• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.3
• /
• pp.258-266
• /
• 2012

This paper describes a biped walking algorithm for a hydraulic humanoid robot on inclined floors. To realize stable and robust biped walking, the walking algorithm was divided into five control strategies. The first is a joint position control strategy. This strategy is for tracking desired joint position trajectories with a gain switching. The second is a multi-model based ZMP (Zero Moment Point) control strategy for dynamic balance. The third is a walking pattern flow control strategy for smooth transition from step to step. The fourth is an ankle compliance control, which increases the dynamic stability at the moment of floor contact. The last is an upright pose control strategy for robust walking on an inclined floor. All strategies are based on simple pendulum models and include practical sensory feedback in order to implement the strategies on a physical robot. Finally, the performance of the control strategies are evaluated and verified through dynamic simulations of a hydraulic humanoid on level and inclined floors.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.5
• /
• pp.423-430
• /
• 2013

In typical face recognition systems, the frontal view of face is preferred to reduce the complexity of the recognition. Thus individuals may be required to stare into the camera, or the camera should be located so that the frontal images are acquired easily. However these constraints severely restrict the adoption of face recognition to wide applications. To alleviate this problem, in this paper, we address the problem of tracking and recognizing faces in video captured with no environmental control. The face tracker extracts a sequence of the angle/size normalized face images using IVT (Incremental Visual Tracking) algorithm that is known to be robust to changes in appearance. Since no constraints have been imposed between the face direction and the video camera, there will be various poses in face images. Thus the pose is identified using a PCA (Principal Component Analysis)-based pose classifier, and only the pose-matched face images are used to identify person against the pre-built face DB with 5-poses. For face recognition, PCA, (2D)PCA, and $(2D)^2PCA$ algorithms have been tested to compute the recognition rate and the execution time.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.6
• /
• pp.553-562
• /
• 2015

This paper presents a strategy and an algorithm for levitation control of an over-actuated passive maglev tray system. The passive maglev tray system has more actuators than its degrees of freedom. The actuators of the system are switching when the tray travels longitudinally. Furthermore, the levitation forces of the actuators are non-homogeneous because the actuation devices are not in the moving platform. These characteristics make a limit in using conventional control approaches for levitation. For smooth actuator switching, the actuator force generation should be dependent on longitudinal positions of the tray. To enable constant pose tracking, this research introduces a control strategy and a control algorithm based on integral controllers on virtual variables. The states of the tray are estimated using a Kalman filter and fed to the proposed controller. The performances of the proposed control strategy and the algorithm are validated through tests.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.166-171
• /
• 2023

With significant advancements in the field of artificial intelligence, many novel algorithms and technologies have emerged. Currently, AI painting can generate high-quality images based on textual descriptions. However, it is often challenging to control details when generating images, even with complex textual inputs. Therefore, there is a need to implement additional control mechanisms beyond textual descriptions. Based on ControlNet, this passage describes a combined utilization of various local controls (such as edge maps and depth maps) and global control within a single model. It provides a comprehensive exposition of the fundamental concepts of ControlNet, elucidating its theoretical foundation and relevant technological features. Furthermore, combining methods and applications, understanding the technical characteristics involves analyzing distinct advantages and image differences. This further explores insights into the development of image generation patterns.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2393-2395
• /
• 2001

The mobile robot is used as an instrument of transportation in automated plant. But the greater part of the moving method is the wheel-type. The wheel-type robot is easier control than the track-type, However the track-type is better than the wheel-type in bad landform(bend landform, an incline plane, stairs). In this paper, we propose the navigation algorithm of track-type robot in order to improve a defect of wheel-type. We experiment in bend landfrom and even ground to differentiate the navigation method. To estimate robot pose, we use the 80196 in a close distance and the vision-board in a long distance. Each data is managed in main PC and then the part of managing correspond to every sensor. We also use twelve supersonic wave-sensors to recognize external surroundings. As the result of experiment, we analyze the algorithm of control and make possible surroundings-adaptation.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2414-2416
• /
• 2003

In this raper, we present a Wavelet Neural Network(WNN) approach to the solution of the tracking problem for mobile robots that possess complexity, nonlinearity and uncertainty. The neural network is constructed by the wavelet orthogonal decomposition to form a wavelet neural network that can overcome the problems caused by local minima of optimization and various uncertainties. This network structure is helpful to determine the number of the hidden nodes and the initial value of weights with compact structure. In our control method, the control signals are directly obtained by minimizing the difference between the reference track and the pose of a mobile robot that is controlled through a wavelet neural network. The control process is a dynamic on-line process that uses the wavelet neural network trained by the gradient-descent method. Through computer simulations, we demonstrate the effectiveness and feasibility of the proposed control method.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.2
• /
• pp.123-130
• /
• 2016

This paper describes the design and implementation scheme of HTS(Helmet Tracking System) providing coincident LOS(Line of Sight) between aircraft and HMD(Helmet Mounted Display) which displays flight and mission information on Pilot helmet. The functionality and performance of HMD system depends on the performance of helmet tracking system. The target of HTS system design is to meet real-time performance and reliability by predicting non-periodic latency and high accuracy performance. To prove an availability of a proposed approach, a robust hybrid scheme with a fusion optical and inertial tracking system are tested through a implemented test-bed. Experimental results show real-time and reliable tracking control in spite of external errors.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2508-2513
• /
• 2003

This paper presents a nuclear steam generator tube inspection/maintenance robot system. The robot assists in automatic non-destructive testing and the repair of nuclear steam generator tubes welded into a thick tube sheet that caps a hemispherical or quarter-sphere plenum which is a high-radiation area. For easy carriage and installation, the robot system consists of three separable parts: a manipulator, a water-chamber entering and leaving device for the manipulator and a manipulator base pose adjusting device. A software program to control and manage the robotic system has been developed on the NT based OS to increase the usability. The software program provides a robot installation function, a robot calibration function, a managing and arranging function for the eddy-current test, a real time 3-D graphic simulation function which offers remote reality to operators and so on. The image information acquired from the camera attached to the end-effecter is used to calibrate the end-effecter pose error and the time-delayed control algorithm is applied to calculate the optimal PID gain of the position controller. The developed robotic system has been tested in the Ulchin NPP type steam generator mockup in a laboratory.

• Health Policy and Management
• /
• v.3 no.2
• /
• pp.25-56
• /
• 1993

Hypertension has already become a serious health problem in many countries. Treatment is effective, however, and the detection and long-term management of those at risk pose sustained challenges. Community programs can be an important strategy for primary prevention of hypertention and for monitoring the progress and promoting compliance of hypertensive patients. Hwachon Health Demonstrain Project has designed community hypertention control program, especially emphasizing role of public health sector, and operate that model from 1990 at Hwachon county, Kwangwon province. This paper appraise the effectiveness of curent activities. Many paper appraise the effectiveness of curent activities. Many hypertensive persons who have not recognized his disease were identified and began hypertension treatment. However about two thirds of patients have not complied continuously with medical advice. Consequently, the project team redirects its efforts. Less emphasis is being placed screening and identification of patients, while more emphasis is being placed on increasing compliance with treatment recommendations. Some approches to improve hypertension control program are also discussed in the context of the field experience and literature on this suvjest.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.559-563
• /
• 2000

In this paper we describe a method for aligning a robot gripper using image information. The region of gripper is represented from HSI color model that has major advantage of brightness independence. In order to extract the feature points for vision based position control, we find the corners of gripper shape using polygonal approximation method which determines the segment size and curvature of each points. We apply the vision based scheme to the task of alignment of gripper to reach the desired position by 2 RGB cameras. Experiments are carried out to exhibit the effectiveness of vision based control using feature points from polygonal approximation of gripper.