2D RGB depth map building for outdoor mobile robots using Particle Filter

Yu Cheol Lee, Christiand, Joochan Sohn, Sunghoon Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes the RGB depth (RGB-D) map building for mobile robots based on accurate outdoor localization and perception sensors consisting of wheel odometer, global positioning system (GPS), and camera and laser range finder (LRF). A localization method based on Particle Filter (PF) is used to integrate the sensor data and the topological map. The sensors data include geo-locations, the relative moving positions and the traffic mark positions measured by GPS, odometer and camera. The topological map has information for converting domains between geo-and metric-locations of GPS and odometer. And it also gives the actual positions of traffic marks extracted from aerial or satellite images. In addition, we used also a 2D RGB-D map building method by matching information between RGB and depth by camera and LRF at estimated position from PF. An experiment has been performed in outdoor environment to validate the proposed method. Experimental results show the high accuracy RGB-D map that is able to use for navigation of mobile robot in outdoor environments.

Original languageEnglish
Title of host publicationCINTI 2012 - 13th IEEE International Symposium on Computational Intelligence and Informatics, Proceedings
Pages201-206
Number of pages6
DOIs
StatePublished - 2012
Event13th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2012 - Budapest, Hungary
Duration: 20 Nov 201222 Nov 2012

Publication series

NameCINTI 2012 - 13th IEEE International Symposium on Computational Intelligence and Informatics, Proceedings

Conference

Conference13th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2012
Country/TerritoryHungary
CityBudapest
Period20/11/1222/11/12

Fingerprint

Dive into the research topics of '2D RGB depth map building for outdoor mobile robots using Particle Filter'. Together they form a unique fingerprint.

Cite this