A Robust Pose Estimation Algorithm for Mobile Robot Based on Clusters

Authors:
Yuhua Xu;Chongwei Zhang;Wei Bao;Ling Su;Mulan Wang
Affiliations:
School of Electrical Engineering and Automation, Anhui, China 230009;School of Electrical Engineering and Automation, Anhui, China 230009;School of Electrical Engineering and Automation, Anhui, China 230009;School of Computer and Science, Hefei University of Technology, Anhui, China 230009;Jiangsu Province College Key Laboratory of Advanced Numerical Control Technology, Nanjing Institute of Technology, Email: robot802@hotmail.com, Jiangsu, China 211167
Venue:
ICIRA '08 Proceedings of the First International Conference on Intelligent Robotics and Applications: Part I
Year:
2008

Citing 5
Cited 0

Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Computer Vision: A Modern Approach

Computer Vision: A Modern Approach
Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans

Journal of Intelligent and Robotic Systems
MonoSLAM: Real-Time Single Camera SLAM

IEEE Transactions on Pattern Analysis and Machine Intelligence
Vision-based global localization and mapping for mobile robots

IEEE Transactions on Robotics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Pose estimation is a key component of a mobile robot system. In this paper, a new pose estimation method for mobile robot is developed based on 2D laser radar. Firstly, scan data points in each frame are divided into clusters. Then the current scan and the previous scan are matched according to the clusters to obtain two types of match clusters, holonomic matches and nonholonomic. For a pair of holonomic match clusters, their both pairs of endpoints and centroids are considered as match points, and for nonholonomic match clusters, only endpoints are considered as match points. Finally, RANSAC algorithm is used to remove outliers and nonlinear least squares method is adopted to estimate the motion parameters of the mobile robot. Experimental results demonstrate that the approach achieves satisfactory performance in dynamic indoor environments and the results are compared with angle histogram algorithm.