Advertisement

e & i Elektrotechnik und Informationstechnik

, Volume 134, Issue 6, pp 293–298 | Cite as

Autonomous robots: potential, advances and future direction

  • Simon Hangl
  • Emre Ugur
  • Justus Piater
Originalarbeit

Abstract

Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents.

Keywords

autonomous robots cognitive robotics developmental robotics lifelong learning robot creativity robot playing 

Autonome Roboter: Potenzial, Fortschritte und künftige Richtungen

Zusammenfassung

Jüngste Fortschritte im maschinellen Lernen, wie tiefe Neuronale Netze, haben einen großen Schub in vielen verschiedenen Bereichen der Künstlichen Intelligenz und Robotik bewirkt. Diese Methoden erfordern in der Regel einen großen Stamm an gut aufbereiteten Trainingsdaten, welche die Anwendbarkeit der Robotik begrenzen. Unserer Meinung nach ist es eine grundlegende Herausforderung in der autonomen Robotik, Systeme zu entwerfen, die einfach genug sind, um einfache Aufgaben zu lösen. Diese Systeme sollten dann Schritt für Schritt an Komplexität zunehmen. Komplexere Modelle, wie Neuronale Netze, sollten schließlich durch das Auswerten der über die Zeit gewonnenen Informationen laufend weiter trainiert werden. Letztendlich sollten aus diesen Modellen hochrangige Abstraktionen generiert werden, die gewisse fehlende Informationen von Low-Level-Sensordaten hin zu High-Level-Systemen der Künstlichen Intelligenz überbrücken können. Die Autoren stellen erste Schritte in diese Richtung vor und analysieren die Grenzen bzw. künftigen Erweiterungen mit dem Ziel, autonome Agenten zu entwerfen.

Schlüsselwörter

autonome Roboter kognitive Robotik lebenslanges Lernen Roboter-Kreativität Roboter-Spiele 

References

  1. 1.
    Aristotle (−369 BC): Theaetetus. Google Scholar
  2. 2.
    Asada, M., Hosoda, K., Kuniyoshi, Y., Ishiguro, H., Inui, T., Yoshikawa, Y., Ogino, M., Yoshida, C. (2009): Cognitive developmental robotics: a survey. IEEE Trans. Auton. Ment. Dev., 1(1), 12–34. doi: 10.1109/TAMD.2009.2021702. CrossRefGoogle Scholar
  3. 3.
    Briegel, H. J., De las Cuevas, G. (2012): Projective simulation for artificial intelligence. Sci. Rep., 2, 400, EP CrossRefGoogle Scholar
  4. 4.
    Fukushima, K. (1988): Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Netw., 1(2), 119–130. CrossRefGoogle Scholar
  5. 5.
    Hangl, S., Dunjko, V., Briegel, H., Piater, J. H. (2017): Skill learning by autonomous robotic playing using active learning and creativity. CoRR. 1706.08560.
  6. 6.
    Hangl, S., Stabinger, S., Piater, J. (2017): Autonomous skill-centric testing using deep learning. In IEEE/RSJ international conference on intelligent robots and systems. Google Scholar
  7. 7.
    Hangl, S., Ugur, E., Szedmak, S., Piater, J. (2016): Robotic playing for hierarchical complex skill learning. In IEEE/RSJ international conference on intelligent robots and systems. Google Scholar
  8. 8.
    Hubel, D. H., Wiesel, T. N. (1968): Receptive fields and functional architecture of monkey striate cortex. J. Physiol., 195(1), 215–243. CrossRefGoogle Scholar
  9. 9.
    Izhikevich, E. M. (2003): Simple model of spiking neurons. IEEE Trans. Neural Netw., 14(6), 1569–1572. MathSciNetCrossRefGoogle Scholar
  10. 10.
    Kahn, G., Villaflor, A., Pong, V., Abbeel, P., Levine, S. (2017): Uncertainty-aware reinforcement learning for collision avoidance. CoRR. 1702.01182.
  11. 11.
    LeCun, Y., Bengio, Y., Hinton, G. (2015): Deep learning. Nature, 521(7553), 436–444. CrossRefGoogle Scholar
  12. 12.
    Levine, S., Pastor, P., Krizhevsky, A., Ibarz, J., Quillen, D. (2017): Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int. J. Robot. Res., doi: 10.1177/0278364917710318 Google Scholar
  13. 13.
    Lungarella, M., Metta, G., Pfeifer, R., Sandini, G. (2003): Developmental robotics: a survey. Connect. Sci., 15(4), 151–190. CrossRefGoogle Scholar
  14. 14.
    McCarthy, J., Minsky, M. L., Rochester, N., Shannon, C. E. (1955): A proposal for the Dartmouth summer research project on artificial intelligence. AI Mag., 31(4), 12. 27, 2006. Google Scholar
  15. 15.
    Piaget, J. (1952): The origins of intelligence in children. New York: Norton. CrossRefGoogle Scholar
  16. 16.
    Sadeghi, F., Levine, S. (2017): Cad2rl: real single-image flight without a single real image. In Robotics: science and systems. Google Scholar
  17. 17.
    Schmidhuber, J. (2015): Deep learning in neural networks: an overview. Neural Netw., 61, 85–117. CrossRefGoogle Scholar
  18. 18.
    Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016): Mastering the game of go with deep neural networks and tree search. Nature, 529(7587), 484–489. CrossRefGoogle Scholar
  19. 19.
    Stoytchev, A. (2009): Some basic principles of developmental robotics. IEEE Trans. Auton. Ment. Dev., 1(2), 122–130. CrossRefGoogle Scholar
  20. 20.
    Sutton, R. S. (2001): Verification, the key to AI. Online essay. http://www.cs.ualberta.ca/sutton/IncIdeas/KeytoAI.html.
  21. 21.
    Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P. (2017): Domain randomization for transferring deep neural networks from simulation to the real world. CoRR. 1703.06907.
  22. 22.
    Turing, A. M. (1950): Computing machinery and intelligence. Mind, 59(236), 433–460. MathSciNetCrossRefGoogle Scholar
  23. 23.
    Ugur, E., Piater, J. (2015): Bottom-up learning of object categories, action effects and logical rules: from continuous manipulative exploration to symbolic planning. In IEEE international conference on robotics and automation, ICRA (S. 2627–2633). New York: IEEE Press. Google Scholar
  24. 24.
    Weng, J. (2004): Developmental robotics: theory and experiments. Int. J. Humanoid Robot., 1(02), 199–236. CrossRefGoogle Scholar
  25. 25.
    Yu, W., Liu, C. K., Turk, G. (2017): Preparing for the unknown: Learning a universal policy with online system identification. CoRR. 1702.02453.

Copyright information

© Springer-Verlag GmbH Austria 2017

Authors and Affiliations

  1. 1.Intelligent and Interactive SystemsUniversität InnsbruckInnsbruckAustria
  2. 2.Bogazici UniversityIstanbulTurkey

Personalised recommendations