• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2006.11a
• /
• pp.335-338
• /
• 2006

The more deeply the researches make progress in ocean researches including the seabed resource investigation or the oceanic ecosystem investigation, the more important the role of UUV gets. In case of study on the deep sea, there are difficulties in telecommunications between AUV and ships, and in data communication and recharging. Therefore, docking is required. In AUV docking system, the AUV should identify the position of docking and make contact with a certain point of docking device. MOERI (Maritime & Ocean Engineering Research Institute), KORDI has conducted the docking testing on AUV ISIMI in KORDI Ocean Engineering Water Tank. As AUV ISIMI approachs the docking device, it is presented that attitude is unstable, because the lights Which is on Image Frame are disappeared. So we fix the rudder and stem, if the lights on Image Frame are reaching the specific area in the Image Frame. In this paper, we intend to solve the problems that were found in the testing, which, first, will be identified via simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.4
• /
• pp.65-73
• /
• 1997

This paper proposes a new method of the structure pruning of dynamic recurrent neural networks (DRNN) using evolutionary computations. In general, evolutionary computations are population-based search methods, therefore it is very useful when several different properties of neural networks need to be optimized. In order to prune the structure of the DRNN in this paper, we used the evolutionary programming that searches the structure and weight of the DRNN and evolution strategies which train the weight of neuron and pruned the net structure. An addition or elimination of the hidden-layer's node of the DRNN is decided by mutation probability. Its strategy is as follows, the node which has mhnimum sum of input weights is eliminated and a node is added by predesignated probability function. In this case, the weight is connected to the other nodes according to the probability in all cases which can in- 11:ract to the other nodes. The proposed pruning scheme is exemplified on the stabilization and position control of the inverted-pendulum system and visual servoing of a robot manipulator and the effc: ctiveness of the proposed method is demonstrated by numerical simulations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.375-381
• /
• 2005

Usually genetic algorithms are used to design optimal system. However the performance of the algorithm is determined by the fitness function and the system environment. It is expected that a co-evolutionary algorithm, two populations are constantly interact and co-evolve, is one of the solution to overcome these problems. In this paper we propose three types of co-evolutionary algorithm to solve GA-Hard problem. The first model is a competitive co-evolutionary algorithm that solution and environment are competitively co-evolve. This model can prevent the solution from falling in local optima because the environment are also evolve according to the evolution of the solution. The second algorithm is schema co-evolutionary algorithm that has host population and parasite (schema) population. Schema population supply good schema to host population in this algorithm. The third is game model-based co-evolutionary algorithm that two populations are co-evolve through game. Each algorithm is applied to visual servoing, robot navigation, and multi-objective optimization problem to verify the effectiveness of the proposed algorithms.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.4
• /
• pp.358-365
• /
• 2017

In this paper, we propose an object recognition method using image information to improve the efficiency of visual servoingfor industrial manipulators in industry. This is an image-processing method for real-time responses to an abnormal situation or to external environment change in a work object by utilizing camera-image information of an industrial manipulator. The object recognition method proposed in this paper uses the Otsu method, a thresholding technique based on separation of the V channel containing color information and the S channel, in which it is easy to separate the background from the HSV channel in order to improve the recognition rate of the existing Harris Corner algorithm. Through this study, when the work object is not placed in the correct position due to external factors or from being twisted,the position is calculated and provided to the industrial manipulator.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.29-37
• /
• 1999

In general, the information processing capability of a neural network is determined by its architecture and efficient training patterns. However, there is no systematic method for designing neural network and selecting effective training patterns. Evolutionary Algorithms(EAs) are referred to as the methods of population-based optimization. Therefore, EAs are considered as very efficient methods of optimal system design because they can provide much opportunity for obtaining the global optimal solution. In this paper, we propose a new method for finding the optimal structure of neural networks based on competitive co-evolution, which has two different populations. Each population is called the primary population and the secondary population respectively. The former is composed of the architecture of neural network and the latter is composed of training patterns. These two populations co-evolve competitively each other, that is, the training patterns will evolve to become more difficult for learning of neural networks and the architecture of neural networks will evolve to learn this patterns. This method prevents the system from the limitation of the performance by random design of neural networks and inadequate selection of training patterns. In co-evolutionary method, it is difficult to monitor the progress of co-evolution because the fitness of individuals varies dynamically. So, we also introduce the measurement method. The validity and effectiveness of the proposed method are inspected by applying it to the visual servoing of robot manipulators.