Independent Local Mapping for Large-Scale SLAM

SLAM algorithms do not perform consistent maps for large areas mainly due to the uncertainties that become prohibitive when the scenario becomes larger and to the increase of computational cost. The use of local maps has been demonstrated to be well suited for mapping large environments, reducing computational cost and improving map consistency. This paper proposes a technique based on using independent local maps. Every time a loop is detected, these local maps are corrected using the information from local maps that overlap with them. Meanwhile a global stochastic map is kept through loop detection and minimization as it is done in the classical Hierarchical SLAM approach. This global level contains the relative transformations between local maps, which are updated once a new loop is detected. In addition, the information within the local maps is also corrected, maintaining always each local map separately. This approach requires robust data association algorithms, for instance, an adapted version of the JCBB algorithm. Experimental results show that our approach is able to obtain large maps areas with high accuracy.