• Journal of Electrical Engineering and Technology
• /
• 제10권6호
• /
• pp.2420-2426
• /
• 2015

This paper proposes an evolutionary optimization approach for optimal hopping of humanoid robots. In the proposed approach, the hopping trajectory is generated by a central pattern generator (CPG). The CPG is one of the biologically inspired approaches, and it generates rhythmic signals by using neural oscillators. During the hopping motion, the disturbance caused by the ground reaction forces is compensated for by utilizing the sensory feedback in the CPG. Posture control is essential for a stable hopping motion. A posture controller is utilized to maintain the balance of the humanoid robot while hopping. In addition, a compliance controller using a virtual spring-damper model is applied for stable landing. For optimal hopping, the optimization of the hopping motion is formulated as a minimization problem with equality constraints. To solve this problem, two-phase evolutionary programming is employed. The proposed approach is verified through computer simulations using a simulated model of the small-sized humanoid robot platform DARwIn-OP.

• 대한기계학회논문집A
• /
• 제26권6호
• /
• pp.1092-1098
• /
• 2002

This paper discusses the composition of the theory of reinforcement teaming, which is applied in real-time teaming, and evolutionary strategy, which proves its the superiority in the finding of the optimal solution at the off-line teaming method. The individuals are reduced in order to team the evolutionary strategy in real-time, and new method that guarantee the convergence of evolutionary mutations are proposed. It is possible to control the control object varied as time changes. As the state value of the control object is generated, applied evolutionary strategy each sampling time because of the teaming process of an estimation, selection, mutation in real-time. These algorithms can be applied, the people who do not have knowledge about the technical tuning of dynamic systems could design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes. In the future, studies are needed on the proof of the theory through experiments and the characteristic considerations of the robustness against the outside disturbances.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
• /
• pp.1960-1961
• /
• 2006

In this paper, The trajectory control of robot manipulator is proposed. It divides by trajectory planning and tracking control. A trajectory planning and tracking control of robot manipulator is used to the neural network and evolutionary algorithm. The trajectory planning provides not only the optimal trajectory for a given cost function through evolutionary algorithm but also the configurations of the robot manipulator along the trajectory by considering the robot dynamics. The computed torque method (C.T.M) using the model of the robot manipulators is an effective means for trajectory tracking control. However, the tracking performance of this method is severely affected by the uncertainties of robot manipulators. The Radial Basis Function Networks(RBFN) is used not to learn the inverse dynamic model but to compensate the uncertainties of robot manipulator. The computer simulations show the effectiveness of the proposed method.

• 한국지능시스템학회논문지
• /
• 제10권4호
• /
• pp.315-323
• /
• 2000

본 논문에서는 생명창발과 진화에 기반한 신경망 구성방법을 제안한다. 이 방법은 생뭉의 DNA 구조의 특성과 식물의 생장에 기반을 둔 방법이다. 본 논문에서 제안한 방법은 DNA 코딩 방법과 L-system의 생장 구칙을 이용하여 신경망을 구성하는 방법이닫. L-system은 병렬적인 제조합 규칙을 이용하여, DNA 코딩 방법은 표현의 제약이 없는 표기법이다. 또한 진화 알고리듬은 다윈의 자연도태를 모방한 탐색법으로 다양한 해공간의 표현과 높은 효율로 탐색이 가능하다. 본 논문에서는 이러한 방법들을 이용햐 신경망을 구성하고, 신경망의 Mackey-Glass, Sunspot, KOSPI 같은 시계열 예측분제에 적용하여 유효성을 입증하고자 한다.

• 전자공학회논문지S
• /
• 제36S권1호
• /
• pp.29-37
• /
• 1999

일반적으로 신경망의 정보처리 능력은 신경망의 구조와 효율적인 학습패턴에 의해 결정된다. 그러나 아직까지 체계적으로 신경망의 구조를 설계하거나 효율적인 학습패턴을 선택하는 방법은 없다. 한편 진화 알고리즘은 개체군을 이용한 탐색법으로 전역적 최적해를 구하는 데 많이 사용되고 있으며, 특히 최적의 시스템을 설계하고자 할 때 매우 유용한 방법이다. 본 논문에서는 유전자 알고리즘으로 구성된 두 개의 개체군이 서로 경쟁적으로 진화하는 공진화 방법에 의해 최적의 신경망구조를 찾는 방법을 제안한다. 이 방법은 신경망구조를 나타내는 주개체군과 학습패턴을 나타내는 부개체군으로 되어 있으며, 이 두 개체군(신경망과 학습패턴)은 서로 경쟁적으로 진화한다. 즉, 학습패턴은 신경망이 학습하기 힘든 패턴으로 진화하고 신경망은 그 패넌들을 학습할 수 있도록 진화하단. 이 방법은 부적절한 학습패턴의 선택과 임의적인 신경망의 설계로 인한 시스템의 성능이 저하되는 것을 해결한다. 또한 공진화 방법에서 각 개체군의 적합도는 동적으로 변화하기 때문에 그 진행과정을 쉽게 알 수 없다. 따라서 본 논문에서는 그 진행과정을 관찰할 수 있는 방법도 소개한다. 마지막으로 제안한 방법을 로봇 매니플레이터의 비주얼 서보임 문제에 적용하여 그 유효성을 검증한다.

• 전자공학회논문지C
• /
• 제36C권3호
• /
• pp.58-64
• /
• 1999

진화 프로그래밍은 두 가지 요소로 특징지을 수 있다. 하나는 선택 방법이고 나머지는 돌연변이 규칙이다. 본 논문에서는 신경회로망의 역전파 학습 알고리듬을 이용하여 돌연변이 연산을 수행하는 새로운 진화 프로그래밍 알고리듬을 제안한다. 신경회로망의 학습 알고리듬에서 현재 오차는 진화 프로그래밍의 개체가 진화해 나가야 할 방향을 지정해 주고, 관성은 개체의 변이에 지금까지의 진화 경향을 더해 주어서 빠르게 전역 최적해를 찾도록 하였다. 표준 테스트 함수를 이용하여 제안된 알고리듬의 성능과 강건함을 확인하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2005년도 춘계학술대회 학술발표 논문집 제15권 제1호
• /
• pp.297-300
• /
• 2005

In this study, we proposed genetically optimized self-organizing fuzzy polynomial neural network based on information granulation and evolutionary algorithm (gdSOFPNN), develop a comprehensive design methodology involving mechanisms of genetic optimization. The proposed gdSOFPNN gives rise to a structural Iy and parametrically optimized network through an optimal parameters design available within FPN (viz. the number of input variables, the order of the polynomial, input variables, the number of membership functions, and the apexes of membership function). Here, with the aid of the information granulation, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. The performance of the proposed gdSOFPNN is quantified through experimentation that exploits standard data already used in fuzzy modeling.

• 전기학회논문지
• /
• 제67권12호
• /
• pp.1665-1670
• /
• 2018

A convolutional neural network (CNN), which is one of the deep learning models, has been very successful in a variety of computer vision tasks. Filters of a CNN are automatically generated, however, they can be further optimized since there exist the possibility of existing redundant and less important features. Therefore, the aim of this paper is a filter reduction to accelerate and compress CNN models. Evolutionary algorithms is adopted to remove the unnecessary filters in order to minimize the parameters of CNN networks while maintaining a good performance of classification. We demonstrate the proposed filter reduction methods performing experiments on CIFAR10 data based on the classification performance. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제9권2호
• /
• pp.83-89
• /
• 2005

In this paper a new algorithm of learning and evolving artificial neural networks using gene expression programming (GEP) is presented. Compared with other traditional algorithms, this new algorithm has more advantages in self-learning and self-organizing, and can find optimal solutions of artificial neural networks more efficiently and elegantly. Simulation experiments show that the algorithm of evolving weights or thresholds can easily find the perfect architecture of artificial neural networks, and obviously improves previous traditional evolving methods of artificial neural networks because the GEP algorithm imitates the evolution of the natural neural system of biology according to genotype schemes of biology to crossover and mutate the genes or chromosomes to generate the next generation, and the optimal architecture of artificial neural networks with evolved weights or thresholds is finally achieved.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.413-415
• /
• 2001

In this paper, Polynomial Neural Networks(PNN) is proposed to overcome some problems, such as the conflict between overfitting and good generation, and low reliability and to control nonlinearity and unknown parameter of complex system. PNN structure is consisted of layers and nodes like conventional neural networks but is not fixed and can be generated according to the system environments. The performances depend on two factors, number of inputs and order of polynomials in each node directly. In most cases these factors are decided by the trial and error of designer so optimization is needed in deciding procedure of the factors. Evolutionary algorithm is applied to decide the factors in PNN. The study is illustrated with the aid of representative time series data for gas furnace process used widely for performance comparison, and shows the designed PNN architecture with evolutionary algorithm.