Improving Recurrent CSVM Performance for Robot Navigation on Discrete Labyrinths

  • Nancy Arana-Daniel
  • Carlos López-Franco
  • Eduardo Bayro-Corrochano
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5856)

Abstract

This paper presents an improvement of a recurrent learning system called LSTM-CSVM (introduced in [1]) for robot navigation applications, this approach is used to deal with some of the main issues addressed in the research area: the problem of navigation on large domains, partial observability, limited number of learning experiences and slow learning of optimal policies. The advantages of this new version of LSTM-CSVM system, are that it can find optimal paths through mazes and it reduces the number of generations to evolve the system to find the optimal navigation policy, therefore either the training time of the system is reduced. This is done by adding an heuristic methodoly to find the optimal path from start state to the goal state.can contain information about the whole environment or just partial information about it.

Keywords

Robot navigation LSTM-CSVM optimal path heuristic 

References

  1. 1.
    Bayro-Corrochano, E., Arana-Daniel, N., Vallejo-Gutierrez, R.: Recurrent Clifford Support Machines. In: Proceedings IEEE World Congress on Computational Intelligence, Hong-Kong (2008)Google Scholar
  2. 2.
    Schmidhuber, J., Gagliolo, M., Wierstra, D., Gomez, F.: Recurrent Support Vector Machines, Technical Report, no. IDSIA 19-05 (2005)Google Scholar
  3. 3.
    Bayro-Corrochano, E., Arana-Daniel, N., Vallejo-Gutierrez, R.: Geometric Preprocessing, geometric feedforward neural networks and Clifford support vector machines for visual learning. Journal Neurocomputing 67, 54–105 (2005)CrossRefGoogle Scholar
  4. 4.
    Hochreiter, S., Bengio, Y., Frasconi, P., Schmidhuber, J.: Gradient ow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer, S.C., Kolen, J.F. (eds.) A field guide to dynamical recurrent neural networks. IEEE Press, Los Alamitos (2001)Google Scholar
  5. 5.
    Hochreiter, S., Schmidhuber, J.: Long Short-Term Memory, Technical Report FKI-207-95 (1996)Google Scholar
  6. 6.
    Hestenes, D., Li, H., Rockwood, A.: New algebraic tools for classical geometry. In: Sommer, G. (ed.) Geometric Computing with Clifford Algebras. Springer, Heidelberg (2001)Google Scholar
  7. 7.
    Gómez, F.J., Miikkulainen, R.: Active guidance for a finless rocket using neuroevolution. In: Proc. GECCO, pp. 2084–2095 (2003)Google Scholar
  8. 8.
    Millán, J.R., Torras, C.: A Reinforcement Connectionist Approach to Robot Path Finding in Non-Maze-Like Environments. J. Mach. Learn. 8, 363–395 (1992)Google Scholar
  9. 9.
    Sutton, R.S.: Temporal credit assignment in reinforcement learning. Ph.D. Thesis, Dept. of Computer and Information Science, University of Massachusetts, Amherst (1984)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Nancy Arana-Daniel
    • 1
  • Carlos López-Franco
    • 1
  • Eduardo Bayro-Corrochano
    • 2
  1. 1.Electronics and Computer Science Division, Exact Sciences and Engineering Campus, CUCEIUniversidad de GuadalajaraGuadalajaraMéxico
  2. 2.Department of Electrical Engineering and Computer ScienceCinvestav del IPNZapopanMéxico

Personalised recommendations