• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.1044-1046
• /
• 2022

'22년 중대재해처벌법과 항만안전특별법이 본격 시행되었다. 이에 대비하기 위하여 본 논문에서는 위험물 컨테이너에서 발생하는 안전사고를 사전에 방지하는 지능형 컨테이너 및 청소 로봇을 제안한다. 지능형 컨테이너 및 청소 로봇은 다음과 같은 기능을 수행한다. 첫째, 유해물질 감지 센서와 산소 센서 등을 통해 컨테이너 상태를 실시간으로 관리한다. 둘째, 유해물질 유출 및 산소 농도가 부족한 경우 위험 컨테이너로 변경 관리한다. 셋째, 컨테이너 내부 유해물질 청소를 위해 로봇을 호출하고 지능형 청소 로봇은 방제약품과 흡착포를 통해 컨테이너 내부를 청소한다. 넷째, 위험 컨테이너는 자동문 개폐관리 기능을 통해 유해물질 청소 완료 전까지 문을 폐쇄하여 안전사고를 방지한다. 본 논문은 제시한 기능을 통해 위험물 컨테이너에서 발생하는 작업자 질식사 등의 사고를 감소시키는 것을 목표로 한다.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.1
• /
• pp.39-44
• /
• 1996

In this paper, adaptive controller with switching action is designed for rigid body robot manipulators to ensure the uniform stability of the manipulator system without a priori knowledge of the unmodeled dynamics. It will be shown that the parameter estimates are bounded independent of the other closed-loop signals boundedness, and also shown that the tracking error belongs to the normalized error bound via mathematical analisys. The robustness and performance of the proposed adaptive controller is investigated for the two-link direct drive manipulator actuated by VRM(Variable Reluctance Motor).

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• 한국정보교육학회:학술대회논문집
• /
• 2010.08a
• /
• pp.9-13
• /
• 2010

Supported by the Ministry of Knowledge Economy, this research explored the potentiality of the use of hands-on robots in elementary school curriculum. On the basis of the analysis of prior research, we defined the meaning and the characteristics of hands-on robots. The priority was given to the development of lesson plans in attempting to activate the use of robots in elementary school curriculum. Also considering the difficulties faced in schools and the characteristics of robot-based instruction, we classified hands-on robots according to the shape and the goal of use.

• Journal of Advanced Navigation Technology
• /
• v.14 no.4
• /
• pp.553-561
• /
• 2010

This paper proposed the face tracking method which can be effectively applied to the robot's vision system. The proposed algorithm tracks the facial areas after detecting the area of video motion. Movement detection of video images is done by using median filter and erosion and dilation operation as a method for removing noise, after getting the different images using two continual frames. To extract the skin color from the moving area, the color information of sample images is used. The skin color region and the background area are separated by evaluating the similarity by generating membership functions by using MIN-MAX values as fuzzy data. For the face candidate region, the eyes are detected from C channel of color space CMY, and the mouth from Q channel of color space YIQ. The face region is tracked seeking the features of the eyes and the mouth detected from knowledge-base. Experiment includes 1,500 frames of the video images from 10 subjects, 150 frames per subject. The result shows 95.7% of detection rate (the motion areas of 1,435 frames are detected) and 97.6% of good face tracking result (1,401 faces are tracked).

• Journal of KIISE:Software and Applications
• /
• v.37 no.5
• /
• pp.363-369
• /
• 2010

Demonstration-based learning has the advantage that a user can easily teach his/her robot new task knowledge just by demonstrating directly how to perform the task. However, many previous demonstration-based learning techniques used a kind of attribute-value vector model to represent their state spaces and policies. Due to the limitation of this model, they suffered from both low efficiency of the learning process and low reusability of the learned policy. In this paper, we present a new demonstration-based learning method, in which the relational model is adopted in place of the attribute-value model. Applying the relational instance-based learning to the training examples extracted from the records of the user demonstrations, the method derives a relational instance-based policy which can be easily utilized for other similar tasks in the same domain. A relational policy maps a context, represented as a pair of (state, goal), to a corresponding action to be executed. In this paper, we give a detail explanation of our demonstration-based relational policy learning method, and then analyze the effectiveness of our learning method through some experiments using a robot simulator.

• The Journal of Korean Association of Computer Education
• /
• v.16 no.6
• /
• pp.33-43
• /
• 2013

Compiler and language implementation courses have long been recognized as an important subject in Computer Science curricula. It is because not only the knowledge for a compiler plays important roles in understanding programming languages and systems but compiler technologies can be used in many applications. However it requires much effort to teach effectively it due to limited resources and time restriction. We present a compiler teaching model using Edu-IDEC which is a development environment of educational compilers. Edu-IDEC is a tool on the robot platform. It uses the Eclipse plug-ins and has functions like compiler developing tools, a reference compiler, visualization tool of syntax tree, visualization tool of object language, NXT robot controllers, and its simulator. We also present the evaluation results for our model by applying it to an actual class.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.6
• /
• pp.81-89
• /
• 2010

The purpose of this research is to verify the influence of STEM integrate education using educational robots on improvement of the level of attitude towards Mathematics. The following hypothesis was formulated in order to achieve this purpose: There will be a meaningful difference in the level of attitude towards Mathematics between elementary school students educated by STEM integrated education with robots and by the traditional method of teaching Mathematics. To prove this hypothesis, 56 of first grade students were tested under the nonequivalent control group in the pretest-posttest designs. As a result of the study, it is showed that STEM integrated education has a positive effect on promoting the level of elementary school students' attitude towards Mathematics. Therefore, we need the instructional activities which can combine the knowledge gained from a variety of curriculum with activities by using educational robots.

• The KIPS Transactions:PartA
• /
• v.18A no.5
• /
• pp.165-176
• /
• 2011

In this paper, we show how a curriculum using LEGO MINDSTORMS NXT robot based ROBOTC for undergraduate students has been developed, and we analyze the educational effect of the curriculum. The curriculum is composed of basic knowledge learning, practice with basic robots, practice with advanced robots, and creative design and implementation of robots. During the three year period since 2009, educational achievement has been analyzed by surveys for 6 classes, 94 students. According to the analysis, the curriculum has highly motivated the students and made them to achieve effectively our educational and academic goals. Also, we observe that the curriculum helped the students to improve their creativity and the problem solving skill, and that the students were autonomously and deeply involved in the homework and the term projects, which made them be very cooperative. Finally, the intensive practice with ROBOTC programming is shown to help students to improve their programming ability of C language.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.4
• /
• pp.37-48
• /
• 2009

Household service robots should be able to provide their users with a variety of temporal reasoning services. In this paper, we propose an effective way of developing such temporal reasoning services using a domain-independent AI planner. Developing temporal reasoning services with a domain-independent AI planner, we have to address both the knowledge engineering problem of how to represent various real-world temporal constraints in a planning domain definition language, and the system design problem of how to realize the interface between the AI planner and the service consumer. In this paper, we introduce an example scenario and a set of typical temporal constraints for a household service robot, and then present how to represent them in the standard planning domain definition language. We also explain how to implement a service agent based on an AI planner in order to develop and provide new services efficiently.