• 제어로봇시스템학회논문지
• /
• 제11권12호
• /
• pp.1062-1067
• /
• 2005

This paper discusses a skeleton feature extraction method for ubiquitous robot system. The skeleton features are used to analyze human motion and pose estimation. In different conventional feature extraction environment, the ubiquitous robot system requires more robust feature extraction method because it has internal vibration and low image quality. The new hybrid silhouette extraction method and adaptive skeleton model are proposed to overcome this constrained environment. The skin color is used to extract more sophisticated feature points. Finally, the experimental results show the superiority of the proposed method.

• 한국지능시스템학회논문지
• /
• 제6권3호
• /
• pp.40-50
• /
• 1996

By using the neural networks(NN) as system identifier, the on-line self tuning method for fuzzy controller(FC) is proposed. In theis method, the learning of NN is carried out during control operation of FC and the cinsequent parameters of FC is tuned on-line automatically by means of system output errors backpropagated through NN. The Sugeno fuzzy model with constants as consequent parameters is selected for simplifying computation. In procedures of parameter tuning, the gradient descent method is used and the gradient vectors for adjusting the weight of NN are transferred as controller output errors. To evaluate the performance, the proposed method is applied to the inverted pendulum system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권1호
• /
• pp.224-241
• /
• 2015

Multiview plus depth (MVD) videos are widely used in free-viewpoint TV systems. The best-known technique to determine depth information is based on stereo vision. In this paper, we propose a novel local stereo matching algorithm which is radiometric invariant. The key idea is to use a combined matching cost of intensity and gradient based similarity measure. In addition, we realize an adaptive cost aggregation scheme by constructing an adaptive support window for each pixel, which can solve the boundary and low texture problems. In the disparity refinement process, we propose a four-step post-processing technique to handle outliers and occlusions. Moreover, we conduct stereo reconstruction tests to verify the performance of the algorithm more intuitively. Experimental results show that the proposed method is effective and robust against local radiometric distortion. It has an average error of 5.93% on the Middlebury benchmark and is compatible to the state-of-art local methods.

• 제어로봇시스템학회논문지
• /
• 제8권1호
• /
• pp.67-73
• /
• 2002

This paper presents the development of development of stabilization and tracking algorithms for a shipboard satellite antenna system. In order to stabilize the satellite antenna system designed in the previous work, a model for each control axis is derived and its parameters are estimated using a genetic algorithm, and the state feedback controller is designed based on the linearized model. Then a tracking algorithm is derived to overcome some drawbacks of the step tracking. The proposed algorithm searches for the best position using gradient-based formulae and signal intensities measured according to a search pattern. The effectiveness of both the stabilization and tracking algorithms is demonstrated through experiment using real-world data.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권3호
• /
• pp.210-217
• /
• 2010

This paper presents integrated path planning and collision avoidance for an omni-directional mobile robot. In this scheme, the autonomous mobile robot finds the shortest path by the descendent gradient of a navigation function to reach a goal. In doing so, the robot based on the proposed approach attempts to overcome some of the typical problems that may pose to the conventional robot navigation. In particular, this paper presents a set of analysis for an omni-directional mobile robot to avoid trapped situations for two representative scenarios: 1) Ushaped deep narrow obstacle and 2) narrow passage problem between two obstacles. The proposed navigation scheme eliminates the nonfeasible area for the two cases by the help of the descendent gradient of the navigation function and the characteristics of an omni-directional mobile robot. The simulation results show that the proposed navigation scheme can effectively construct a path-planning system in the capability of reaching a goal and avoiding obstacles despite possible trapped situations under uncertain world knowledge.

• 상하수도학회지
• /
• 제10권4호
• /
• pp.85-93
• /
• 1996

This study is to make a comparison between the node method and the pipeline method for the analysis of the water distribution systems. For these purposes, the two methods were applied to a pipeline system in series, an artificial distribution network and a real distribution network. The results are as follows. 1. The difference between the results of the two methods was increased with the increase of the hydraulic gradient and the length between two adjacent nodes. 2. When all pipe lengths between two adjacent nodes were larger than 200~300m and have the steep hydraulic gradient, it was found that the results of the two methods showed high differences. 3. The difference between the results of the two methods were negligible in the case of the real distribution system in which only 12% whole pipelines were longer than 30m and the longest pipe length was 850m.

• 제어로봇시스템학회논문지
• /
• 제22권1호
• /
• pp.46-52
• /
• 2016

We propose a new type of semi-global matching (SGM) in order to solve a streaking problem arising from conventional SGM. Conventional SGM imposes a penalty to a pixel when the disparity of the pixel differs from that of the previous pixel along a scan path, and thus, disparity changes are not easily allowed, causing the streaking effect. The road surface is an appropriate target for such an effect, because the colors of the surfaces are very similar, and the image pixels corresponding to the surfaces show disparities that change very smoothly along the viewing direction. In contrast to conventional SGM, the new type of SGM imposes penalties depending on the disparity gradients, and thus, the streaking effect is controlled. The experimental results show the effectiveness of the proposed SGM method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권3호
• /
• pp.209-215
• /
• 2014

Sequence tagging is the task of predicting frame-wise labels for a given input sequence and has important applications to diverse domains. Conventional methods such as maximum likelihood (ML) learning matches global features in empirical and model distributions, rather than local features, which directly translates into frame-wise prediction errors. Recent probabilistic sequence models such as conditional random fields (CRFs) have achieved great success in a variety of situations. In this paper, we introduce a novel discriminative CRF learning algorithm to minimize local feature mismatches. Unlike overall data fitting originating from global feature matching in ML learning, our approach reduces the total error over all frames in a sequence. We also provide an efficient gradient-based learning method via gradient forward-backward recursion, which requires the same computational complexity as ML learning. For several real-world sequence tagging problems, we empirically demonstrate that the proposed learning algorithm achieves significantly more accurate prediction performance than standard estimators.

• 제어로봇시스템학회논문지
• /
• 제7권12호
• /
• pp.985-992
• /
• 2001

This paper proposes a self-organizing fuzzy modeling(SOFUM)which an create a new hyperplane shaped cluster and adjust parameters of the fuzzy model in repetition. The suggested algorithm SOFUM is composed of four steps: coarse tuning. fine tuning cluster creation and optimization of learning rates. In the coarse tuning fuzzy C-regression model(FCRM) clustering and weighted recursive least squared (WRLS) algorithm are used and in the fine tuning gradient descent algorithm is used to adjust parameters of the fuzzy model precisely. In the cluster creation, a new hyperplane shaped cluster is created by applying multiple regression to input/output data with relatively large fuzzy entropy based on parameter tunings of fuzzy model. And learning rates are optimized by utilizing meiosis-genetic algorithm in the optimization of learning rates To check the effectiveness of the suggested algorithm two examples are examined and the performance of the identified fuzzy model is demonstrated via computer simulation.

• 제어로봇시스템학회논문지
• /
• 제8권2호
• /
• pp.97-103
• /
• 2002

This paper deals with a PWM(Pulse Width Modulation) current amplifier using digital controller in order to generate a gradient magnetic field far the MRI(Magnetic Resonance Image) system. Because of tolerance of discrete devices, it is difficult to set accurate values of the control parameters and to make an analog-controlling circuit. However, using digital controller, it is possible to set exact control parameters and to adopt a modern control techniques. It is shown that the digital controller will highly enhance the output current response and it will improve the quality of the MRI.