Localization is the process of knowing and updating
continuously a robot position with regards to its environment
based on sensor information. Localization strategies are required
for accurate mobile robot navigation and they should be adapted
to the new tendencies and tools. The main purpose of this work
is to develop a localization system that allows a mobile robot to
know its position at each moment as well as to identify when it
has gotten lost.
In this paper, localization is applied to a topologically defined
environment using Hidden Markov Models (HMMs) as
main probability algorithm. HMMs give a stochastic solution
applicable to discrete representations such as events associated
to sensorial actions. The developed topological localization system
requires an a priori environment representation, the acquisition
of perceptions related to events, the planning of a path as a
sequence of actions and perceptions and the navigation that
converts the sequence into real movements.
Finally, experiments have been carried out in a simulated
environment, their results show the feasibility of the localization
system and motivates the future test in real robotic platforms.
The results also encourage to integrate topological and metric
information in the probability distributions.