• 전자공학회논문지CI
• /
• 제40권4호
• /
• pp.193-205
• /
• 2003

지능 제어, 통신, 컴퓨터 및 센서 기술, 영상 처리, 메카트로닉스 등과 같은 다양한 분야에서 로봇 축구 시스템에 대한 연구가 진행되고 있다. 그중 전략 연구는 대부분 공격 전략 연구에 치중하고 있으며, 점차 지능적인 공격 전략을 구현하는 방향으로 흘러가고 있다. 이에 따라 과거의 단순한 수비 전략으로는 완전한 수비가 불가능하게 되었다. 따라서, 지능적인 공격을 효율적으로 수비할 수 있는 수비 전략이 필요하며, 효율적인 수비를 위하여 공격자 로봇의 의도 추출이 필요하다. 본 논문에서는, 퍼지 최대 최소 신경망을 이용한 축구 로봇의 공격 의도 추출기를 설계하였다. 첫째로 축구 로봇 시스템에서의 의도를 정의하고 의도 추출에 대하여 설명한다. 다음으로 설계한 퍼지 최대 최소 신경망을 이용하여 설계한 축구 로봇의 의도 추출기에 대하여 설명한다. 퍼지 최대 최소 신경망은 패턴분류 방법 중의 하나로 온라인 적용, 짧은 학습 시간, 소프트 결정(soft decision) 등의 많은 장점을 갖고 있다. 따라서, 다이나믹한 환경을 가진 축구 로봇 시스템의 의도 추출에 적합하다. 이 의도 추출기는 상대 팀 로봇이 공격시 어떠한 상황에서 어떠한 행동을 할 것인가를 미리 알아내어 수비 시 이용할 수 있도록 하며, 학습을 통하여 의도 추출을 함으로써 상대 팀 경기를 보고 팀의 전략을 파악하는 전략 분석기로도 사용이 가능하다. 자체 제작한 3대3 로봇 축구 시뮬레이터를 이용하여 시뮬레이션을 하였으며, 학습을 함에 따라서 의도 추출률이 증가함을 확인할 수 있었다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제49권1호
• /
• pp.41-47
• /
• 2000

A better tracking performance can be achieved, if visual sensors such as CCD cameras are used in controling a robot manipulator, than when only relative sensors such as encoders are used. However, for precise visual servoing of a robot manipulator, an expensive vision system which has fast sampling rate must be used. Moreover, even if a fast vision system is implemented for visual servoing, one cannot get a reliable performance without use of robust and stable inner joint servo-loop. In this paper, we propose a dynamic control scheme for robot manipulators with eye-in-hand camera configuration, where a dynamic learning controller is designed to improve the tracking performance of robotic system. The proposed control scheme is implemented for tasks of tracking moving objects and shown to be robust to parameter uncertainty, disturbances, low sampling rate, etc.

• 로봇학회논문지
• /
• 제13권4호
• /
• pp.205-212
• /
• 2018

This paper deals with the paddle type end of arm tool for rescue robot instead of rescue worker in dangerous environments such as fire, earthquake, national disaster and defense. It is equipped at the dual arm manipulator of the rescue robot to safely lift up an injured person. It consists of the paddle for lifting person, sensors for detecting insertion of person onto the paddle, sensor for measuring the tilting angle of the paddle, and mechanical compliance part for preventing incidental injuries. The electronics is comprised of the DAQ module to acquire the sensors data, the control module to treat the sensors data and to manage the errors, and the communication module to transmit the sensors data. After optimally designing the mechanical and electronical parts, we successfully made the paddle type end of arm tool and evaluated its performance by using specially designed jigs. The developed paddle type end of arm tool is going to be applied to the rescue robot for performance verification through field testing.

• 한국군사과학기술학회지
• /
• 제27권4호
• /
• pp.474-484
• /
• 2024

Reinforcement learning, which are also studied in the field of defense, face the problem of sample efficiency, which requires a large amount of data to train. Transfer learning has been introduced to address this problem, but its effectiveness is sometimes marginal because the model does not effectively leverage prior knowledge. In this study, we propose a stochastic initial state randomization(SISR) method to enable robust knowledge transfer that promote generalized and sufficient knowledge transfer. We developed a simulation environment involving a cooperative robot transportation task. Experimental results show that successful tasks are achieved when SISR is applied, while tasks fail when SISR is not applied. We also analyzed how the amount of state information collected by the agents changes with the application of SISR.

• 한국자동차공학회논문집
• /
• 제22권3호
• /
• pp.25-32
• /
• 2014

There are many type vehicles in army. They are jeep and truck by basic type. Recently many countries are developing new conceptual military vehicles. And they try for export of those military vehicles to another countries. Also Korea Army is developing military tactical and combat vehicles, and considering various necessary factors for export. But as easing the cold war system tension and reducing of defense budget, decrease in quantity of military vehicles. We think this trend is accelerative. Therefore Government(Military) and defense industry make every effort to increasing sales and productions. In this study, I'll inquire '2013~2017 basic plan for defense industry promotion' for strengthen the power of international competitiveness, and then suggest the increasing method for productions of military vehicles.

• Journal of Electrical Engineering and Technology
• /
• 제9권1호
• /
• pp.352-362
• /
• 2014

In this paper, a fuzzy logic controller is designed for a DC motor which can be used for navigation control of mobile robots. These mobile robots can be used for agricultural, defense and assorted social applications. The robots used in these fields can reduce manpower, save human life and can be operated using remote control from a distant place. The developed fuzzy logic controller is used to control navigation speed and steering angle according to the desired reference position. Differential drive is used to control the steering angle and the speed of the robot. Two DC motors are connected with the rear wheels of the robot. They are controlled by a fuzzy logic controller to offer accurate steering angle and the driving speed of the robot. Its location is monitored using GPS (Global Positioning System) on a real time basis. IR sensors in the robot detect obstacles around the robot. The designed fuzzy logic controller has been implemented in a robot, which depicts that the robot could avoid obstacle as well as perform its operation efficiently with remote online control.

• 항공우주시스템공학회지
• /
• 제12권5호
• /
• pp.16-23
• /
• 2018

본 논문에서는 생체모방기술을 적용한 로봇제어방법에 대해 기술한다 물방개의 유영동작을 모방하고 발생시키기 위해 푸리에 최소자승기법을 적용하여 일반식을 정립하였다. 일반식의 계수의 값을 조정하여 관측된 물방개의 유영동작과 발생시킨 모방동작의 비교를 통해 제어 파라미터가 정의되었으며 각 파라미터들의 상관관계를 밝히고 이를 파라미터 공간상에 표현하여 다양한 생체모방 동작을 쉽게 발생시킬 수 있음을 확인하였다. 추가로, 생물체의 구조적인 장점을 반영한 로봇설계에 대해 간략히 소개하였고 제안한 생체모방 발생기법은 다양한 환경에서의 로봇시스템 개발에 적용 가능함을 확인하였다.

• ETRI Journal
• /
• 제29권2호
• /
• pp.189-200
• /
• 2007

This paper addresses the localization and navigation problem in the movement of service robots by using invisible two dimensional barcodes on the floor. Compared with other methods using natural or artificial landmarks, the proposed localization method has great advantages in cost and appearance since the location of the robot is perfectly known using the barcode information after mapping is finished. We also propose a navigation algorithm which uses a topological structure. For the topological information, we define nodes and edges which are suitable for indoor navigation, especially for large area having multiple rooms, many walls, and many static obstacles. The proposed algorithm also has the advantage that errors which occur in each node are mutually independent and can be compensated exactly after some navigation using barcodes. Simulation and experimental results were performed to verify the algorithm in the barcode environment, showing excellent performance results. After mapping, it is also possible to solve the kidnapped robot problem and to generate paths using topological information.

• 대한기계학회논문집A
• /
• 제26권2호
• /
• pp.357-364
• /
• 2002

A new chattering free sliding made control is proposed for robot manipulators. The control input is derived from the reaching law and the Lyapunov stability criteria, which is only composed of continuous terms. It has a chattering free characteristics and a concise farm. In implementing procedures, no change of equations is needed. Thus, it does not degrade the original merits of the sliding mode control. And it is applied to a 2-link SCARA robot manipulator. It is shown that the proposed control has good trajectory tracking performance compared with the PD control and the conventional sliding mode control which uses the boundary layer concept.

• 한국CDE학회논문집
• /
• 제22권2호
• /
• pp.162-171
• /
• 2017

Unmanned military vehicles (UMVs) are most commonly characterized as dealing with dull, dirty, and dangerous tasks with automation. Although most of the UMVs are designed to a high degree of autonomy, the human operator will still intervene in the robot's operation, and teleoperate them to achieve his or her mission. Thus, operator capacity, together with robot autonomy and user interface, is one of the most important design factors in the research and development of the UMVs. Further, communication may affect the operator task performance. In this paper, we analyze the operator performance and the communication effects on the operator performance by using the extended Petri nets, called OTSim nets. The OTSim nets was designed by the authors, being extended using pure Petri nets.