• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.228-233
• /
• 2004

Nowadays, the robot with various and complex functions is required. previous algorithms, however, cannot satisfy the requirement. In order to solve these problems, we introduce the 2-Layer Fuzzy Controller, which has a small number of fuzzy rules corresponding to various inputs and outputs. Also, it controls robustly and effectively an object. The main problem in the fuzzy controller is how to design the fuzzy rule. This paper designs the optimal 2-layer fuzzy controller using the Schema Co-Evolutionary Algorithm. The schema co-evolutionary algorithm can find more rapidly and excellently than simple genetic algorithm does.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.2 no.1
• /
• pp.95-110
• /
• 1998

Evolutionary Algorithms (EAs) are population-based optimization methods based on the principle of Darwinian natural selection. The representative methodology in EAs is genetic algorithm (GA) proposed by J. H. Holland, and the theoretical foundations of GA are the Schema Theorem and the Building Block Hypothesis. In the meaning of these foundational concepts, simple genetic algorithm (SGA) allocate more trials to the schemata whose average fitness remains above average. Although SGA does well in many applications as an optimization method, still it does not guarantee the convergence of a global optimum in GA-hard problems and deceptive problems. Therefore as an alternative scheme, there is a growing interest in a co-evolutionary system, where two populations constantly interact and co-evolve in contrast with traditional single population evolutionary algorithm. In this paper we show why the co-evolutionary algorithm works better than SGA in terms of an extended schema theorem. And predator-prey co-evolution and symbiotic co-evolution, typical approaching methods to co-evolution, are reviewed, and dynamic fitness landscape associated with co-evolution is explained. And the experimental results show a co-evolutionary algorithm works well in optimization problems even though in deceptive functions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.491-496
• /
• 2002

Multi-objective Optimization Problems(MOPs) are occur more frequently than generally thought when we try to solve engineering problems. In the real world, the majority cases of optimization problems are the problems composed of several competitive objective functions. In this paper, we introduce the definition of MOPs and several approaches to solve these problems. In the introduction, established optimization algorithms based on the concept of Pareto optimal solution are introduced. And contrary these algorithms, we introduce theoretical backgrounds of Nash Genetic Algorithm(Nash GA) and Evolutionary Stable Strategy(ESS), which is the basis of Co-evolutionary algorithm proposed in this paper. In the next chapter, we introduce the definitions of MOPs and Pareto optimal solution. And the architecture of Nash GA and Co-evolutionary algorithm for solving MOPs are following. Finally from the experimental results we confirm that two algorithms based on Evolutionary Game Theory(EGT) which are Nash GA and Co-evolutionary algorithm can search optimal solutions of MOPs.

• International Journal of Aeronautical and Space Sciences
• /
• v.3 no.1
• /
• pp.50-60
• /
• 2002

A new co-evolutionary algorithm, of which the convergence speed is accelerated by neural networks, is proposed and verified in this paper. To reduce computational load required for co-evolutionary optimization processes, the cost function and constraint information is stored in the neural networks, and the extra offspring group, whose cost is computed by the neural networks, is generated. It increases the offspring population size without overloading computational effort; therefore, the convergence speed is accelerated. The proposed algorithm is applied to attitude control design of flexible satellites, and it is verified by computer simulations and experiments using a torque-free air bearing system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.93.3-93
• /
• 2002

$\textbullet$ Co-evolutionary algorithms $\textbullet$ Nash Genetic Algorithms $\textbullet$ Multi-objective Optimization $\textbullet$ Distance dependent mutation $\textbullet$ Pareto Optimality

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.123-126
• /
• 1998

The theoretical foundations of GA are the Schema Theorem and the Building Block Hypothesis. In the Meaning of these foundational concepts, simple genetic algorithm(SGA) allocate more trials to the schemata whose average fitness remains above average. Although SGA does well in many applications as an optimization method, still it does not guarantee the convergence of a global optimum. Therefore as an alternative scheme, there is a growing interest in a co-evolutionary system, where two populations constantly interact and co-evolve in contrast with traditional single population evolutionary algorithms. In this paper, we propose a new design method of an optimal fuzzy logic controller using co-evolutionary concept. In general, it is very difficult to find optimal fuzzy rules by experience when the input and/or output variables are going to increase. So we propose a co-evolutionary method finding optimal fuzzy rules. Our algorithm is that after constructing two population groups m de up of rule vase and its schema, by co-evolving these two populations, we find optimal fuzzy logic controller. By applying the proposed method to a path planning problem of autonomous mobile robots when moving objects exist, we show the validity of the proposed method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.601-606
• /
• 1998

In this paper, we propose a new design method of an optimal fuzzy logic controller using co-evolutionary concept. In general, it is very difficult to find optimal fuzzy rules by experience when the input and/or output variables are going to increase. Futhermore proper fuzzy partitioning is not deterministic ad there is no unique solution. So we propose a co-evolutionary method finding optimal fuzzy rules and proper fuzzy membership functions at the same time. Predator-Prey co-evolution and symbiotic co-evolution algorithms, typical approaching methods to co-evolution, are reviewed, and dynamic fitness landscape associated with co-evolution is explained. Our algorithm is that after constructing two population groups made up of rule base and membership function, by co-evolving these two populations, we find optimal fuzzy logic controller. By applying the propose method to a path planning problem of autonomous mobile robots when moving objects applying the proposed method to a pa h planning problem of autonomous mobile robots when moving objects exist, we show the validity of the proposed method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.354-360
• /
• 1998

In general, it is very difficult to find optimal fuzzy rules by experience when a system is dynamical and/or complex. Futhermore proper fuzzy partitioning is not deterministic and there is no unique solution. Therefore we propose a new design method of an optimal fuzzy logic controller, that is a co-evolutionary genetic algorithm finding optimal fuzzy rule and proper membership functions at the same time. We formalize the relation between fuzzy rules and membership functions in terms of fitness. We review the typical approaching methods to co-evolutionary genetic algorithms , and then classify them by fitness relation matrix. Applications of the proposed method to a path planning problem of autonomous mobile robots when moving objects exist are presented to demonstrate the performance and effectiveness of the method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.223-226
• /
• 1997

Usually, the Evolutionary Algorithms(EAs) are considered more efficient for optimal, system design because EAs can provide higher opportunity for obtaining the global optimal solution. This paper presents a mechanism of co-evolution consists of the two genetic algorithms(GAs). This mechanism includes host populations and parasite populations. These two populations are closely related to each other, and the parasite populations plays an important role of searching for useful schema in host populations. Host population represented by feedforward neural network and the result of co-evolution we will find the optimal structure of the neural network. We used the genetic algorithm that search the structure of the feedforward neural network, and evolution strategies which train the weight of neuron, and optimize the net structure. The validity and effectiveness of the proposed method is exemplified on the stabilization and position control of the inverted-pendulum system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.82-85
• /
• 2003

In this paper, in order to deduce the deep structure of a set of fuzzy rules from the surface structure, we use co-evolutionary algorithm based on modified Nash GA. This algorithm coevolves membership functions in antecedents and parameters in consequents of fuzzy rules. We demonstrate this co-evolutionary algorithm and apply to the mobile robot control. From the result of simulation, we compare modified Nash GA with the other co-evolution algorithms and verify the efficacy of this algorithm through application to fuzzy systems.