Monocular vision based indoor simultaneous localisation and mapping for quadrotor platform

摘要

An autonomous robot acting in an unknown dynamic environment requires a detailed understanding
\nof its surroundings. This information is provided by mapping algorithms which are
\nnecessary to build a sensory representation of the environment and the vehicle states. This aids
\nthe robot to avoid collisions with complex obstacles and to localize in six degrees of freedom i.e.
\nx, y, z, roll, pitch and yaw angle. This process, wherein, a robot builds a sensory representation
\nof the environment while estimating its own position and orientation in relation to those sensory
\nlandmarks, is known as Simultaneous Localisation and Mapping (SLAM).
\nA common method for gauging environments are laser scanners, which enable mobile robots to
\nscan objects in a non-contact way. The use of laser scanners for SLAM has been studied and
\nsuccessfully implemented. In this project, sensor fusion combining laser scanning and real time
\nimage processing is investigated. Hence, this project deals with the implementation of a Visual
\nSLAM algorithm followed by design and development of a quadrotor platform which is equipped
\nwith a camera, low range laser scanner and an on-board PC for autonomous navigation and
\nmapping of unstructured indoor environments.
\nThis report presents a thorough account of the work done within the scope of this project.
\nIt presents a brief summary of related work done in the domain of vision based navigation
\nand mapping before presenting a real time monocular vision based SLAM algorithm. A C++
\nimplementation of the visual slam algorithm based on the Extended Kalman Filter is described.
\nThis is followed by the design and development of the quadrotor platform. First, the baseline
\nspeci cations are described followed by component selection, dynamics modelling, simulation
\nand control. The autonomous navigation algorithm is presented along with the simulation
\nresults which show its suitability to real time application in dynamic environments. Finally,
\nthe complete system architecture along with 
\night test results are described.