Visual Hybrid SLAM: An Appearance-Based Approach to Loop Closure
Lorenzo Fernandez, Luis Paya, Oscar Reinoso, Arturo Gil, and David Valiente
Advances in Intelligent Systems and Computing Volume 252 ROBOT2013: First Iberian Robotics Conference Advances in Robotics, Volume 1  (Madrid (Spain), 28-29 November 2013)
Ed. Springer  ISBN:978-3-319-03412-6  ISSN:2194-5357  - 1, pp. 693-701

Abstract:


This paper proposes an appearance-based method to detect loop closure in visual SLAM (Simultaneous Localization and Mapping). To solve this problem, we make use of omnidirectional images and the internal odometry captured by a robot in a real indoor environment. We build an appearance-based model and, subsequently, two maps of the environment are constructed, one metric and other topological with relationships between them. These relationships are updated in each step of our hybrid approach. The topological map is a graph built from the appearance information in the scenes. A new node is added when the new visual information is different enough from the previous information. At the same time, we check a possible topological loop closure with previous nodes. On the other hand we estimate the metric position of the new pose using a Monte-Carlo approach with the aim of building a metric map. The experimental results demonstrate the reasonable performance of our method.