• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.431-431
• /
• 2000

The modeling of 5-bar linkage robot manipulator dynamics by means of a mathematical and neural architecture is presented. Such a model is applicable to the design of a feedforward controller or adjustment of controller parameters. The inverse model consists of two parts: a mathematical part and a compensation part. In the mathematical part, the subsystems of a 5-bar linkage robot manipulator are constructed by applying Kawato's Feedback-Error-Learning method, and trained by given training data. In the compensation part, MLP backpropagation algorithm is used to compensate the unmodeled dynamics. The forward model is realized from the inverse model using the inverse of inertia matrix and the compensation torque is decoupled in the input torque of the forward model. This scheme can use tile mathematical knowledge of the robot manipulator and analogize the robot characteristics. It is shown that the model is reasonable to be used for design and initial gain tuning of a controller.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2000년도 추계종합학술대회논문집
• /
• pp.201-204
• /
• 2000

This paper describes a study on the time-varying control of parameters in learning of the neural network. Elman recurrent neural network (RNN) is used to implement the control of parameters. The parameters of learning and momentum rates In the error backpropagation algorithm ate updated at every iteration using fuzzy rules based on performance index. In addition, the gain and slope of the neuron's activation function are also considered time-varying parameters. These function parameters are updated using the gradient descent algorithm. Simulation results show that the auto-tuned learning algorithm results in faster convergence and lower system error than regular backpropagation in the system identification.

• 한국소음진동공학회논문집
• /
• 제25권11호
• /
• pp.753-763
• /
• 2015

This paper proposes a decentralized robust adaptive neural network control scheme using multiple radial basis function neural networks for electrically driven robot manipulators with bounded input voltages in the presence of uncertainties. The proposed controller considers both robot link dynamics and actuator dynamics. Practically, the controller gain coefficients applied at each joint may be nonlinear time-varying and the input voltage at each joint is saturated. The proposed robot controller overcomes the various uncertainties and the input voltage saturation problem. The proposed controller does not require any robot and actuator parameters. The adaptation laws of the proposed controller are derived by using the Lyapunov stability analysis and the stability of the closed-loop control system is guaranteed. The validity and robustness of the proposed control scheme are verified through simulation results.

• International Journal of Control, Automation, and Systems
• /
• 제2권3호
• /
• pp.374-383
• /
• 2004

This paper presents a neural network adaptive controller for autonomous diving control of an autonomous underwater vehicle (AUV) using adaptive backstepping method. In general, the dynamics of underwater robotics vehicles (URVs) are highly nonlinear and the hydrodynamic coefficients of vehicles are difficult to be accurately determined a priori because of variations of these coefficients with different operating conditions. In this paper, the smooth unknown dynamics of a vehicle is approximated by a neural network, and the remaining unstructured uncertainties, such as disturbances and unmodeled dynamics, are assumed to be unbounded, although they still satisfy certain growth conditions characterized by 'bounding functions' composed of known functions multiplied by unknown constants. Under certain relaxed assumptions pertaining to the control gain functions, the proposed control scheme can guarantee that all the signals in the closed-loop system satisfy to be uniformly ultimately bounded (UUB). Simulation studies are included to illustrate the effectiveness of the proposed control scheme, and some practical features of the control laws are also discussed.

• 한국군사과학기술학회지
• /
• 제26권1호
• /
• pp.10-21
• /
• 2023

For various target tracking applications, it is well known that the Kalman filter is the optimal estimator(in the minimum mean-square sense) to predict and estimate the state(position and/or velocity) of linear dynamical systems driven by Gaussian stochastic noise. In the case of nonlinear systems, Extended Kalman filter(EKF) and/or Unscented Kalman filter(UKF) are widely used, which can be viewed as approximations of the(linear) Kalman filter in the sense of the conditional expectation. However, to implement EKF and UKF, the exact dynamical model information and the statistical information of noise are still required. In this paper, we propose the recurrent neural-network based Kalman filter, where its Kalman gain is obtained via the proposed GRU-LSTM based neural-network framework that does not need the precise model information as well as the noise covariance information. By the proposed neural-network based Kalman filter, the state estimation performance is enhanced in terms of the tracking error, which is verified through various linear and nonlinear tracking problems with incomplete model and statistical covariance information.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제51권10호
• /
• pp.573-580
• /
• 2002

This paper presents neural load disturbance observer that used to deadbeat load torque observer and regulation of the compensation gain by parameter estimator As a result, the response of PMSM follows that of the nominal plant. The load torque compensation method is compose of a neural deadbeat observer. To reduce of the noise effect, the post-filter, which is implemented by MA process, is proposed. The parameter compensator with RLSM(recursive least square method) parameter estimator is suggested to increase the performance of the load torque observer and main controller. The proposed estimator is combined with a high performance neural torque observer to resolve the problems. As a result, the proposed control system becomes a robust and precise system against the load torque and the parameter variation. A stability and usefulness, through the verified computer simulation and experiment, are shown in this paper.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1994년도 추계학술대회 논문집 학회본부
• /
• pp.326-328
• /
• 1994

A modified Kohonen's simple Competitive Learning(SCL) algorithm which has binary reinforcement function and a constant adaptation gain is proposed. In contrast to the time-varing adaptation gain of the original Kohonen's SCL algorithm, the proposed algorithm uses a constant adaptation gain, and adds a binary reinforcement function in order to compensate for the lowered learning ability of SCL due to the constant adaptation gain. Since the proposed algorithm does not have the complicated multiplication, it's digital hardware implementation is much easier than one of the original SCL.

• 한국음향학회지
• /
• 제21권6호
• /
• pp.522-530
• /
• 2002

본 논문에서는 선형 예측 후에 얻어지는 잔차 신호 (residual signal)를 신경 회로망에 바탕을 둔 비선형 예측기로 예측하는 방법을 제안하였다. 신경 회로망을 이용한 예측 방법의 타당성을 입증하기 위해, 먼저 선형 장구간 예측기와 신경 회로망이 도입된 비선형 장구간 예측기의 성능을 서로 비교하였다. 그리고 비선형 예측 후의 잔차 신호를 양자화 하는 과정에서 발생하는 양자화 오차의 영향에 대해 분석하였다. 제안된 신경망 예측기는 예측 오차뿐만 아니라 양자화의 영향을 함께 고려하였으며, 양자화오차에 대한강인성을 갖게 하기 위하여 쿤-터커 (Kuhn-Tucker) 부등식 조건을 만족하는 제한조건 역전파 알고리즘을 새로이 제안하였다. 실험 결과, 제안된 신경망 예측기는 제한조건을 갖는 학습 알고리즘을 사용했음에도 불구하고, 예측 이득이 크게 뒤떨어지지 않는 성능을 나타내었다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 추계학술대회 논문집
• /
• pp.357-360
• /
• 1997

Abstract: In teleoperation field robotic system such as hydraulically actuated robotic excavator, the maneuverability and convenience is the most important part in the operation of robotic excavator. Particularly the force information is important in dealing with digging and leveling operation in the teleoperated excavator. Excavators are also subject to a wide variation of soil-tool interaction forces. This paper presents a new force reflecting joystick in a velocity-force type bilateral teleoperation system. The master system is electrical joystick and the slave system IS hydraulically actuated cylinder with linear position sensor. Particularly Pneumatic motor is used newly in the master joystick for force reflection and the information of the pressure of salve cylinder is measured and utilized as the force feedback signal. Also force-reflection gain greatly affects the excavation performance of a hydraulically actuated robotic system and it is very difficult to determine it appropriately since slave excavator contacts with various environments such as from soft soil to rock. To overcome this, this paper proposes a force-reflection gain selecting algorithm based on artificial neural network and fuzzy logic.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 B
• /
• pp.606-608
• /
• 1997

In this paper, Neuro-Fuzzy Controller(NFC), a fuzzy system realized using a neural network, is to adopt for the multivariable system. In the multivariable system, the interactive effects between the variables should be taken into account. A simple compensator, using the steady-state information can be obtained for open-loop stable systems, is presented to cope with this problem. However, it should be supposed that the plant is unknown to the control system designer, but an estimate of the DC gain has been obtained by carrying out experiments on the plant. Also, if the variables are not combinated completely, it is difficult to design the controller. Therefore, we design a neuro-fuzzy controller which controls a multivariable system with only input output informations, and compare its performance with that of a PI controller. In the proposed controller, the construction of the membership functions and rule base, which is highly heuristic, can be achieved using a training process. This allows the combination of knowledge of human experts and evidence from input-output data.