Mobile robot localisation using active vision

Abstract

Active cameras provide a mobile robot with the capability to fixate and track features over a wide field of view. However, their use emphasises serial attention focussing on a succession of scene features, raising the question of how this should be best achieved to provide localisation information. This paper describes a fully automatic system, able to detect, store and track suitable landmark features during goal-directed navigation. The robot chooses which of the available set of landmarks to track at a certain time to best improve its position knowledge, and decides when it is time to search for new features. Localisation performance improves on that achieved using odometry alone and shows significant advantages over passive structure-from-motion techniques. Rigorous consideration is given to the propagation of uncertainty in the estimation of the positions of the robot and scene features as the robot moves, fixates and shifts fixation. The paper shows how the estimates of these quantities are inherently coupled in any map-building system, and how features can reliably be re-found after periods of neglect, mitigating the “motion drift” problem often encountered in structure-from-motion algorithms.

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.