Information Based Exploration with Panoramas and Angle Occupancy Grids

  • Daniel Mox
  • Anthony Cowley
  • M. Ani Hsieh
  • C. J. Taylor
Part of the Springer Proceedings in Advanced Robotics book series (SPAR, volume 6)


In this work we present a multi-robot information based exploration strategy with the goal of constructing high resolution 3D maps. We use a Cauchy–Schwarz Quadratic Mutual Information (CSQMI) based objective which operates on a novel angle enhanced occupancy grid to guide robots in the collection of RGBD panoramas, which have been shown to provide memory efficient high quality representations of space. To intelligently collect panoramas, we introduce the angle enhanced occupancy grid which emphasizes perspective in addition to coverage, a characteristic we believe results in the construction of higher quality maps than traditional occupancy grid methods. To show this, we conduct simulations and compare our approach with frontier exploration. Using our angle enhanced occupancy grid, only 11.4% of decimeter wall segments were covered by fewer than 20 pixels as compared with 33.5% for the frontier method.



The authors gratefully acknowledge the support of ARL grant W911NF-08-2-0004 and NSF grant OISE-1131011.


  1. 1.
    Charrow, B., Liu, S., Kumar, V., Michael, N.: Information-theoretic mapping using Cauchy–Schwarz quadratic mutual information. In: 2015 IEEE International Conference on Robotics and Automation (ICRA) pp. 4791–4798 (2015).
  2. 2.
    Cover, T.M., Thomas, J.A.: Elements of Information Theory (2005).
  3. 3.
    Cowley, A., Taylor, C.J., Southall, B.: Rapid multi-robot exploration with topometric maps. In: Proceedings-IEEE International Conference on Robotics and Automation pp. 1044–1049 (2011).
  4. 4.
    Elfes, A.: Using occupancy grids for mobile robot perception and navigation. Computer 22(6), 46–57 (1989). CrossRefGoogle Scholar
  5. 5.
    Henry, P., Krainin, M., Herbst, E., Ren, X., Fox, D.: RGB-D mapping: using depth cameras for dense 3D modeling of indoor environments. Springer Tracts in Adv. Robot. 79, 477–491 (2014). CrossRefGoogle Scholar
  6. 6.
    Julian, B.J., Karaman, S., Rus, D.: On mutual information-based control of range sensing robots for mapping applications. Int. J. Robot. Res. 33(10), 1375–1392 (2014). CrossRefGoogle Scholar
  7. 7.
    Newcombe, R.A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A.J., Kohli, P., Shotton, J., Hodges, S., Fitzgibbon, A.: KinectFusion: Real-time dense surface mapping and tracking. In: 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011 (July 2016), pp. 127–136 (2011).
  8. 8.
    Stachniss, C., Martínez Mozos, Ó., Burgard, W.: Efficient exploration of unknown indoor environments using a team of mobile robots. Ann. Math. Artif. Intell. 52(2), 205–227 (2008). MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Taylor, C.J., Cowley, A., Kettler, R., Ninomiya, K., Gupta, M., Niu, B.: Mapping with depth panoramas. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015), pp. 6265–6272 (2015)Google Scholar
  10. 10.
    Thrun, S., Burgard, W., Fox, D.: Probabilistic robotics. MIT press, USA (2005)Google Scholar
  11. 11.
    Whelan, T., Kaess, M., Fallon, M., Johannsson, H., Leonard, J., McDonald, J.: Kintinuous: Spatially extended kinectfusion (2012)Google Scholar
  12. 12.
    Yamauchi, B.: Frontier-based exploration using multiple robots. In: Proceedings of the Second International Conference On Autonomous Agents, pp. 47–53. ACM (1998)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Daniel Mox
    • 1
  • Anthony Cowley
    • 2
  • M. Ani Hsieh
    • 2
  • C. J. Taylor
    • 2
  1. 1.Drexel UniversityPhiladelphiaUSA
  2. 2.University of PennsylvaniaPhiladelphiaUSA

Personalised recommendations