Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.

  

Simultaneous Localization and Mapping with Linear Features

Author(s):

C, Vitadello
Conference/Journal:

Master Thesis, FS 09
Abstract:

Simultaneous Localization and Mapping (SLAM) with Linear Features Simultaneous Localization and Mapping (SLAM) is one of the most challenging problems in robotics. The ultimate goal of SLAM is to enable robots to operate in an environment without a priori knowledge of obstacle locations: the robot acquires a map of its environment while simultaneously localizing itself relative to this map. This dual and interconnected task makes SKAM a particularly difficult problem. It is more than a mere localization problem: the map is unknown and has to be estimated along the way. It is also more difficult than mapping with known poses, because the robot path is unknown and has to be estimated along the way. Although many advancements towards the solution of the problem have been introduced in the recent years, SLAM is still an open research topic. The main goal of this project is to develop novel FastSLAM algorithms based on linear feature detection and optimal control. Most traditional FastSLAM algorithms and results are based on a point-wise representation of obstacles, and linear features are extracted with techniques that rely on a very high amount of information gathered by the robot, with cameras or very expensive laser scan sensors. Where walls and linear objects are the predominant map features and when the robot has a cheaper sensor set (US and IR sensors), linear feature representation may decrease the complexity of the problem even in the presence of more sparse data acquisition and thus lead to more efficient algorithms oriented to a cheaper robot category for exploration.

Year:

2009
Type of Publication:

(12)Diploma/Master Thesis
Supervisor:

J. Lygeros

No Files for download available.
% Autogenerated BibTeX entry
@PhdThesis { CVit:2009:IFA_3450
}
Permanent link