Simultaneous Localization and Mapping using Stereo Cameras

Abstract

This thesis studies the Simultaneous Localization and Mapping (SLAM) algorithm bases on image and uses it on mobile robotics Mobile robots are computer-controlled devices that have the capability to move around in an unknown environment Mobile robots are extensively applied in fields such as industry military and unsafe environments One of the important topics for research and development of mobile robots researchers is how to guide the vehicle automatically and safely move from one place to another so it must know where it is and what its surround is In this algorithm we use stereo camera to acquire two images of environment in the same time and use Speeded-Up Robust Features (SURF) algorithm to detect and match features on the image By way of similar relationship the distance between the landmark and the robot can be calculated by the pair of images Estimations of vehicle motion and landmarks’ positions are computed within a standard Extended Kalman Filter frame work The robot will continuously move execute the localization step and then update the map This map can provide mobile robotics localization and navigation

Date of Award	2014 Jan 28
Original language	English
Supervisor	Ta-Chung Wang (Supervisor)