This thesis focuses on the problem of enabling mobile robots to autonomously build
world models of their environments and to employ them as a reference to self–localization
and navigation.
For mobile robots to become truly autonomous and useful, they must be able of
reliably moving towards the locations required by their tasks. This simple requirement
gives raise to countless problems that have populated research in the mobile robotics
community for the last two decades. Among these issues, two of the most relevant
are: (i) secure autonomous navigation, that is, moving to a target avoiding collisions
and (ii) the employment of an adequate world model for robot self-referencing within
the environment and also for locating places of interest. The present thesis introduces
several contributions to both research fields.
Among the contributions of this thesis we find a novel approach to extend SLAM
to large-scale scenarios by means of a seamless integration of geometric and topological
map building in a probabilistic framework that estimates the hybrid metric-topological
(HMT) state space of the robot path. The proposed framework unifies the research areas
of topological mapping, reasoning on topological maps and metric SLAM, providing
also a natural integration of SLAM and the “robot awakening” problem.
Other contributions of this thesis cover a wide variety of topics, such as optimal
estimation in particle filters, a new probabilistic observation model for laser scanners
based on consensus theory, a novel measure of the uncertainty in grid mapping, an
efficient method for range-only SLAM, a grounded method for partitioning large maps
into submaps, a multi-hypotheses approach to grid map matching, and a mathematical
framework for extending simple obstacle avoidance methods to realistic robots.
Buscar en Dimension