Autonomous Localization and Mapping for Mobile Robot Based on ORB-SLAM

  • Hongwei MoEmail author
  • Xiaosen Chen
  • Kai Wang
  • Haoran Wang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 528)


We aim to realize autonomous localization and mapping for mobile robot while no prior knowledge of its environment provided, based on one of the state-of-the-art SLAM algorithm called ORB-SLAM. A local 3D point cloud map is constructed, through the depth information acquired from RGB-D sensor and corresponding camera poses estimated from ORB-SLAM, which is then transformed to a 2D occupancy grid map using octree. Based on the 2D map, an information-theoretic exploration algorithm is used to travel through all the environment. Finally, experiments are carried out in a mobile robot.


Autonomous exploration Mobile robot ORB-SLAM 


  1. 1.
    S. Thrun, W. Burgard, D. Fox, Probabilistic Robotics (MIT Press, 2005)Google Scholar
  2. 2.
    S. Thrun, Y. Liu, D. Koller et al., Simultaneous localization and mapping with sparse extended information filters. Int. J. Rob. Res. 23(7–8), 693–716 (2004)Google Scholar
  3. 3.
    G. Klein, D. Murray, Parallel tracking and mapping for small AR workspaces, in IEEE and ACM International Symposium on Mixed and Augmented Reality (IEEE Computer Society, 2007), pp. 1–10Google Scholar
  4. 4.
    C. Forster, M. Pizzoli, D. Scaramuzza, SVO: fast semi-direct monocular visual odometry, in IEEE International Conference on Robotics and Automation (IEEE, 2014), pp. 15–22Google Scholar
  5. 5.
    J. Engel, T. Schöps, D. Cremers, LSD-SLAM: large-scale direct monocular slam, in Computer Vision—ECCV 2014 (Springer International Publishing, 2014), pp. 834–849Google Scholar
  6. 6.
    R. Mur-Artal, J.M.M. Montiel et al., ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Rob. 31(5), 1147–1163 (2015)CrossRefGoogle Scholar
  7. 7.
    R.A. Newcombe, S.J. Lovegrove, A.J. Davison, DTAM: dense tracking and mapping in real-time, in IEEE International Conference on Computer Vision (IEEE, 2011), pp. 2320–2327Google Scholar
  8. 8.
    R.A. Newcombe et al., KinectFusion: real-time dense surface mapping and tracking, in IEEE International Symposium on Mixed and Augmented Reality (IEEE, 2012), pp. 127–136Google Scholar
  9. 9.
    F. Endres, J. Hess, J. Sturm et al., 3-D mapping with an RGB-D camera. IEEE Trans. Rob. 30(1), 177–187 (2017)CrossRefGoogle Scholar
  10. 10.
    A. Elfes, Robot navigation: integrating perception, environmental constraints and task execution within a probabilistic framework. Lect. Notes Comput. Sci. 1093, 91–130 (1996)CrossRefGoogle Scholar
  11. 11.
    S. Bai, J. Wang, K. Doherty et al., Inference-enabled information-theoretic exploration of continuous action spaces. Rob. Res (2018)Google Scholar
  12. 12.
    S. Bai, J. Wang, F. Chen et al., Information-theoretic exploration with Bayesian optimization, in IEEE/RSJ International Conference on Intelligent Robots and Systems (IEEE, 2016), pp. 1816–1822Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Hongwei Mo
    • 1
    Email author
  • Xiaosen Chen
    • 1
  • Kai Wang
    • 1
  • Haoran Wang
    • 1
  1. 1.School of AutomationHarbin Engineering UniversityHarbinChina

Personalised recommendations