Visual Simultaneously Localization And Mapping (VSLAM) For UAV In GPS Denied Environments

Saat, Shahrizal and Md Saat, Mohd Shakir and Mohd Tumari, Mohd Zaidi and Abd Rashid, Wan Norhisyam and Wahid, Mohammad Khalid and Razali, Saifuddin and Abas, Mohammad Fadhil (2018) Visual Simultaneously Localization And Mapping (VSLAM) For UAV In GPS Denied Environments. Project Report. UTeM, Melaka, Malaysia. (Submitted)

Text (24 Pages) Visual Simultaneously Localization and Mapping (VSLAM) For UAV In GPS Denied Environments.pdf - Submitted Version Restricted to Registered users only Download (1MB)

Abstract

The main focus of this project is to present a case study of a Simultaneous Localization and Mapping (SLAM) on vehicle that will operate in real-world environments. The SLAM was implemented to provide localization estimates in environments, where there are static landmarks that are only rarely recognized by the vehicle or robot. The main idea of SLAM is to consider the features that enter and leave the environment as temporary landmarks that can be used in combination with the rarely seen static landmarks. Thus, SLAM can make up with another part to complete the robot system such as flight control, obstacle avoidance, navigation and other function on the future. The project is tested and verified in a curtain room with Robot Operating System (ROS). The project includes also a general discussion on how SLAM can be used in room with vehicle. The software development is using Linux OS in Ubuntu to run the ROS and SLAM. As a conclusion, this project is design to consider features that move in the environment using SLAM visual mapping.

Actions (login required)

View Item