Sciweavers

ICRA
2007
IEEE

A Hybrid Active Global Localisation Algorithm for Mobile Robots

13 years 10 months ago
A Hybrid Active Global Localisation Algorithm for Mobile Robots
— Localisation is one of the most important tasks to be accomplished in order to realize the complete autonomy of a mobile robot. In this paper, a new strategy for global localisation is proposed. Applying this method a robot is able to safely initialise its position or relocalise itself in case of recovery of pose tracking failure. The algorithm presented adopts an hybrid approach. First a particle filter is used to generate hypotheses on the possible pose supposing that no movements are allowed to avoid collisions. Thereafter safe trajectories are planned and executed to reduce the remaining ambiguities while the hypotheses are monitored and validated by a set of parallel Extended Kalman Filters. The novelty of this approach stands on the ability to generate the pose hypotheses without any feature- based knowledge. As a consequence, a landmark-based description of the environment is no longer required for the algorithm execution.
Andrea Gasparri, Stefano Panzieri, Federica Pascuc
Added 03 Jun 2010
Updated 03 Jun 2010
Type Conference
Year 2007
Where ICRA
Authors Andrea Gasparri, Stefano Panzieri, Federica Pascucci, Giovanni Ulivi
Comments (0)