Experimental investigation of a prediction algorithm for an indoor SLAM platform

Authors:
Jung-Fu Hou;Yu-Shin Chou;Yau-Zen Chang;Jing-Sin Liu
Affiliations:
Department of Mechanical Engineering, Chung-Gung University, Taiwan;Institute of Information Science, Academia Sinica, Taiwan;Department of Mechanical Engineering, Chung-Gung University, Taiwan;Institute of Information Science, Academia Sinica, Taiwan
Venue:
ICIRA'10 Proceedings of the Third international conference on Intelligent robotics and applications - Volume Part II
Year:
2010

Citing 7
Cited 0

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 comparison of line extraction algorithms using 2D range data for indoor mobile robotics

Autonomous Robots
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

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.