http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김곤우(Gon-Woo Kim) 대한전기학회 2009 전기학회논문지 Vol.58 No.12
The fundamental research for the mobile robot navigation using the numerical optimization method is presented. We propose an image-based visual servo navigation algorithm for a wheeled mobile robot utilizing a ceiling mounted camera. For the image-based visual servoing, we define the composite image Jacobian which represents the relationship between the speed of wheels of a mobile robot and the robot's overall speed in the image plane. The rotational speed of wheels of a mobile robot can be directly related to the overall speed of a mobile robot in the image plane using the composite image Jacobian. We define the mobile robot navigation problem as an unconstrained optimization problem to minimize the cost function with the image error between the goal position and the position of a mobile robot. In order to avoid the obstacle, the modified cost function is proposed which is composed of the image error between the position of a mobile robot and the goal position and the distance between the position of a mobile robot and the position of the obstacle. The performance was evaluated using the simulation.
고정밀 위치인식 시스템에서의 위치 추적편이 완화를 통한 이동 로봇의 효율적 위치 추정
김곤우(Gon-Woo Kim),이상무(Sang-Moo Lee),임충혁(Chung-Hieog Yim) 제어로봇시스템학회 2008 제어·로봇·시스템학회 논문지 Vol.14 No.8
In this paper, we propose a high accurate geo-location system based on a single base station, where its location is obtained by Time-of-Arrival(ToA) and Direction-of-Arrival(DoA) of the radio signal. For estimating accurate ToA and DoA information, a MUltiple SIgnal Classification(MUSIC) is adopted. However, the estimation of ToA and DoA using MUSIC algorithm is a time-consuming process. The position tracking bias is occurred by the time delay caused by the estimation process. In order to mitigate the bias error, we propose the estimation method of the position tracking bias and compensate the location error produced by the time delay using the position tracking bias mitigation. For accurate self-localization of mobile robot, the Unscented Kalman Filter(UKF) with position tracking bias is applied. The simulation results show the efficiency and accuracy of the proposed geo-Iocation system and the enhanced performance when the Unscented Kalman Filter is adopted for mobile robot application.
김곤우(Gon-Woo Kim),차영엽(Young-Youp Cha) 대한전기학회 2011 전기학회논문지 Vol.60 No.7
The fundamental research for the mobile robot navigation using the numerical optimization method is presented. We define the mobile robot navigation problem as an unconstrained optimization problem to minimize the cost function with the pose error between the goal position and the position of a mobile robot. Using the nonlinear least squares optimization method, the optimal speeds of the left and right wheels can be found as the solution of the optimization problem. Especially, the rotational speed of wheels of a mobile robot can be directly related to the overall speed of a mobile robot using the Jacobian derived from the kinematic model. It will be very useful for applying to the mobile robot navigation. The performance was evaluated using the simulation.
전역경로계획을 위한 단경로 스트링에서 당기기와 밀어내기 SOFM을 이용한 방법의 비교
차영엽(Young-Youp Cha),김곤우(Gon-Woo Kim) 제어로봇시스템학회 2009 제어·로봇·시스템학회 논문지 Vol.15 No.4
This paper provides a comparison of global path planning method in single string by using pulled and pushed SOFM (Self-Organizing Feature Map) which is a method among a number of neural network. The self-organizing feature map uses a randomized small valued initial-weight-vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified SOFM method in this research uses a predetermined initial weight vectors of the one dimensional string, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward or reverse the input vector, by using a pulled- or a pushed-SOFM. According to simulation results one can conclude that the modified neural networks in single string are useful tool for the global path planning problem of a mobile robot. In comparison of the number of iteration for converging to the solution, the pushed-SOFM is more useful than the pulled-SOFM in global path planning for mobile robot.
3D LiDAR기반 그래프SLAM 구현을 위한 누적 키프레임 검출 방법
양은성(Eun-Sung Yang),김곤우(Gon-Woo Kim) 제어로봇시스템학회 2017 제어·로봇·시스템학회 논문지 Vol.23 No.3
In this paper, we propose a robust key frame extraction method using 3D LiDAR point cloud information for GraphSLAM. Key frame extraction is a very important issue for obtaining correlation between nodes in GraphSLAM. However, the 3D LiDAR point cloud information obtained from one frame does not have enough information to be used as a key frame. We calculate the amount of information through the features extracted from the point cloud information and accumulate frames until the enough information has been acquired to solve this problem. Through these processes, a key frame has been detected with sufficient information for use in GraphSLAM. We show that more accurate maps can be obtained using the proposed method by comparing the performance with the existing algorithm using Tracking and Mapping through experimentation.