Robot system development consists of several sub-tasks such as layout design, motion planing, and sensor programming etc. In general, on-line programming and debugging for such tasks demands burdensome time and labor costs, which motivates an off-line graphic simulation system. MSRS(Microsoft Robotics Studio) released in recent years is an appropriate tool for the graphic simulation system since it supports CCR(Concurrency and Coordination Runtime), DSS(Decentralized System Services), and dynamics simulation based on PhysX and graphic animation as well. In this paper, we developed an MSRS based network simulation system for quadruped walking robots, which controls virtual 3D graphic robots existing in remote side through internet.

In this paper, new application of adaptive neural network to design a ship's Rudder-Roll Damping(RRD) control system is presented Firstly, the ANNAI neural network controller is presented. Secondly, new RRD control system using this neural network approach is developed. It uses two neural network controllers for heading control and roll damping control separately. Finally, Computer simulation of this RRD control system is carried out to compare with a linear quadratic optimal RRD control system; discussions and conclusions are provided. The simulation results show the feasibility of using ANNAI controller for RRD. Also, the necessity of mathematical ship model in designing RRD control system is removed by using NN control technique.

구조 재료와 시공기술의 발달로 구조물은 높고 길게 설계할 수 있게 되었으나, 그에 따른 진동문제와 사용성에 관한 문제가 발생하였고, 구조물의 과다한 변위는 구조물에 심각한 손상을 발생시켰다. 이러한 구조물의 진동 문제를 해결하기 위하여 본 논문에서는 구조물의 상태벡터와 제어력만으로 구성된 훈련패턴을 기본으로 하여 인공신경망이론과 확률신경망이론을 사용하여 구조물의 진동을 능동제어하는 방법을 제안하였다. 구조물의 제어를 위해 LQR 제어알고리즘을 이용하여 구조물의 상태벡터와 제어력을 구한 후, 상태벡터를 입력으로 제어력을 출력으로 하는 인공신경망과 확률신경망의 훈련패턴을 구성하였다. 제안된 방법을 사용하여 Northridge 지진하중을 받는 3층 빌딩구조물을 제어하였고, 제안된 인공신경망과 확률신경망의 제어 결과를 비교하였다.

게임의 발전에 따라 게임에 등장하는 NPC(Non-Player Character)들의 지능 또한 중요성을 더해 가고 있다. 단순히 이동하고 플레이어를 공격하기만 하는 수준을 넘어서 WPC들 역시 다양한 기술과 전술을 사용하는 것이 최근의 MMORPG 게임의 추세이다. 본 논문에서는 신경망과 유전자 알고리즘을 이용하여 롤플레잉 게임에 사용되는 캐릭터에게 학습 및 적응 능력을 부여하는 방법을 제안한다. 제안된 지능 캐릭터가 얼마나 게임의 규칙과 전술을 잘 학습하고 적응하는지를 살펴보기 위하여 본 논문에서는 간단한 게임 모델을 제작하여 실험하였다. 캐릭터는 탱커(Tanker), 딜러(Dealer), 힐러(Healer)의 3가지 종류가 있으며, 지능 캐릭터 집단은 신경망과 유전 알고리즘으로 학습되고 FSM으로 움직이는 적 캐릭터 집단과의 전투를 통해 학습한다. 실험 결과 지능 캐릭터가 전투를 통해 자신과 적의 능력에 따른 적절한 전투 방식을 스스로 학습하고, 게임 규칙의 변화에 적응하는 것을 볼 수 있었다.

This paper presents an improved adaptive neural network autopilot based on our previous study for track-keeping control of ships. The proposed optimal neural network controller can automatically adapt its learning rate and number of iterations. Firstly, the track-keeping control system of ships is described For the track-keeping control task, a way-point based guidance system is applied To improve the track-keeping ability, the off-track distance caused by external disturbances is considered in learning process of neural network controller. The simulations of track-keeping performance are presented under the influence of sea current and wind as well as measurement noise. The toolbox for track-keeping simulation on Mercator chart is also introduced.

In Part I(theoretical study) of the paper, a new adaptive autopilot for ships based on Adaptive Neural Networks was proposed. The ANNAI autopilot was designed for course-keeping, turning and track-keeping control for ships. In this part of the paper, to show the effectiveness and feasibility of the ANNAI autopilot and automatic selection algorithm for learning rate and number of iterations, computer simulations of course-keeping and track-keeping tasks with and without the effects of measurement noise and external disturbances are presented. Additionally, the results of the previous studies using Adaptive Neural Network by backpropagation algorithm are also showed for comparison.

This paper presents a new adaptive autopilot for ships based on the Adaptive Neural Networks. The proposed adaptive autopilot is designed with some modifications and improvements from the previous studies on Adaptive Neural Networks by Adaptive Interaction (ANNAI) theory to perform course-keeping, turning and track-keeping control. A strategy for automatic selection of the neural network controller parameters is introduced to improve the adaptation ability and the robustness of new ANNAI autopilot. In Part II of the paper, to show the effectiveness and feasibility of the proposed ANNAI autopilot, computer simulations of course-keeping and track-keeping tasks with and without the effects of measurement noise and external disturbances will be presented.

최근에, 자동화 크레인 제어 시스템은 빠른 속도와 신속한 수송이 요구되어 지고 있다. 따라서, 컨테이너가 초기좌표에서 최종좌표로 이동될 때 컨테이너 경로는 최소시간에 흔들림 없이 설계되어야 한다. 이를 위해 본 연구에서는 최종 좌표까지 이동에서 충돌을 피하기 위하여 충돌방지 경로를 계산하였다. 그리고, 정확한 주행 제어를 위해서 신경회로망 예측 PID제어기를 구성하였다. 제안된 예측제어 시스템은 PID 파라미터를 생산하기 위하여 신경회로망 예측기, PID 제어기 그리고 신경회로망 자기 동조기로 구성하였다 크레인 시스템을 통한 시뮬레이션 분석에서 다른 기존의 제어기들 보다 우수한 제어 수행을 증명하였다.

Along with the rapid growth of shipping and transportation , the size of a ship larger and larger. Low speed maneuverabililty of a full ship has been received a great deal of attention concerting about the navigation safety, especially in the harbour area of waterway. And, the iperation of the full ship in harbour area is one fo tehmost difficult technique. Usually highly experienced experts can make a suitable decision considering various propeller ,rudder actions and environmental conditions. The Artificial Neural Network is applied to the automatic berthing control of a ship. The teaching data are made by the berthing simulation of a ship on the computer. And, the layer neural network is used and the 'Error Back-Propagation Algorithm' is used to teach the neural network. Finally, it is shown that the berthing control is successfully done by the established neural network.

Studies on the ship's automatic navigation & berthing control have been continued by way of solving the ship's mathematical model, but the results of such studies have not reached to our satisfactory level due to its non-linear characteristics at low speed. In this paper, the authors propose a new berthing control system which can evaluate as closely as cap-tain's decision-making by using the FNN(Fuzzy Neural Network) controller which can simulate captain's knowledge. This berthing controller consists of the navigation subsystem FNN controller and the berthing subsystem FNN controller. The learning data are drawn from Ship Handling Simulator (NavSim NMS-90 MK Ⅲ) and represent the ship motion characteristics internally. According to learning procedure, both FNN controllers can tune membership functions and identify fuzzy control rules automatically. The verified results show the FNN controllers effective to incorporate captain's knowledge and experience of berthing.

Studies on the ship's automatic navigation & berthing control have been continued by way of solving the ship's mathematical model, but the results of such studies have not reached to our satisfactory level due to its non-linear characteristics at low speed. In this paper, the authors propose a new control system which can evaluate as closely as captain's decision-making by using the FNN(Fuzzy Neural Network) controller which can simulate captain's knowledge. This controller contains the concept of safety according to channel width. The learning data are drawn from ship Handling simulator(NavSim NMS-90 MK III) and represent the ship motion characteristics internally. According to learning procedure, the FNN controller can tune membership functions and identify fuzzy control rules automatically. The verified results show that the FNN controller is effective to incorporate captain's knowledge and experience of manoeuvrability in channel.