Defesa de Exame de Qualificação – Seyed Jamalaldin Haddadi – 13/04/2018
13/04/2018 17:17
| Defesa de Exame de Qualificação | |
| Aluno | Seyed Jamalaldin Haddadi |
| Orientador | Prof. Eugênio de Bona Castelan Neto, Dr. – DAS/UFSC |
| Data
Local |
13/04/2018 13h30 (sexta-feira)
Sala PPGEAS II (piso superior) |
| Prof. Leandro Buss Becker, Dr. – DAS/UFSC (presidente)
Prof. Guilherme Vianna Raffo, Dr. – UFMG Prof. Henrique Simas, Dr. – EMC/UFSC Prof. Fábio Luis Baldissera, Dr. – DAS/UFSC (suplente) |
|
| Título
|
Pose Estimation and Indoor Navigation of Quad Rotors using ORB-SLAM |
| Abstract: This study addresses the problem of pose estimation with accuracy for Low-Cost Quadrotor using visual odometry and sensor data fusion and also its use for making autonomous indoor navigation in a known GPS-denied environment. For pose estimation, two kinds of modules are employed: i) a Simultaneous Localization and Mapping (SLAM) system with Oriented Fast and rotated BRIEF (ORB) features, also known as ORB_SLAM; and ii) an Extended Kalamn Filter (EKF) that is applied for combining the obtained pose from ORB_SLAM and Inertial Measurement Unit (IMU). Since the SLAM process is done by the frontal monocular camera of Quadrotor, developing scale estimation in order to calculate the scale of map with minimum error is necessary. In the present stage of this work, a proportional Integral Derivative (PID) controller law is utilized to conduct the maneuver of robot. Also to perform the practical experiments, measured data are sent via Wi-Fi to a ground station in order to perform the data processing. To show the performance of the proposed algorithm, two experiments are carried out using an AR-Drone 2.0 quadrotor. The first one is position holding that shows the robustness of estimated position of system in hovering situation after take-off and the second one is an indoor trajectory tracking that illustrates the difference between real position and estimated position. The goal of this study is to show the validity of the present work and also showing some of its drawbacks and challenges to overcome. | |
