Year: 2011
Type: dissertation
Abstract: Simultaneous Localization and Mapping (SLAM) do not result in consistent maps of large areas because\n\nof gradual increase of the uncertainty for long term missions. In addition, as the size of the map grows\n\nthe computational cost increases, making SLAM solutions unsuitable for on-line applications. This thesis\n\nsurveys SLAM approaches paying special attention to those approaches aimed to work on large\n\nscenarios. Special focus is given to existing underwater SLAM applications. A technique based on using\n\nindependent local maps together with a global stochastic map is presented. This technique is called\n\nSelective Submap Joining SLAM (SSJS). A global map contains relative transformations between local\n\nmaps, which are updated once a new loop is detected. Maps sharing several features are fused,\n\nmaintaining the correlation between landmarks and vehicle's pose. The use of local maps reduces\n\ncomputational costs and improves map consistency as compared to state of the art techniques.
Authors: Aulinas Masó, M Josep
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2263058343