http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Grey Neural Network-Based Forecasting System for Vision-Guided Robot Trajectory Tracking
Shih-Hung Yang,Chung-Hsien Chou,Chen-Fang Chung,Wen-Pang Pai,Tse-Han Liu,Yung-Sheng Chang,Jung-Che Li,Huan-Chan Ting,Yon-Ping Chen 제어로봇시스템학회 2011 제어로봇시스템학회 국제학술대회 논문집 Vol.2011 No.10
This paper presents a grey neural network-based forecasting system (GNNFS) in solving the prediction problem. GNNFS adopts a grey model to predict the signal and a neural network (NN) to forecast the prediction error of the grey model. A sequential batch learning (SBL) is developed to adjust the weights of the NN. The proposed GNNFS is applied to a binocular robot, called an Eye-Robot, for human-robot interaction which involved predicting the trajectory of a participant’s hand and tracking the hand. By applying the SBL, the GNNFS can gradually learn to predict the trajectory of the hand and track it well. The experimental results show that the GNNFS can carry out the SBL in real-time for vision-guided robot trajectory tracking.
A Vertically Intersected Dual Axes Modularized Actuator System (DAMA)
Ren-Jeng Wang,Han-Pang Hung,Tz-How Huang,His-Fan Liao 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10
A Vertically Intersected Dual Axes Modularized Actuator System (DAMA) designed for humanoid robots is developed in this paper. The DAMA consists of two independent joint systems, joint 01 and joint02. Joint 01 uses a harmonic drive while joint02 uses a cable arrangement. Based on the simulations of ADMAS and MATLAB software packages, the system dynamic properties can be observed. The system structure is further refined using finite element analysis. In addition, the hardware and software control systems of DAMA are developed. The architecture of hardware is composed of notebook computer, a USB to RS-232 module, an RS-232 to CAN Bus Module and two independent-joint controller modules. The software control system (user interface) is written by Visual C++ 2005 to enable users to manipulate a two-axial robot easily. The system employs a simple, but effective, PID scheme to independently control the DAMA’s two joints. The experimental result shows that, for an S curve input position command, the DAMA’s two independent joints rotate and track the command well. Hence, DAMA can be used as a generic module for a multiple degree-of-freedom system.