Implementation of Image-Based Visual Servo (IBVS) with Linear Quadratic Gaussian (LQG) Method for Yaw-Pitch Camera

• Main Author: MANGKUSASMITO (NIM : 23215012), FAKHRUDDIN
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/27130
• Institution: Institut Teknologi Bandung

Visual information has been used as sensor feedback to complete robotic applications, both in manufacturing, security, and even the entertainment industry, known as visual servoing. On platforms with 2 DOFs such as the Yaw-pitch camera platform, it can be used to perform surveillance tasks independently with other more complex platforms such as aircraft, Unmanned Aerial Vehicle (UAV), Unmanned Ground Vehicle (UGV), etc. Despite its simple operation the Yaw-pitch camera platform still requires a good control method to improve its performance especially when used in conjunction with other more complex platforms. <br /> <br /> In this research, will be implementation of Image Based Visual Servoing (IBVS) with Linear Quadratic Regulator (LQG) method. This method is applied with the assumption that the system is a regulator system, which keeps the system output always stable and there is a noise in the form of white noise on the system. This method also ensures that the closed loop system is stable in the sense of Lyapunov. <br /> <br /> The results of this study indicate that the design results IBVS controller with LQG method is as expected. The implementation results show that the system is capable of running the visual servoing task to keep the desired object always in the middle of the image area.