Normalized graph-cuts for large scale visual SLAM
Author(s)
Rogers, John G.
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Simultaneous Localization and Mapping (SLAM)
suffers from a quadratic space and time complexity per update
step. Recent advancements have been made in approximating
the posterior by forcing the information matrix to remain sparse
as well as exact techniques for generating the posterior in the
full SLAM solution to both the trajectory and the map. Current
approximate techniques for maintaining an online estimate of
the map for a robot to use while exploring make capacity-based
decisions about when to split into sub-maps. This paper
will describe an alternative partitioning strategy for online
approximate real-time SLAM which makes use of normalized
graph cuts to remove less information from the full map.
Sponsor
Date
2009-10
Extent
Resource Type
Text
Resource Subtype
Article