This paper proposes extending Monte Carlo Localization methods with visual information in order to build a long term robot localization system. This system is aimed to work in crowded and non-planar scenarios, where 2D laser rangefinders may not always be enough to match the robot position with the map. Thus, visual place recognition will be used in order to obtain robot position clues that can be used to detect when the robot is lost and also to reset its positions to the right one. The paper presents experimental results based on datasets gathered with a real robot in challenging scenarios.
No takes yet. Share an insight, caveat, or question.
Pérez et al. (2014) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: