• The Journal of Korea Robotics Society
• /
• v.14 no.3
• /
• pp.157-162
• /
• 2019

The video game Tetris is one of most popular game and it is well known that its game rule can be modelled as MDP (Markov Decision Process). This paper presents a DQN (Deep Q-Network) based game agent for Tetris game. To this end, the state is defined as the captured image of the Tetris game board and the reward is designed as a function of cleared lines by the game agent. The action is defined as left, right, rotate, drop, and their finite number of combinations. In addition to this, PER (Prioritized Experience Replay) is employed in order to enhance learning performance. To train the network more than 500000 episodes are used. The game agent employs the trained network to make a decision. The performance of the developed algorithm is validated via not only simulation but also real Tetris robot agent which is made of a camera, two Arduinos, 4 servo motors, and artificial fingers by 3D printing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.635-637
• /
• 2016

The purpose of this study was to apply other programming tools such as robots parish. The robot was utilized for Lego Mindstorms NXT. Programming tools were used to block generic programming tools were used in the NXT-G, was used as a simulation programming tools MSRDS, mobile App Inventor is a programming tool (App Inventor). It can lead to interesting effects of learning and learning based on three programming tool above.

• Journal of information and communication convergence engineering
• /
• v.19 no.1
• /
• pp.54-60
• /
• 2021

Various digital devices were supplied throughout the Fourth Industrial Revolution. Accordingly, the importance of data processing has increased. Data processing significantly affects equipment reliability. Thus, the importance of data processing has increased, and various studies have been conducted on this topic. This study proposes a modified Gaussian filter algorithm based on a fuzzy membership function. The proposed algorithm calculates the Gaussian filter weight considering the standard deviation of the filtering mask and computes an estimate according to the fuzzy membership function. The final output is calculated by adding or subtracting the Gaussian filter output and estimate. To evaluate the proposed algorithm, simulations were conducted using existing additive white Gaussian noise removal algorithms. The proposed algorithm was then analyzed by comparing the peak signal-to-noise ratio and differential image. The simulation results show that the proposed algorithm has superior noise reduction performance and improved performance compared to the existing method.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.1
• /
• pp.67-73
• /
• 2023

As interest in underwater structures and ocean exploration increases, many researchers are proposing methods for modeling and controlling various remotely operated vehicles (ROVs). Recently, hybrid systems composed of an autonomous underwater vehicle and an ROV capable of remote control and autonomous navigation are being developed. In this study we introduce a method that models Ariari-aROV, an ROV consisting of five thrusters, and performs navigation. The proposed ROV can be controlled manually and by autonomous navigation when given a target point. An extended Kalman filter is utilized for sensor measurement correction for more precise navigation. The proposed method is verified through a simulation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1243-1248
• /
• 2022

A mobile platform that can robustly operate in unstructured environments such as construction sites is an essential problem for smart construction technology development. In this paper, we introduce a mobile robot platform that can be applied to the unstructured environment to support the collection of geographical information at construction sites. The proposed mobile platform is designed to cope with not only vertical slopes but also side slopes, and the performance of overcoming the step difference of the proposed platform was analyzed through simulation experiments.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.881-886
• /
• 1993

Fuzzy logic rule-based controller has many desirable advantages, which are simple to implement on the real time and need not the information of structure and dynamic characteristics of the system. Thus, nowadays, the scope of the application of the fuzzy logic controller becomes enlarged. But, if the controlled plant is a time-varying and nonlinear system, it is not easy to construct the fuzzy logic rules which usually need the knowledge of an expert. In this paper, an approach in which the logic control rules can be self-organized using genetic algorithm will be proposed and the effectiveness of the proposed method will be verified by computer simulation of the 2 d.o.f. planar robot manipulator.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.535-537
• /
• 2010

군집로봇은 어떤 작업을 수행하기 위해 여러 로봇이 함께 움직이게 된다. 이렇게 여러 로봇이 함께 작업을 수행하다 보면 로봇 간의 충돌을 피해야 할 경우가 발생한다. 각 로봇은 주어진 환경을 인식하고 모델링하며 로봇들 간에 충돌을 피하여 주어진 임무를 효과적으로 이행할 수 있게 하는 것이 이 연구의 핵심이다. 로봇 간 충돌을 효과적으로 해결하기 위해 충돌 전 다양한 위치와 다양한 방법으로 충돌을 피할 수 있도록 했다. 따라서 이 논문에서는 카메라 센서와 위치정보 통신을 이용한 방법을 통해 군집로봇간의 충돌 회피에 대해 연구하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.189-190
• /
• 2009

For applications involving the monitoring of large areas, dense sensor networks are not practical. For such applications, delay tolerant networks which consist of disconnected clusters of sensors that are visited periodically by a mobile robot are implemented. Because clock synchronization is critical to any data collection endeavor, and because the structure of DTNs is unique, this paper examines various clock synchronization algorithms as they apply to DTNs. A simulation tool was developed to examine and evaluate the RBS clock synchronization algorithm for DTNs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.267-268
• /
• 2009

많은 컴퓨터들이 기존의 단일코어 컴퓨터에서 벗어나 멀티코어를 장착한 컴퓨터로 변화하는 과정에서 기존의 단일 스레드 프로그래밍에서 다중처리가 중요해지는 세상이 되었다. 이러한 다중처리는 지능로봇 시뮬레이션 교육에 창의적 학습방법을 아주 잘 지원하고 있다. 지능로봇의 형태나 모형 그리고 센서 융합분야에서 동시처리는 중요한 역할을 하고 있다. 본 논문에서는 다중처리 기반 지능로봇 시뮬레이션 환경을 통해 창의적 학습방법에 관한 연구를 제안한다. 무한한 상상력과 창의성을 발휘하여 지능로봇의 모형 설계부터 직접 인공지능 프로그램까지 구현할 수 있는 방법을 소개한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.839-840
• /
• 2009

지능 로봇 분야의 발전은 빠른 속도로 성장하고 있으며 여러 환경에서 문제 해결을 할 수 있는 로봇에 대한 연구 또한 활발하게 이루어지고 있다. 지능 로봇을 구현하기 위해서는 주변 환경을 받아들이기 위한 센서 조작이 반드시 필요한데, 비용 면이나 생산량의 한계 등의 이유로 이러한 센서들을 일반 교육자, 학생이 접하기가 쉽지 않다. 본 논문에서는 3D 시뮬레이션 환경에서 다중 센서를 이용한 문제해결 로봇을 구현하는 개발 방법을 제안하고자 한다. 만약 3D 시뮬레이션 환경에서 손쉽게 센서의 생성과 조작이 가능하다면 지능 로봇 연구분야, 특히 지능로봇 교육분야에 큰 도움이 될 것으로 기대한다.