Efficient scene simulation for robust monte carlo localization using an RGB-D camera

M.F. Fallon, H. Johannsson, J.J. Leonard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents Kinect Monte Carlo Localization (KMCL), a new method for localization in three dimensional indoor environments using RGB-D cameras, such as the Microsoft Kinect. The approach makes use of a low fidelity a priori 3-D model of the area of operation composed of large planar segments, such as walls and ceilings, which are assumed to remain static. Using this map as input, the KMCL algorithm employs feature-based visual odometry as the particle propagation mechanism and utilizes the 3-D map and the underlying sensor image formation model to efficiently simulate RGB-D camera views at the location of particle poses, using a graphical processing unit (GPU). The generated 3D views of the scene are then used to evaluate the likelihood of the particle poses. This GPU implementation provides a factor of ten speedup over a pure distance-based method, yet provides comparable accuracy. Experimental results are presented for five different configurations, including: (1) a robotic wheelchair, (2) a sensor mounted on a person, (3) an Ascending Technologies quadrotor, (4) a Willow Garage PR2, and (5) an RWI B21 wheeled mobile robot platform. The results demonstrate that the system can perform robust localization with 3D information for motions as fast as 1.5 meters per second. The approach is designed to be applicable not just for robotics but other applications such as wearable computing.
Original languageEnglish
Title of host publicationRobotics and Automation (ICRA), 2012 IEEE International Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1663-1670
Number of pages8
ISBN (Electronic)978-1-4673-1404-6
ISBN (Print)978-1-4673-1403-9
DOIs
Publication statusPublished - 2012

Keywords

  • Monte Carlo methods
  • graphics processing units
  • image colour analysis
  • mobile robots
  • robot vision
  • solid modelling
  • 3D information
  • GPU
  • KMCL algorithm
  • Kinect Monte Carlo localization
  • Microsoft Kinect
  • RGB-D camera
  • RWI B21 wheeled mobile robot platform
  • a priori 3-D model
  • ascending technologies quadrotor
  • efficient scene simulation
  • feature-based visual odometry
  • graphical processing unit
  • large planar segments
  • particle propagation mechanism
  • pure distance-based method
  • robotic wheelchair
  • robust Monte Carlo localization
  • sensor image formation model
  • three dimensional indoor environments
  • wearable computing
  • willow garage PR2
  • Buildings
  • Cameras
  • Mathematical model
  • Robot sensing systems
  • Solid modeling

Fingerprint

Dive into the research topics of 'Efficient scene simulation for robust monte carlo localization using an RGB-D camera'. Together they form a unique fingerprint.

Cite this