A Method for Registration of 3-D Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Shape registration using optimization for mobile robot navigation
Shape registration using optimization for mobile robot navigation
Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans
Journal of Intelligent and Robotic Systems
A relative map approach to SLAM based on shift and rotation invariants
Robotics and Autonomous Systems
A new methodology of mobile robot navigation: The agoraphilic algorithm
Robotics and Computer-Integrated Manufacturing
Topological SLAM using neighbourhood information of places
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Hi-index | 0.00 |
This paper presents a scheme for the indoor simultaneous localization and mapping (SLAM) problem. The scheme is based on the scan matching method and is treated as an optimization problem solve by the Simplex method. The two-dimensional distance transform method is used to facilitate the cost value evaluation. In order to register scanned maps with built map through maximum overlap between the maps, a predictive algorithm is proposed. The algorithm can not only reduce search scope but also discard unexpected objects that may cause false match. The approach is investigated by an experimental platform with differential drives. The ICP-SLAM is also implemented for performance comparison. Experimental result shows that the prediction algorithm can improve accumulation error in the indoor environment.