Simultaneous Localization and Mapping with Active Stereo Vision J. Diebel, K. Reuterswärd, and S. Thrun, Stanford University, Palo Alto, CA J. Davis, and R. Gupta, Honda Research, Mountain View, CA

Please see the research page for details on other projects.

Abstract— We present an algorithm for creating globally consistent three-dimensional maps from depth fields produced by camera-based range measurement systems. Our approach is specifically suited to dealing with the high noise levels and the large number of outliers often produced by such systems. Range data is filtered to reject outliers within each scan. The point-to-plane variant of ICP is used for local alignment, including weightings that favor nearby points and a novel outlier rejection strategy that increases the robustness for this class of data while eliminating the burden of user-specified thresholds. Global consistency is imposed on cycles by optimally distributing the cyclic discrepancy according to the local fit correlation matrices. The algorithm is demonstrated on a dataset collected by an active unstructured light space-time stereo vision system.

This paper was presented at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS04) in Sendai, Japan, in September 2004.

	Paper: IROS 2004 paper [PDF] [Bibtex].	9/26/2004
	Presentation: IROS 2004 presentation, in PPT format (movies not included).	10/2/2004
	Movie: Video of the scanning process: the robot moving about the conference room.	2/17/2004
	Movie: Animation of the direct output of the space-time stereo algorithm, rendered as 3d mesh.	2/12/2004
	Movie: Animation showing the ICP alignment process between two consecutive meshes.	3/13/2004
	Movie: Animation showing overlapping meshes, chaining together pairwise alignments in an open-loop manner.	3/12/2004
	Movie: Animation showing globally-aligned overlapping meshes after having closed the loop.	3/12/2004
	Movie: Animation showing the final model of the room after using a point-based rendering technique.	3/13/2004