http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Autonomous flight of the rotorcraft-based UAV using RISE feedback and NN feedforward terms
Jongho Shin,H. Jin Kim,Youdan Kim,Warren E. Dixon 한국산업응용수학회 2013 한국산업응용수학회 학술대회 논문집 Vol.8 No.1
A position tracking control system is developed for a rotorcraft-based unmanned aerial vehicle (RUAV) using robust integral of the signum of the error (RISE) feedback and neural network (NN) feedforward terms. While the typical NN-based adaptive controller guarantees uniformly ultimately bounded stability, the proposed NN-based adaptive control system guarantees semiglobal asymptotic tracking of the RUAV using the RISE feedback control. The developed control system consists of an inner-loop and outer-loop. The inner-loop control system determines the attitude of the RUAV based on an adaptive NN-based linear dynamic model inversion (LDI) method with the RISE feedback. The outer-loop control system generates the attitude reference corresponding to the given position, velocity, and heading references, and controls the altitude of the RUAV by the LDI method with the RISE feedback. The linear model for the LDI is obtained by a linearization of the nonlinear RUAV dynamics during hover flight. Asymptotic tracking of the attitude and altitude states is proven by a Lyapunov-based stability analysis, and a numerical simulation is performed on the nonlinear RUAV model to validate the effectiveness of the controller.
Adaptive Range Estimation in Perspective Vision System Using Neural Networks
Shin, Jongho,Kwak, Kiho,Kim, Suseong,Kim, H. Jin IEEE 2018 IEEE/ASME transactions on mechatronics Vol.23 No.2
<P>This paper proposes an adaptive range estimation method in a perspective vision system using neural networks (NN). With a universal function approximation property of the NN, this study first defines the NN-based range value and the adaptive observer to determine the distance is designed with the known object motion, i.e., translational and rotational velocities. To remove the uncertainty between the true range and the estimated value, the proposed estimator utilizes a saturation function with a time-varying gain. The adaptive rules of the weight parameters of the NN and time-varying gain are derived using Lyapunov stability theory and the overall closed-loop stability is proven by introducing a deadzoned estimation error, which is composed of the estimation error and the saturation function. Finally, to validate the performance of the proposed method, experiments are conducted for the estimation of the relative distance between a target and a camera mounted on a multirotor unmanned aerial vehicle with an inertial measurement unit and a motion capture system.</P>
Adaptive feedback linearization using support vector regression
Jongho Shin,H. Jin Kim,Youdan Kim 제어로봇시스템학회 2009 제어로봇시스템학회 국내학술대회 논문집 Vol.2009 No.9
This paper presents adaptive feedback linearization using support vector regression. Support vector regression (SVR) has been proven to generate global solutions contrary to neural networks (NN), because SVR basically solves quadratic programming (QP) problems. With this advantage, the mathematical model based on the feedback linearization is first trained offline. In order to compensate the offline training error and unknown uncertainties in the control process, and to avoid the controller singularity problem, a stable adaptation rule is proposed using the concept of the virtual control. Stability of the overall system is analyzed by the uniformly ultimately bounded property in the nonlinear system theory. Simulations using a Van der pol system validate the performance of the proposed algorithm.
Adaptive Path-Following Control for an Unmanned Surface Vessel Using an Identified Dynamic Model
Shin, Jongho,Kwak, Dong Jun,Lee, Young-il IEEE 2017 IEEE/ASME transactions on mechatronics Vol.22 No.3
<P>This paper proposes a path-following control method for an unmanned surface vessel (USV) based on an identified dynamic model. To handle the USV dynamic-model effectively, a three degree-of-freedom model is employed instead of a full nonlinear dynamic model and linearized at specific equilibrium condition. The linearized model is identified with real data from several experiments by utilizing a particle swarm optimization method. Then, based on the identified model, an adaptive control algorithm is proposed to follow several waypoints and velocity command. The proposed control method utilizes virtual control input, dynamic surface control method, and adaptive terms to handle matched and unmatched uncertainties simultaneously. The overall closed-loop stability is analyzed by introducing deadzone errors composed of tracking error and saturation function. Finally, some experiment with a remodeled commercial fishing boat are conducted and analyzed to validate the performance of the proposed methods.</P>
JongHo Shin,Yun Kyung Shin,Yong Se Kim (사)한국CDE학회 2010 한국CAD/CAM학회 국제학술발표 논문집 Vol.2010 No.8
As an effort to provide students the opportunity in enhancing design creativity in a personalized adaptive manner, an exercise program that address cognitive elements of creativity has been devised so that personalized needs in specific elements could be addressed. We conducted an experiment with students in interdisciplinary, integrated design where the exercise program for cognitive creativity elements with self-reporting of affective states was assigned between two simple conceptual design tasks. The experiment result supports that the exercise program helps in enhancing design creativity. Employing the experiment results, we are using data mining approaches in understanding the relations among various characteristics of students and their learning experiences in this creativity enhancement exercise. Findings in the experiments as well as data mining results will be presented together with implications in design creativity education.
Model predictive flight control using adaptive support vector regression
Jongho Shin,H. Jin Kim,Sewook Park,Youdan Kim 한국산업응용수학회 2009 한국산업응용수학회 학술대회 논문집 Vol.2009 No.5
This paper explores an application of support vector regression (SVR) to model predictive control (MPC). SVR is employed to identify a dynamic system from input-output data, and the identified model is used for predicting the future states in the MPC framework. In order to deal with time-dependent perturbations, an online adaptation algorithm is proposed for compensating the error between the actual dynamics and identified model. The convergence property of the adaptation rule is discussed using discrete-time Lyapunov stability analysis. Finally, the proposed approach is applied to identification and flight control of a fixed-wing unmanned aircraft.