An algorithm to identify docking locations for autonomous surface vessels from 3-D LiDAR scans

Author

Esposito, Joel M. ; Graves, Mitchell

Author_Institution

Syst. Eng. Dept., United States Naval Acad., Annapolis, MD, USA

fYear

2014

fDate

14-15 April 2014

Firstpage

1

Lastpage

6

Abstract

In this paper we present a novel algorithm to identify docks (or piers) from Light Detection and Ranging (LiDAR) scans. The algorithm exploits the expected geometric features of the dock and does not require modifying the dock in any way. Our approach consists of a novel combination and application of open source tools for point cloud and image processing. In our limited testing on 8 fused data sets, the algorithm successfully identified a usable portion of all the docks with only one false positive (a seawall). The target application is automated docking (a.k.a. recovery) for small Unmanned Surface Vessels (USVs).

Keywords

computer vision; marine vehicles; mobile robots; optical radar; public domain software; 3-D LiDAR scans; USV; automated docking; autonomous surface vessels; docking locations; expected geometric features; image processing; open source tools; point cloud; unmanned surface vessels; Data collection; Distance measurement; Google; Laser radar; Lasers; Three-dimensional displays; Vehicles; LiDAR; Object Recognition; Unmanned Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Technologies for Practical Robot Applications (TePRA), 2014 IEEE International Conference on

Conference_Location

Woburn, MA

Print_ISBN

978-1-4799-4606-8

Type

conf

DOI

10.1109/TePRA.2014.6869160

Filename

6869160