Navigation‎ > ‎

SLAM for Hybrid Mapping

SLAM for Hybrid Mapping
  • Researchers
    • Yong-Ju Lee (Ph.D. yongju_lee@korea.ac.kr)
  • Research Period
    • 2006.7 ~ 2007.10
  • Research Background
    • Indoor environments generally consist of visual features and range-based features. Therefore, a hybrid vision/grid map offers a intuitive and useful map to a human and robot.
    • Both can be exploited together as landmarks for SLAM.
    • Most conventional object recognizers for navigation need the prior knowledge of objects. However, teaching prior knowledge of an object by a human is time-consuming and tedious task.
            
            
                              Environment with both visual and range-based features

  • Research objectives
    • Development of a practical SLAM(Simultaneous Localization And Mapping) method to model the unknown environments through fusion of vision and range sensors.
  • Research Output
            
            
                                                                                     Hybrid vision / grid map built by SLAM

  • Paper 1 :  Yong-Ju Lee, Tae-Bum Kwon, Jae-Bok Song, SLAM of a Mobile Robot Using Thinning-based Topological Information, Int. Journal of Control, Automation and Systems, Vol. 5, No. 5, pp. 577-583, 2007.10. 
  • Paper 2 :  Yong-Ju Lee, Jae-Bok Song, Autonomous Recognition and Registration of Objects for Visual SLAM in Indoor Environments,  Proc. of Int. Conf. on Control, Automation and Systems, pp. 668-673, 2007.10.  
  • Paper 3 :  Yong-Ju Lee, Byung-Doo Yim, Jae-Bok Song, SLAM of a Mobile Robot Using IR sensor and Vision sensor, KSME Fall Annual Meeting, pp. 704-709, 2006. 
  • Paper 4 :  Yong-Ju Lee, Park Joong-Tae, Song Jae-Bok and Chung Woo Jin, SLAM of a Mobile Robot Using Thinning Information, CASS2006, 2006.06.
  • Paper 5 :  Yong-Ju Lee and Song Jae-Bok, SLAM of a Mobile Robot in Dynamic Enviroments, The joint conference on control, automation and systems, 2005.11.

* Last updated: 2012. 4. 27