• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2717-2719
• /
• 2005

Generally, biped walking is difficult to control because a biped robot is a nonlinear system with various uncertainties. In this paper, we propose a hybrid control system to improve the efficiency of position tracking performance of biped locomotion. In our control system, the wavelet neural network (WNN) based on Sliding mode controller is used as a main controller which estimates a biped robot model, and the compensated controller is proposed to compensate the estimation error. A WNN is utilized to estimate uncertain and nonlinear system parameters, where the weights of WNN are trained by adaptive laws that are induced from the Lyapunov stability theorem. Finally, the effectiveness of the proposed control system is verified through computer simulations.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.424-426
• /
• 2005

We propose an analytic trajectory planning method using a wavelet neural network (WNN) for a natural and stable locomotion of the 9-link biped robot. We design a appropriate locomotion, which have a kick-action, by means of a ballastic walking model condition. In this paper, a WNN is used to interpolate the trajectory planed by the analytic method. Finally, we show the proposed trajectories through the computer simulation.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.1062-1065
• /
• 2002

We have evaluated the ability of a time-delayed artificial neural network (TDANN) to predict muscle forces using only eletromyographic(EMG) signals. To achieve this goal, tendon forces and EMG signals were measured simultaneously in the gastrocnemius muscle of a dog while walking on a motor-driven treadmill. Direct measurements of tendon forces were performed using an implantable force transducer and EMG signals were recorded using surface electrodes. Under dynamic conditions, the relationship between muscle force and EMG signal is nonlinear and time-dependent. Thus, we adopted EMG amplitude estimation with adaptive smoothing window length. This approach improved the prediction ability of muscle force in the TDANN training. The experimental results indicated that dynamic tendon forces from EMG signals could be predicted using the TDANN, in vivo.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.3
• /
• pp.269-282
• /
• 2007

This paper presents a robust control method via the intelligent adaptive backstepping design technique for stable walking of nine-link biped robots with unknown model uncertainties and external disturbances. In our control structure, the self recurrent wavelet neural network(SRWNN) which has the information storage ability is used to observe the uncertainties of the biped robots. The adaptation laws for all weights of the SRWNN are induced from the Lyapunov stability theorem, which are used for on-line controlling biped robots. Also, we prove that all signals in the closed-loop adaptive system are uniformly ultimately bounded. Through computer simulations of a nine-link biped robot with model uncertainties and external disturbances, we illustrate the effectiveness of the proposed control system.

• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.308-312
• /
• 2019

When one enters a space, perceives the material geometry of that space. Walking inside buildings or across the city is generating a geometry of moving bodies that fills the space. These two geometries coexist: a static geometry of the space and an invisible one of the moving bodies. The space that we actually experience, whether interior or exterior, is a continuous network of voids. Individuals' movement will fill the network of voids that we understand as "the city". Our environment of voids and borders is organized by the means of architecture and urbanism. The geometry generated by motion affects both the limits and the voids, thus space can be defined by the tandem of the moving bodies and their environment. We propose in this study a mean of investigating users' movement and thus understanding the qualities of space while introducing the concept of space scores as analytical maps and design tools.

• Journal of Integrative Natural Science
• /
• v.12 no.1
• /
• pp.14-19
• /
• 2019

In this paper, we propose a system for controlling the brightness of street lights by predicting pedestrian paths, identifying the position of pedestrians with motion sensing sensors and obtaining motion vectors based on past walking directions, then predicting pedestrian paths through the route prediction smart street lighting system. In addition, by using motion vector data, the pre-treatment process using linear interpolation method and the fuzzy system and neural network system were designed in parallel structure to increase efficiency and the rough set was used to correct errors. It is expected that the system proposed in this paper will be effective in securing the safety of pedestrians and reducing light pollution and energy by predicting the path of pedestrians in the detection of movement of pedestrians and in conjunction with smart street lightings.

• Journal of information and communication convergence engineering
• /
• v.22 no.2
• /
• pp.139-144
• /
• 2024

In this study, four types of fall detection systems - designed with YOLOPose, principal component analysis (PCA), convolutional neural network (CNN), and long short-term memory (LSTM) architectures - were developed and compared in the detection of everyday falls. The experimental dataset encompassed seven types of activities: walking, lying, jumping, jumping in activities of daily living, falling backward, falling forward, and falling sideways. Keypoints extracted from YOLOPose were entered into the following architectures: RAW-LSTM, PCA-LSTM, RAW-PCA-LSTM, and PCA-CNN-LSTM. For the PCA architectures, the reduced input size stemming from a dimensionality reduction enhanced the operational efficiency in terms of computational time and memory at the cost of decreased accuracy. In contrast, the addition of a CNN resulted in higher complexity and lower accuracy. The RAW-LSTM architecture, which did not include either PCA or CNN, had the least number of parameters, which resulted in the best computational time and memory while also achieving the highest accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.2
• /
• pp.300-308
• /
• 2002

This paper deals with the remote control of a quadruped robot by using network concept. In case we have to work out the designed plan under the irregular terrains and have the human friendly actions,. our robot will be required to have walking capability, and patterns with legs, which are designed like gaits of insert, dog and human. Our quadruped robot(called SERO) has not only the basic actions operated with sensors and actuators but also the various advanced walking trajectories, which are generated by Genetic Algorithm In addition, it has the remote controller in order to operate the remote actions such as generation of command via web browser and monitoring the robot status. In this paper the body and the controller structures are suggested and the results of kinematics analysis are also presented, All of the suggested motions of SERO are generated by PC simulation and implemented in real environment successfully.

• Journal of information and communication convergence engineering
• /
• v.2 no.2
• /
• pp.110-115
• /
• 2004

The prosthesis of current commercialized apparatus has considerable problems, requiring improvement. Especially, LLP(Lower Limb Prosthesis)-related problems have improved, but it cannot provide normal walking because, mainly, the gait control of the LLP does not fit with patient's gait manner. To solve this problem, HCI((Human Computer Interaction) that adapts and controls LLP postures according to patient's gait manner more effectively is studied in this research. The proposed control technique has 2 steps： 1) the multilayer neural network forecasts angles of gait of LLP by using the angle of normal side of lower limbs； and 2) the adaptive neural controller manages the postures of the LLP based on the predicted joint angles. According to the experiment data, the prediction error of hip angles was 0.32［deg.］, and the predicted error of knee angles was 0.12［deg.] for the estimated posture angles for the LLP. The performance data was obtained by applying the reference inputs of the LLP controller while walking. Accordingly, the control performance of the hip prosthesis improved by 80% due to the control postures of the LLP using the reference input when comparing with LQR controller.

• Convergence Security Journal
• /
• v.11 no.4
• /
• pp.31-36
• /
• 2011

Enterprise which has a core technology or organization which manages a core information will be walking into a critical situation like a ruins when organization's confidential information is outflowed. In the past confidential information that was leaked to the off-line, recently the outflow made possible through a variety of equipment at any time via the network based on the ubiquitous communication environment. In this paper, we propose to authenticate and block all packets transmitted via the network at real-time in order to prevent confidentials outflow. Especially in or der to differentiate between users who attempt to disclose confidentials, we propose to insert user's biometric informaion transparently at per-packet basis, and also verify a performance by simulation.