• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(3)
• /
• pp.127-130
• /
• 2002

Human's brain action can divide by recognition and intelligence. recognition is sensing voice, image and smell and Intelligence is logical judgment, inference, decision. To this concept, Define function of cerebral cortex, and apply the result. Current expert system is lack, that reasoning by cerebral cortex and thalamus, hoppocampal and so on. In this paper, With human's brain action, wish to embody human's action artificially Embody brain mechanism using Modular Neural Network, Applied this result to snake robot.

• 한국정밀공학회지
• /
• 제29권9호
• /
• pp.978-985
• /
• 2012

Starfish are a critical problem for fishermen since they eat every farming product including shellfish. The number of starfish is increasing dramatically because they have no natural enemy underwater. We consider the concept of capturing starfish using a semi-autonomous robot. A new underwater robot design to capture starfish is proposed using cooperation between humans and the robot. A requirements list for the robot is developed and two conceptual designs are proposed. Each robot is designed as a modular platform. The kinematic and dynamic performance of each robot is analyzed and compared. This study is a starting point for developing a starfish capture robot and designing underwater robots for other applications. In the near future, a prototype will be assembled and tested in a marine environment.

• 제어로봇시스템학회논문지
• /
• 제11권4호
• /
• pp.314-321
• /
• 2005

In this paper an intelligence embedding quadruped pet robot is described. It has 15 degrees of freedom and consists of various sensors such as CMOS image, voice recognition and sound localization, inclinometer, thermistor, real-time clock, tactile touch, PIR and IR to allows owners to interact with pet robot according to human's intention as well as the original features of pet animals. The architecture is flexible and adopts various embedded processors for handling sensors to provide modular structure. The pet robot is also used for additional purpose such like security, gaming visual tracking, and research platform. It is possible to generate various actions and behaviors and to download voice or music files to maintain a close relation of users. With cost-effective sensor, the pet robot is able to find its recharge station and recharge itself when its battery runs low. To facilitate programming of the robot, we support several development environments. Therefore, the developed system is a low-cost programmable entertainment robot platform.

• 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.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.496-499
• /
• 1999

This paper describes a medular neural network(MNN) for a vision system which tracks a given object using a sequence of images from a camera unit. The MNN is used to precisely recognize the given robot endeffector and to minize the processing time. Since the robot endeffector can be viewed in many different shapes in 3-D space, a MNN structure, which contains a set of feedforwared neural networks, co be more attractive in recognizing the given object. Each single neural network learns the endeffector with a cluster of training patterns. The training patterns for a neural network share the similar charateristics so that they can be easily trained. The trained MNN is less sensitive to noise and it shows the better performance in recognizing the endeffector. The recognition rate of MNN is enhanced by 14% over the single neural network. A vision system with the MNN can precisely recognize the endeffector and place it at the center of a display for a remote operator.

• 한국실천공학교육학회논문지
• /
• 제4권2호
• /
• pp.162-170
• /
• 2012

로봇이 수많은 작업을 수행하고 목표를 향해서 진행하기 위해서는 무엇보다 위치를 인식하는 것이 대단히 중요하다. 본 논문에서는 랜드 마크와 센서 네트워크 환경하에서 주행하는 로봇의 위치를 구별할 수 있는 위치 인식시스템을 제안한다. 전적으로 기본 지능형 로봇에 위치 인식 시스템과 환경 센서 모듈을 부가하여 구현하고, 이를 컴퓨터 시뮬레이션을 통해서 제안된 알고리즘이 합당함을 검증한다.

• Journal of Information Processing Systems
• /
• 제8권3호
• /
• pp.471-482
• /
• 2012

For disaster exploration and surveillance application, this paper aims to present a novel application of a multi-robot agent based on WSN and to evaluate a multi-hop communication caused by the robotics correspondingly, which are used in the uncertain and unknown subterranean tunnel. A Primary-Scout Multi-Robot System (PS-MRS) was proposed. A chain topology in a subterranean environment was implemented using a trimmed ZigBee2006 protocol stack to build the multi-hop communication network. The ZigBee IC-CC2530 modular circuit was adapted by mounting it on the PS-MRS. A physical experiment based on the strategy of PS-MRS was used in this paper to evaluate the efficiency of multi-hop communication and to realize the delivery of data packets in an unknown and uncertain underground laboratory environment.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1178-1183
• /
• 2003

As personal robots coexist with a person with a role to help a person, while adapting various human life and environment, the personal robots have to accommodate frequently-changing or different-from-home-to-home environment. In addition, personal robots may have many kinds of different Kinematic configurations depending on the capabilities. Some may have a mobile base and others may have arms and a head. The motivation of this study arises from this not-well-defined home environment and varying Kinematic configuration. So the goal of this study is to develop a general control architecture for personal robots. There exist three major architectures; deliberative, reactive and hybrid. We found that these are applicable only for the defined environment with a fixed Kinematic configuration. Neither could accommodate the above two requirements. For the general solution, we propose a Supervised Hybrid Architecture (SHA), in which we use double layers of deliberative and reactive controls, distributed control with a modular design of Kinematic configurations, and real-time Linux OS. Deliberative and reactive actions interact through a corresponding arbitrator. These arbitrators help a robot to choose an appropriate architecture depending on the current situation to successfully perform a given task. The distributed control modules communicate through IEEE 1394 for the easy expandability. With a personal robot platform with a mobile base, two arms, a head and a pan-tilt stereo eye system, we tested the developed SHA for static as well as dynamic environments. For this application, we developed decision-making rules for selecting appropriate control methods for several situations of navigation task. Examples are shown to show the effectiveness.

• 제어로봇시스템학회논문지
• /
• 제17권6호
• /
• pp.539-545
• /
• 2011

This paper describes an intelligent service robot system for managing a store in an unmanned environment. The robot can be a good replacement for humans because it is possible to work all day and to remember lots of information. We design a system architecture for configuring many intelligent functions of intelligent service robot system which consists of four layers; a User Interaction Layer, a Behavior Scheduling Layer, a Intelligent Module Layer, and a Hardware Layer. We develop an intelligent service robot 'Part Timer' based on the designed system architecture. The 'Part Timer' has many intelligent function modules such as face detection-recognition-tracking module, speech recognition module, navigation module, manipulator module, appliance control module, etc. The 'Part Timer' is possible to answer the phone and this function gives convenient interface to users.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2008년도 춘계학술대회 논문집
• /
• pp.907-908
• /
• 2008