Traversability Cost Identification of Dynamic Environments Using Recurrent High Order Neural Networks for Robot Navigation

  • Nancy Arana-Daniel
  • Julio Valdés-López
  • Alma Y. Alanís
  • Carlos López-Franco
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10657)

Abstract

In this paper, it is presented a neural network methodology for learning traversability cost maps to aid autonomous robotic navigation. This proposal is based on the control theory idea for dynamical system identification i.e. we solve the problem of learning and recognizing the pattern which describes the best the behavior of the cost function that represents the environment to obtain traversability cost maps as if we are identifying a dynamical system that is the rough terrain where the robot navigates. Recurrent High Order Neural Networks (RHONN) trained with Extended Kalman Filter (EKF) are used to identify rough terrain traversability costs, and besides the good results in the identification tasks, we get the advantages of using a robust machine learning method such as RHONNs. Our proposal gives the robot the capability to generalize the knowledge learned in previous navigation episodes when it is navigating on similar (but not necessarily equal) environments, so the robot can re-use learned knowledge, generalize it and also it can recognize hidden states. Experimental results show that our proposed approach can identify and learn very complex cost maps, we prove it with artificially generated maps as well as satellite maps of real land.

References

  1. 1.
    Kim, D., Sun, J., Oh, S.M., Rehg, J.M., Bobick, A.F.: Traversability classification using unsupervised on-line visual learning for outdoor robot navigation. In: Proceedings 2006 IEEE International Conference on Robotics and Automation, ICRA 2006, pp. 518–525. IEEE (2006)Google Scholar
  2. 2.
    Murphy, L., Newman, P.: Risky planning on probabilistic costmaps for path planning in outdoor environments. IEEE Trans. Robot. 29(2), 445–457 (2013)CrossRefGoogle Scholar
  3. 3.
    Ratliff, N.D., Silver, D., Bagnell, J.A.: Learning to search: functional gradient techniques for imitation learning. Auton. Robots 27(1), 25–53 (2009)CrossRefGoogle Scholar
  4. 4.
    Rebula, J., Hill, G., Bonnlander, B., Johnson, M., Neuhaus, P., Perez, C., Carff, J., Howell, W., Pratt, J.: Learning terrain cost maps. In: IEEE International Conference on Robotics and Automation, ICRA 2008, p. 2217. IEEE (2008)Google Scholar
  5. 5.
    Roncancio, H., Becker, M., Broggi, A., Cattani, S.: Traversability analysis using terrain mapping and online-trained terrain type classifier (2014)Google Scholar
  6. 6.
    Rovithakis, G.A., Christodoulou, M.A.: Adaptive Control with Recurrent High-Order Neural Networks: Theory and Industrial Applications. Springer Science & Business Media, Berlin (2012).  https://doi.org/10.1007/978-1-4471-0785-9 Google Scholar
  7. 7.
    Sanchez, E.N., Alanis, A.Y., Loukianov, A.G.: Discrete-Time High Order Neural Control. Springer, Berlin (2008).  https://doi.org/10.1007/978-3-540-78289-6 CrossRefMATHGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Nancy Arana-Daniel
    • 1
  • Julio Valdés-López
    • 1
  • Alma Y. Alanís
    • 1
  • Carlos López-Franco
    • 1
  1. 1.Universidad de GuadalajaraGuadalajaraMexico

Personalised recommendations