• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.957-962
• /
• 2005

Today, the elderly is increasing gradually in the Republic of Korea society and this problem will be more serious in the near future. Therefore, engineering support for aged people is required. We are establishing a new field of healthcare engineering for elderly people and aiming to support for aged people and disabled people using adaptive control and instrument technology. In this paper, the goal is to implement the shared control of a robot mobility aid for the elderly. As using this type of assistive technology to be useful by its intended user community, it supports elderly people and handicapped people to live independently in their private homes. The interface transforms the force applied by the user into the robot's motion. Devices like buttons, joysticks, and levers already exist for relaying user input; however, they require hand displacement that would loosen or otherwise release the user's hold. Such interfaces make operation very difficult and potentially unsafe. Therefore, we propose a shared control system. It's safe more than joysticks and buttons. The shared control is a means of registering the user's intention through physical interaction. It's an important component in the development of robotic elderly assistant. The concept of shared control describes a system which is two or more independent control systems. We are using that the three component blocks consist of pressure sensor (flexible force sensor), circuit of measurement and transfer function. Experimental trials of this paper have been tested at the indoor environment. The robot is able to know the user intended direction through haptic device were logged along with the robot's force sensor.

• 로봇학회논문지
• /
• 제19권2호
• /
• pp.139-148
• /
• 2024

In this paper, we propose a two-degree-of-freedom snake robot head system and an I-PID (Intelligent Proportional-Integral-Derivative)-based controller utilizing RBF (Radial Basis Function) neural network and adaptive robust terms as a control strategy to reduce rotation occurring in the snake robot head. This study proposes a two-degree-of-freedom snake robot head system to avoid complex snake robot dynamics. This system has a control system independent of the snake robot. Subsequently, it utilizes an I-PID controller to implement a control system that can effectively manage rotation at the snake robot head, the robot's nonlinearity, and disturbances. To compensate for the time delay estimation errors occurring in the I-PID control system, an RBF neural network is integrated. Additionally, an adaptive robust term is designed and integrated into the control system to enhance robustness and generate control inputs responsive to signal changes. The proposed controller satisfies stability according to Lyapunov's theory. The proposed control strategy was tested using a 9-degreeof-freedom snake robot. It demonstrates the capability to reduce rotation in Lateral undulation, Rectilinear, and Sidewinding locomotion.

• 한국지능시스템학회논문지
• /
• 제24권6호
• /
• pp.586-591
• /
• 2014

본 연구에서는 인공 벌 군집(ABC: Artificial Bee Colony) 알고리즘을 이용하여 주어진 레이더 데이터로부터 강수 사례와 비강수 사례를 분류하는 방사형 기저함수 신경회로망(RBFNNs: Radial Basis Function Neural Networks)분류기를 소개한다. 기상청에서 사용하고 있는 기상 레이더 데이터의 특성 분석을 통해 입력 데이터를 구성한다. 방사형 기저함수 신경회로망의 조건부에서는 Fuzzy C-Means 클러스터링 방법을 이용하여 적합도를 계산하고, 결론부에서는 최소자승법(LSE: Least Square Method)을 이용하여 다항식 계수를 추정한다. 추론부에서 최종출력 값은 퍼지 추론 방법을 이용하여 얻어진다. 제안된 분류기의 성능은 기상청에서 사용하는 QC와 CZ 데이터를 고려하여 비교 및 분석되어진다.

• 한국지능시스템학회논문지
• /
• 제7권5호
• /
• pp.34-45
• /
• 1997

본 논문에서는 경쟁학습 신경회로망의 디지탈 칩 구현에서 뉴런의 집적도를 향상시키기 위해 하드웨어 구현이 용이한 새로운 신경회로망 모델로서 일정 적응이득과 이진 강화함수를 가진 여러 가지 경쟁학습 신경회로망 모델들을 제안하고, 그 중 안정성과 분류성능이 가장 우수한 일정 적응이득과 이진 강화함수를 지닌 자기조직화 형상지도(Self-Organizing Feature Map)신경회로망의 FPGA위에서의 하드웨어 구현에 대해서 논한다. 원래의 SOFM 알고리즘에서 적응이득이 시간 종속형인데 반하여, 본 논문에서 하드웨어로 구현한 알고리즘에서는 적응이득이 일정인 값으로 고정되며 이로 인한 성능저하를 보상하기 위하여 이진 강화함수를 부가한다. 제안한 알고리즘은 복잡한 곱셈 연산을 필요로 하지 않으므로 하드웨어 구현이 용이하다는 특징이있다. 1개의 덧셈/뺄셈기와 2개의 덧셈기로 구성된 단위 뉴런은 형태가 단순하면서 반복적이므로 하나의 FPGA 위에서도 다수의 뉴런을 구현 할수 있으며 비교적 소수의 제어신호로서 이들을 모두 제어 가능할 수 있도록 설계하였다.실험 결과 각 구서부분은 모두 이상 없이 올바로동작하였으며 각 부분이 모두 종합된 전체 시스템도 이상 없이 동작함을 알 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1759-1764
• /
• 2005

Human Adaptive Mechatronics(HAM) is a new concept which was proposed in our university's research project sponsored by Japanese Ministry of Education, Sports, Culture, Science and Technology(MEXT), and is defined as "intelligent mechanical systems that adapt themselves to the user's skill under various environments, assist to improve the user's skill, and assist the human-machine system to achieve best performance". In this paper, the concept and key-items of HAM are mentioned. And the control strategy to realize a HAM human-machine system is explained in the case of physical-interface system, i.e. haptic system. The proposed assist-control of a force-feedback type haptic system includes online estimation of a operator's control characteristics, and a `force assist' function implemented as a change in the support ratio according to the identified skill level. We developed a HAM-haptic device test system, executed evaluation experiments with this apparatus, and analyzed the measured data. It was confirmed that the operator's skill could be estimated and that operator's performance was enhanced by the assist-control.

• 한국통신학회논문지
• /
• 제32권4A호
• /
• pp.373-378
• /
• 2007

본 논문에서는 CR(Cognitive Radio)의 가장 적합한 인공지능 기술로 주목받고 있는 게임이론을 전력 제어 방식에 적용해 OFDM 시스템 기반의 사용효율과 효용에 대한 성능 평가 결과를 제시하였다. 사용자와 네트워크 동시 최적화를 위한 효용함수식을 정의했으며 모의실험을 통해 FOM(Figure of Merit)과 형평성(Fairness)에서 기존의 전력제어 방식보다 월등한 성능을 입증하였다. 또한 게임이론을 이용한 전력 제어 방식은 통신 환경을 인지하고 연산하여 적합한 최적의 서비스를 제공하는 CR의 여러 분야에 확장 적용 가능성을 제시하였다.

• 제어로봇시스템학회논문지
• /
• 제6권1호
• /
• pp.57-65
• /
• 2000

In this paper, a model reference adaptive control for the atomic force microscope (AFM) of tapping mode is investigated. The dynamics between the AFM system and al sample is mathematically modeled as a second order spring-mass-damper system with oscillatory inputs. The attractive and repulsive forces between the tip of the AFM system and the sample are derived using the Lennard-Jones potential energy. By non-dimensionalizing the displacement of the tip and the input frequency, the chaotic behavior near a resonance frequency is better depicted through the non-dimensionalized equations. Four nonlinear analysis techniques, a phase portrait, sensitive dependence on initial conditions, a power spectral density function, and a Pomcare map are investigated. Because the equations of motion derived in this paper involve unknown parameter values such as the damping effect of the air and the interaction constants between materials, the standard model reference adaptive control is adopted. Two control objectives, the prevention of chaos and the tracking of reference signal, are pursued. Simulation results are included.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제12권1호
• /
• pp.314-324
• /
• 2020

Due to the nonlinearity and environmental uncertainties, the design of the ship's steering controller is a long-term challenge. The purpose of this study is to design an intelligent autopilot based on Extended Kalman Filter (EKF) trained Radial Basis Function Neural Network (RBFNN) control algorithm. The newly developed free running model scaled surface vessel was employed to execute the motion control experiments. After describing the design of the EKF trained RBFNN autopilot, the performances of the proposed control system were investigated by conducting experiments using the physical model on lake and simulations using the corresponding mathematical model. The results demonstrate that the developed control system is feasible to be used for the ship's motion control in the presences of environmental disturbances. Moreover, in comparison with the Back-Propagation (BP) neural networks and Proportional-Derivative (PD) based control methods, the EKF RBFNN based control method shows better performance regarding course keeping and trajectory tracking.

• Smart Structures and Systems
• /
• 제33권5호
• /
• pp.365-374
• /
• 2024

This paper adopts a new approach in which nonlinear vibrations can be controlled using fuzzy controllers by optimal grey evolutionary algorithm. If the fuzzy controller cannot stabilize the systems, then the high frequency is injected into the system to assist the controller, and the system is asymptotically stabilized by adjusting the parameters. This paper uses the GM (grey model) and the neural network prediction model. The structure of the neural network is improved from a single factor, and multiple data inputs are extended to various factors and numerous data inputs. The improved model expands the applicable range of uncontrolled elements and improves the accuracy of controlled prediction, using the model that has been trained and stabilized by multiple learning. The simulation results show that the improved gray neural network model has higher prediction accuracy and reliability than the traditional GM model, improving controlled management and pre-control ability. In the combined prediction, the time series parameters and the predicted values obtained from the GM (1,1) (Grey Model of first order and one variable) are simultaneously used as the input terms of the neural network, considering the influence of the non-equal spacing of the data, which makes the results of the combined gray neural network model more rationalized. By adjusting the model structure and system parameters to simulate and analyze the controlled elements, the corresponding risk change trend graphs and prediction numerical calculation results are obtained, which also realize the effective prediction of controlled elements. According to the controlled warning principle and objective, the fuzzy evaluation method establishes the corresponding early warning response method. The goals of this paper are towards access to adequate, safe and affordable housing and basic services, promotion of inclusive and sustainable urbanization and participation, implementation of sustainable and disaster-resilient buildings, sustainable human settlement planning and manage.

• International Journal of Automotive Technology
• /
• 제5권2호
• /
• pp.135-144
• /
• 2004

In this paper, the model-matching control in the longitudinal autonomous driving system is investigated by vehicle dynamics simulation, which contains nonlinear subcomponents and simplified subcomponents. The design of the robust model-matching controller is performed by the characteristics of the 2 degrees of freedom controller, which is composed of the feedforward compensator and the feedback compensator. It makes the characteristics of tractive and brake force to be equivalent to the specific transfer function, which is suggested as the reference model. Mathematical models of vehicle dynamic analysis including the model-matching control are constructed for computer simulation. Then, simple examples on open-loop simulation without any controller and closed loop simulation with the model-matching controller are applied to check the validity of the robust controller. As the practical example, the autonomous driving system in the longitudinal direction is adopted. It is proved that the model-matching control is effective and adequate to the disturbances and the perturbations, which are shown in the responses of the change of a vehicle mass and a road gradient.