Robot Localization and Navigation With Visual Markers

From AIRWiki
Jump to: navigation, search
Robot Localization and Navigation With Visual Markers
Short Description: Robot Localization and Navigation With Visual Markers
Coordinator: MatteoMatteucci (matteo.matteucci@polimi.it)
Tutor: MatteoMatteucci (matteo.matteucci@polimi.it), AndreaBonarini (andrea.bonarini@polimi.it)
Collaborator: SimoneCeriani (ceriani@elet.polimi.it)
Students: AndreaPremarini (ultramito@gmail.com), AndreaScalise (andrea.scalise@aol.it)
Research Area: Robotics
Research Topic: Robot development
Start: 2011/09/01
End: 2012/03/30
Status: Closed
Level: Ms
Type: Thesis


The aim of this project is to create a C++ library that enables mobile robots to build a map of the unknown (a priori) surrounding environment and in the same time to localize themselves within such map, with the help of visual markers (such as data matrix) present in the environment. This goal can be achived using the MoonSLAM framework, which implements a Simultaneous Localization and Mapping algorithm, based on the Extended Kalman Filter to minimize the measurement error, and considering the visual markers detected as SLAM landmarks.