Vision-Based Multi-Robot Simultaneous Localization and Mapping

  • Authors:
  • Affiliations:
  • Venue:
  • CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we present a vision-based approachfor the multi-robot Simultaneous Localization andMapping (SLAM) problem. We study the case of ateam of robots equipped with a single camera andcollaborating in the same worksite. We propose tocalculate the location of the robots by using a collectionof sparse views of the planar surface on whichthese robots are moving. The camera motions are estimatedusing inter-image homographies computedfrom the matching of overhead transformed views.Results of map generated from the estimated robotlocations are presented.