Logo U. Osnabrueck Institute of Computer Science — Knowledge-Based Systems Research Group

Heuristic-Based Laser Scan Matching for Outdoor 6D SLAM

by Andreas Nüchter, Kai Lingemann, Joachim Hertzberg and Hartmut Surmann

Heuristic-Based Laser Scan Matching for Outdoor 6D SLAM


Here we want to give another example for a closing loop experiment considering six degrees of freedom. Robot motion and localization on natural surfaces, e.g., driving with a mobile robot outdoor, must regard these degrees of freedom. Scan matching, combined with a heuristic for closed loop detection and a global relaxation method, results in a highly precise mapping system for outdoor environments. Download the paper here.

The Video

The video shows the 6D SLAM result and additionally a smooth trajectory has been computed. The video shows the path the robot has taken, i.e., the camera follows the trajectory.

Video (DiVX 500 MB)
Video (low-res DiVX 206 MB)
Video (low-res MPEG 72 MB)

Please use a DivX player to show the video.

The 3D Map

Click images to enlarge!
final map, top view
Note: The grid at the starting point denotes an area of 20 x 20 m2 for scale comparison.

Here are some 3D views:
final map, single rendered view final map, single rendered view final map, single rendered view final map, single rendered view final map, single rendered view final map, single rendered view final map, single rendered view

Reference

Andreas Nüchter, Kai Lingemann, Joachim Hertzberg, and Hartmut Surmann. Heuristic-Based Laser Scan Matching for Outdoor 6D SLAM, in KI 2005: Advances in Artificial Intelligence. 28th Annual German Conference on AI, Proceedings Springer LNAI vol. , Koblenz, Germany, September 2005, (accepted). [Get Paper (PDF)] [Get Paper (HTML)]


Andreas Nüchter, June 2005