• 한국지능시스템학회논문지
• /
• 제19권4호
• /
• pp.519-524
• /
• 2009

최근에 강화학습 기법은 기계학습 분야에서 많은 관심을 끌어왔다. 강화학습 관련 연구에서 가장 유력하게 사용되어 온 방법들로는 가치함수를 활용하는 기법, 제어규칙(policy) 탐색 기법 및 액터-크리틱 기법 등이 있는데, 본 논문에서는 이들 중 연속 상태 및 연속 입력을 갖는 문제를 위하여 액터-크리틱 기법의 틀에서 제안된 알고리즘들과 관련된 내용을 다룬다. 특히 본 논문은 퍼지 이론에 기반을 둔 액터-크리틱 계열 강화학습 기법인 ACFRL 알고리즘과, RLS 필터와 NAC(natural actor-critic) 기법에 기반을 둔 RLS-NAC 기법을 접목하는 방안을 집중적으로 고찰한다. 고찰된 방법론은 기는 로봇의 제어문제에 적용되고, 학습 성능의 비교로부터 얻어진 몇 가지 결과가 보고된다.

• 한국지능시스템학회논문지
• /
• 제16권6호
• /
• pp.736-741
• /
• 2006

분류 시스템은 데이터 전처리 모듈, 학습모듈, 의사결정모듈로 구성되어 있으며 지능형시스템의 중요한 구성요소로 활용되어왔다. 특히 학습모듈은 사전정보를 제공하므로 분류를 위한 핵심 역할을 수행하여 왔다. 기존의 학습을 위한 기법은 주로 승자독점방식으로 데이터를 처리하므로 경계가 불명확한 대부분의 실세계 응용에 적합하지 못하다. 또한 학습 알고리즘에 필요한 데이터를 한꺼번에 준비해야 하지만 이는 일반적으로 가능하지 않은 경우가 많다. 이를 위하여 본 논문에서는 점증적 학습 퍼지신경망, FNN-I,를 이용한 적응 분류모델을 설계한다. 이 모델에서는 유용하게 정보를 표현하기 위하여 퍼지이론을 도입하고 계속적으로 모여지는 데이터를 가지고 점증적으로 학습할 수 있는 알고리즘을 제시한다. 제안된 모델을 컴퓨터 바이러스 분류를 위한 실제 데이터에 적용하여 점증적으로 학습할 수 있고 효과적으로, 새로운 바이러스 데이터를 분류할 수 있음을 보인다.

• International Journal of Control, Automation, and Systems
• /
• 제3권4호
• /
• pp.552-563
• /
• 2005

In this paper, we propose a wavelet based fuzzy neural network (WFNN) based direct adaptive control scheme for the solution of the tracking problem of mobile robots. To design a controller, we present a WFNN structure that merges the advantages of the neural network, fuzzy model and wavelet transform. The basic idea of our WFNN structure is to realize the process of fuzzy reasoning of the wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. In our control system, the control signals are directly obtained to minimize the difference between the reference track and the pose of a mobile robot via the gradient descent (GD) method. In addition, an approach that uses adaptive learning rates for training of the WFNN controller is driven via a Lyapunov stability analysis to guarantee fast convergence, that is, learning rates are adaptively determined to rapidly minimize the state errors of a mobile robot. Finally, to evaluate the performance of the proposed direct adaptive control system using the WFNN controller, we compare the control results of the WFNN controller with those of the FNN, the WNN and the WFM controllers.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2254-2259
• /
• 2005

In this paper, we propose a wavelet based fuzzy neural network(WFNN) based direct adaptive control scheme for the solution of the tracking problem of mobile robots. To design a controller, we present a WFNN structure that merges advantages of neural network, fuzzy model and wavelet transform. The basic idea of our WFNN structure is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. In our control system, the control signals are directly obtained to minimize the difference between the reference track and the pose of mobile robot using the gradient descent(GD) method. In addition, an approach that uses adaptive learning rates for the training of WFNN controller is driven via a Lyapunov stability analysis to guarantee the fast convergence, that is, learning rates are adaptively determined to rapidly minimize the state errors of a mobile robot. Finally, to evaluate the performance of the proposed direct adaptive control system using the WFNN controller, we compare the control performance of the WFNN controller with those of the FNN, the WNN and the WFM controllers.

• 전자공학회논문지B
• /
• 제32B권10호
• /
• pp.1358-1363
• /
• 1995

This paper presents a new learning method for a noise tolerant Fuzzy ART. In the conventional Fuzzy ART, the top-down and bottom-up weight vectors have the same value. They are updated by a fuzzy AND operation between the input vector and the current value of the top-down or bottom- up weight vectors. However, it can not prevent the abrupt change of the weight vector and can not achieve good performance for a noisy input vector. To solve the problems, we updated using the weighted sum of the input vector and the current value of the top-down vector. To achieve stability, the bottom-up weight vector is updated using the fuzzy AND operation between the newly learned top-down vector and the current value of the bottom-up vector. Computer simulations show that the proposed method prominently resolves the category proliferation problem without increasing the training epoch for stabilization in noisy environments.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1997년도 춘계학술대회 논문집
• /
• pp.68-75
• /
• 1997

This paper presents a new approach to the design of neural-fuzzy controller for the speed and azimuth control of a track vehicle. The proposed control scheme uses a Gaussian function as a unit function in the frzzy-neural network, and back propagaton algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a track vehicle driven by two independent wheels.

• Journal of Advanced Marine Engineering and Technology
• /
• 제24권2호
• /
• pp.72-81
• /
• 2000

In this paper, we design an adaptive neuro-fuzzy inference system(ANFIS) precompensator for load frequency control of 2-area power systems. While proportional integral derivative (PID) controllers are used in power systems, they may have some problems because of high nonlinearities of the power systems. So, a neuro-fuzzy-based precompensation scheme is incorporated with a convectional PID controller to obtain robustness to the nonlinearities. The proposed precompensation technique can be easily implemented by adding a precompensator to an existing PID controller. The applied neruo-fuzzy inference system precompensator uses a hybrid learning algorithm. This algorithm is to use both a gradient descent method to optimize the premise parameters and a least squares method to solve for the consequent parameters. Simulation results show that the proposed control technique is superior to a conventional Ziegler-Nichols PID controller in dynamic responses about load disturbances.

• 한국정밀공학회지
• /
• 제20권7호
• /
• pp.155-162
• /
• 2003

We propose a new technique far real-tine controller design of a autonomous cruise mobile robot with three drive wheels. The proposed control scheme uses a Caussian function as a unit function in the fuzzy neural network. and a back propagation algorithm to train the fuzzy neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-foray. The control performance of the proposed controller is illustrated by performing the computer simulation for trajectory tracking of the speed and azimuth of a autonomous cruise mobile robot driven by three independent wheels.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.957-959
• /
• 1999

In this paper we proposed a new fuzzy modeling method by Fuzzy Equalization(FE) based on probability theory. FE concerns a process of building membership function without learning using back-propagation of neural network. Therefore, we compare the proposed method with Adaptive Network-based Inference System based on hybrid learning. Finally, we will show better performance and its usefulness for a new fuzzy modeling to automobile mpg prediction.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 춘계학술대회 논문집(한국공작기계학회)
• /
• pp.250-254
• /
• 2001

This paper presents a new approach to the design of cruise control system of a mobile robot with two drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.