것을 요구하지 않는다. 그럼에도 불구하고 이 알고리즘들은 에이전트가 모든 상태-행동 쌍들을 충분히 반복 경험할 수 있다면 최적의 행동전략에 수렴할 수 있다. 하지만 단순한 강화학습 방법들의 가장 큰 문제점은 너무 큰 상태 공간 때문에 보다 복잡한 환경들에 그대로 적용하기 어렵다는 것이다. 이런 문제점을 해결하기 위해 본 연구에서는 기존의 모듈화 Q-학습방법(MQL)을 개선한 적응적 중재에 기초한 모듈화 Q-학습 방법(AMMQL)을 제안한다. 종래의 단순한 모듈화 Q-학습 방법에서는 각 학습 모듈들의 결과를 결합하는 방식이 매우 단순하고 고정적이었으나 AMMQL학습 방법에서는 보상에 끼친 각 모듈의 기여도에 따라 모듈들에 서로 다른 가중치를 부여함으로써 보다 유연한 방식으로 각 모듈의 학습결과를 결합한다. 따라서 AMMQL 학습 방법은 큰 상태공간의 문제를 해결할 수 있을 뿐 아니라 동적인 환경변화에 보다 높은 적응성을 제공할 수 있다. 본 논문에서는 로봇 축구 에이전트의 동적 위치 결정을 위한 학습 방법으로 AMMQL 학습 방법을 사용하였고 이를 기초로 Cogitoniks 축구 에이전트 시스템을 구현하였다.

• 전자공학회논문지B
• /
• 제33B권5호
• /
• pp.25-32
• /
• 1996

This paper will propose the direct adaptive learning control scheme based on adaptive control technique and intelligent control theory for a nonlinear system. Using the proposed learning control scheme, we will apply to on-line control an uncertain but for model perfect matching, it's structure condition is known. The effectiveness of the proposed control schem will be illustrated by simulations of a robot manipulator.

• 공학교육연구
• /
• 제18권3호
• /
• pp.3-12
• /
• 2015

The aim of this paper is to provide teacher awareness and the status of robot based instruction(RBI) by focusing on the school curriculum. To gather that information, we conducted a questionnaire survey composed of six items to 116 teachers who have had experiences on RBI. The questions are about the fit school year for RBI, the fit subjects for it, the possibility of applying it to regular subject, the fit students' learning levels for it, the fit learning styles for it and effective methods to apply it to regular subject teachers. The result is as follows: (1) RBI is suitable for fifth and sixth grade in elementary school and all grades in high school. (2) It is suitable for all regular subjects in all schools. (3) It is more effective for the students who have average learning level. (4) It fits into introverted students more than the other style of learners. (5) It is likely to be more effective in supporting of learning and understanding of the contents than merely assisting the teachers' instruction. (6) The teachers showed positive awareness on applying RBI to subject of creative activities. The results are significant in relation to the following two views. First, we can get the positive possibility in applying school curriculum using RBI. Second we can foresee that RBI will provide an innovative paradigm to school curriculum. In addition, the results of this paper can be used as preliminary information for developing models and programs on RBI.