Incremental probabilistic geometry estimation for robot scene understanding

Author

Cahier, Louis-Kenzo ; Ogata, Tetsuya ; Okuno, Hiroshi G.

Author_Institution

Grad. Sch. of Inf., Univ. of Kyoto, Kyoto, Japan

fYear

2012

fDate

14-18 May 2012

Firstpage

3625

Lastpage

3630

Abstract

Our goal is to give mobile robots a rich representation of their environment as fast as possible. Current mapping methods such as SLAM are often sparse, and scene reconstruction methods using tilting laser scanners are relatively slow. In this paper, we outline a new method for iterative construction of a geometric mesh using streaming time-of-flight range data. Our results show that our algorithm can produce a stable representation after 6 frames, with higher accuracy than raw time-of-flight data.

Keywords

SLAM (robots); computational geometry; image representation; iterative methods; mesh generation; mobile robots; optical scanners; service robots; SLAM; geometric mesh; incremental probabilistic geometry estimation; iterative construction; mapping methods; mobile robots; robot scene understanding; scene reconstruction methods; service robots; streaming time-of-flight range data; tilting laser scanners; Cameras; Optical imaging; Probabilistic logic; Simultaneous localization and mapping; Surface reconstruction;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation (ICRA), 2012 IEEE International Conference on

Conference_Location

Saint Paul, MN

ISSN

1050-4729

Print_ISBN

978-1-4673-1403-9

Electronic_ISBN

1050-4729

Type

conf

DOI

10.1109/ICRA.2012.6225343

Filename

6225343