DocumentCode :
2099873
Title :
Scan matching in a probabilistic framework
Author :
Censi, Andrea
Author_Institution :
Dipartimento di Informatica e Sistemistica, Universita degli Studi di Roma, Rome
fYear :
2006
fDate :
15-19 May 2006
Firstpage :
2291
Lastpage :
2296
Abstract :
We describe an interpretation of scan matching as a probability distribution approximation problem and we propose an algorithm that, employing a particle approximation to the target distribution, can take advantage of the knowledge of the evolution model and provide an estimate of the matching uncertainty. Experiments show it can work in unstructured environments, it is reliable to severe sensor occlusions and it handles under constrained situations gracefully
Keywords :
approximation theory; laser ranging; maximum likelihood estimation; robot vision; statistical distributions; particle approximation; probability distribution approximation problem; scan matching; target distribution; Acoustic sensors; Approximation algorithms; Availability; Bayesian methods; Laser modes; Pattern recognition; Probability distribution; Sensor phenomena and characterization; Simultaneous localization and mapping; Uncertainty;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation, 2006. ICRA 2006. Proceedings 2006 IEEE International Conference on
Conference_Location :
Orlando, FL
ISSN :
1050-4729
Print_ISBN :
0-7803-9505-0
Type :
conf
DOI :
10.1109/ROBOT.2006.1642044
Filename :
1642044
Link To Document :
بازگشت