Publication type: 
Article in Proceedings 
Author: 
René Wagner, Udo Frese, Berthold Bäuml 
Title: 
Graph SLAM with Signed Distance Function Maps on a Humanoid Robot 
Book / Collection title: 
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Chicago, Illinois 
Year published: 
2014 
Abstract: 
For such common tasks as motion planning or object recognition robots need to perceive their environment and create a dense 3D map of it. A recent breakthrough in this area was the KinectFusion algorithm, which relies on step by step matching a depth image to the map via ICP to recover the sensor pose and updating the map based on that pose. In so far it ignores techniques developed in the graphSLAM area such as fusion with odometry, modeling of uncertainty and distributing an observed inconsistency over the map.
This paper presents a method to integrate a dense geometric truncated signed distance function (TSDF) representation as KinectFusion uses with a sparse parametric representation as common in graph SLAM. The key idea is to have local TSDF submaps attached to reference nodes in the SLAM graph and derive graphSLAM links via ICP by matching a map to a depth image. By moving these reference nodes according to the graphSLAM estimate, the overall map can be deformed without touching individual submaps so that rebuilding of submaps is only needed in case of significant deformation within a submap. Also, further information can be added to the graph as common in graph SLAM. Examples are odometry or the fact that the ground is roughly but not exactly planar. Additionally, the paper proposes a modification of the KinectFusion algorithm to improve handling of long range data by taking the range dependent uncertainty into account.

Internet: 
http://www.informatik.unibremen.de/agebv/downloads/published/wagner_iros_14.mp4 
PDF Version: 
http://www.informatik.unibremen.de/agebv/downloads/published/wagner_iros_14.pdf 
Status: 
Reviewed 
Last updated: 
24. 08. 2016 

