A Lazy, Online, and Hierarchical Optimization Approach for 2D and 3D Pose-Graphs Operating on Manifolds
In Proceedings of the International Conference on Robotics and Automation, (ICRA-2010), 03.5.-08.5.2010, Anchorage, Alaska, IEEE, 2010.
In this paper, we present a new hierarchical opti-
mization solution to the graph-based simultaneous localization
and mapping (SLAM) problem. During online mapping, the
approach corrects only the coarse structure of the scene and
not the overall map. In this way, only updates for the parts of
the map that need to be considered for making data associations
are carried out. The hierarchical approach provides accurate
non-linear map estimates while being highly efﬁcient. Our error
minimization approach exploits the manifold structure of the
underlying space. In this way, it avoids singularities in the
state space parameterization. The overall approach is accurate,
efﬁcient, designed for online operation, overcomes singularities,
provides a hierarchical representation, and outperforms a series
of state-of-the-art methods.