Advertisement

Dreaming Mechanism for Training Bio-Inspired Driving Agents

  • Alice Plebe
  • Gastone Pietro Rosati Papini
  • Riccardo DonàEmail author
  • Mauro Da Lio
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 903)

Abstract

This paper addresses one of the key ideas embraced by the European funded H2020 research project Dreams4Cars: to borrow resemblances from the way humans learn to drive. We developed an artificial driving agent, called “Co-driver”, characterized by an architecture mimicking the fundamental components of the human brain involved in the learning of complex sensorimotor abilities, like driving. We implemented a dream-like mechanism to train and test the self-driving agent, and we will show two case studies demonstrating the effectiveness of such approach.

Keywords

Human-systems integration  Artificial neural networks  Autonomous driving Dreaming mechanism 

References

  1. 1.
    Hesslow, G.: The current status of the simulation theory of cognition. Brain 1428, 71–79 (2012)CrossRefGoogle Scholar
  2. 2.
    Cisek, P., Kalaska, J.F.: Neural mechanisms for interacting with a world full of action choices. Ann. Rev. Neurosci. 33, 269–298 (2010)CrossRefGoogle Scholar
  3. 3.
    Wolpert, D.M., Diedrichsen, J., Flanagan, R.: Principles of sensorimotor learning. Nat. Rev. Neurosci. 12, 739–751 (2011)CrossRefGoogle Scholar
  4. 4.
    Hardwick, R.M., Rottschy, C., Miall, C., Eickhoff, S.B.: A quantitative meta-analysis and review of motor learning in the human brain. NeuroImage 67, 283–297 (2013)CrossRefGoogle Scholar
  5. 5.
    Da Lio, M., Plebe, A., Bortoluzzi, D., Papini, G.P.R., Donà, R.: Autonomous vehicle architecture inspired by the neurocognition of human driving. In: International Conference on Vehicle Technology and Intelligent Transport Systems, pp. 507–513. Scitepress (2018)Google Scholar
  6. 6.
    Kosslyn, S.M.: Image and Mind. Harvard University Press, Cambridge (1980)Google Scholar
  7. 7.
    Kosslyn, S.M.: Image and Brain: The Resolution of the Imagery Debate. MIT Press, Cambridge (1994)Google Scholar
  8. 8.
    Horikawa, T., Kamitani, Y.: Hierarchical neural representation of dreamed objects revealed by brain decoding with deep neural network features. Front. Comput. Neurosci. 11 (2018). Article 4Google Scholar
  9. 9.
    Macknik, S., Martinez-Conde, S., Blakeslee, S.: Sleights of Mind: What the Neuro-Science of Magic Reveals About Our Everyday Deceptions. Henry Holt and Company, New York (2010)Google Scholar
  10. 10.
    Thill, S., Svensson, H.: The inception of simulation: a hypothesis for the role of dreams in young children. In: Carlson, L., Hoelscher, C., Shipley, T.F. (eds.) Proceedings of the 33rd Annual Conference of the Cognitive Science Society (2011)Google Scholar
  11. 11.
    Meyer, K., Damasio, A.: Convergence and divergence in a neural architecture for recognition and memory. Trends Neurosci. 32, 376–382 (2009)CrossRefGoogle Scholar
  12. 12.
    Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 28, 504–507 (2006)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)MathSciNetzbMATHGoogle Scholar
  14. 14.
    Larochelle, H., Bengio, Y., Louradour, J., Lamblin, P.: Exploring strategies for training deep neural networks. J. Mach. Learn. Res. 1, 1–40 (2009)zbMATHGoogle Scholar
  15. 15.
    Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2, 1–127 (2009)CrossRefGoogle Scholar
  16. 16.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)Google Scholar
  17. 17.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of International Conference on Learning Representations (2014)Google Scholar
  18. 18.
    Krizhevsky, A., Hinton, G.E.: Using very deep autoencoders for content-based image retrieval. In: European Symposium on Artificial Neural Networks. Computational Intelligence and Machine Learning, pp. 489–494 (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Alice Plebe
    • 1
  • Gastone Pietro Rosati Papini
    • 2
  • Riccardo Donà
    • 2
    Email author
  • Mauro Da Lio
    • 2
  1. 1.Department of Information Engineering and Computer ScienceUniversity of TrentoTrentoItaly
  2. 2.Department of Industrial EngineeringUniversity of TrentoTrentoItaly

Personalised recommendations