Is depth information and optical flow helpful for visual control?

• Autorzy: Hansen J. , Ebner M.

Identyfikatory

DOI

10.1515/bams-2015-0044

• Języki publikacji: EN

Abstrakty

EN

The human visual system was shaped through natural evolution. We have used artificial evolution to investigate whether depth information and optical flow are helpful for visual control. Our experiments were carried out in simulation. The task was controlling a simulated racing car. We have used The Open Racing Car Simulator for our experiments. Genetic programming was used to evolve visual algorithms that transform input images (color, optical flow, or depth information) to control commands for a simulated racing car. We found that significantly better solutions were found when color, depth, and optical flow were available as input together compared with color, depth, or optical flow alone.

Słowa kluczowe

EN

depth map; genetic programming; optical flow; visual control

• Wydawca: Uniwersytet Jagielloński - Collegium Medicum ; Index Copernicus Sp. z o.o.
• Czasopismo: Bio-Algorithms and Med-Systems
• Rocznik: 2016
• Tom: Vol. 12, no. 1
• Strony: 9--18
• Opis fizyczny: Bibliogr. 46 poz., rys., tab., wykr.

Twórcy

autor

Hansen J.

• Institut für Mathematik und Informatik, Ernst-Moritz-Arndt-Universität Greifswald, Walther-Rathenau-Straße 47, 17487 Greifswald, Germany

autor

Ebner M.

• Institut für Mathematik und Informatik, Ernst-Moritz-Arndt-Universität Greifswald, Walther-Rathenau-Straße 47, 17487 Greifswald, Germany

Bibliografia

• 1. Wymann B, Dimitrakakis C, Sumner A, Espié E, Guinneau C. TORCS, The Open Racing Car Simulator. Available at: http://www.torcs.org. Accessed: Mar 2015.
• 2. Holland JH. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. Cambridge, MA: MIT Press, 1992.
• 3. J. Hansen. Visuelle Steuerung eines simulierten Rennfahrzeugs mit Hilfe von genetischer Programmierung. Master’s thesis, Ernst Moritz Arndt Universität Greifswald. Faculty of Mathematics and Natural Sciences, Greifswald, Germany, Dec. 2014.
• 4. Bradski G. The OpenCV library. Dr Dobb’s J Software Tools 2000 Nov.
• 5. Pulli K, Baksheev A, Kornyakov K, Eruhimov V. Real-time computer vision with OpenCV. Commun ACM 2012;55:61–9.
• 6. Koza JR. Genetic programming. On the programming of computers by means of natural selection. Cambridge, MA: MIT Press, 1992.
• 7. Koza JR. Genetic programming II. Automatic discovery of reusable programs. Cambridge, MA: MIT Press, 1994.
• 8. Banzhaf W, Nordin P, Keller RE, Francone FD. Genetic programming – an introduction: on the automatic evolution of computer programs and its applications. San Francisco, CA: Morgan Kaufmann, 1998.
• 9. Darwin C. The origin of species. Edited with an introduction by Gillian Beer. Oxford: Oxford University Press, 1996.
• 10. Nilsson D-E, Pelger S. A pessimistic estimate of the time required for an eye to evolve. Proc R Soc Lond B 1994;256:53–8.
• 11. Tovée MJ. An introduction to the visual system. Cambridge: Cambridge University Press, 1996.
• 12. Dowling JE. The retina: an approachable part of the brain. Cambridge, MA: Belknap Press of Harvard University Press, 1987.
• 13. Livingstone MS, Hubel DH. Anatomy and physiology of a color system in the primate visual cortex. J Neurosci 1984;4:309–56.
• 14. Zeki SM. Review article: functional specialisation in the visual cortex of the rhesus monkey. Nature 1978;274:423–8.
• 15. Zeki S. Inner vision. An exploration of art and the brain. Oxford: Oxford University Press, 1999.
• 16. Moutoussis K, Zeki S. A direct demonstration of perceptual asynchrony in vision. Proc R Soc Lond B 1997;264:393–9.
• 17. Loiacono D, Cardamone L, Lanzi PL. Simulated car racing championship. Competition software manual. Available at: http://arxiv.org/abs/1304.1672. Accessed: Apr 2013.
• 18. Loiacono D, Togelius J, Lanzi PL, Kinnaird-Heether L, Lucas SM, Simmerson M, et al. The WCCI 2008 simulated car racing competition. In: Proceedings of the 2008 IEEE Symposium on Computational Intelligence and Games, Perth, Australia, December 5–18. Piscataway, NJ: IEEE, 2008.
• 19. Wright Jr RS, Haemel N, Sellers G, Lipchak B. OpenGL SuperBible. Comprehensive tutorial and reference, 5th ed. Upper Saddle River, NJ: Addison-Wesley, 2011.
• 20. Horn BK. Robot vision. Cambridge, MA: MIT Press, 1986.
• 21. Bülthoff H, Little J, Poggio T. A parallel algorithm for real-time computation of optical flow. Nature 1989;337:549–53.
• 22. Wang H, Brady M, Page I. A fast algorithm for computing optic flow and its implementation on a transputer array. In: Zisserman A, editor. Proceedings of the British Machine Vision Conference. Oxford: British Machine Vision Association, 1990:175–80.
• 23. Brox T, Bruhn A, Papenberg N, Weickert J. High accuracy optical flow estimation based on a theory for warping. In: Pajdla T, Matas J, editors. Proceedings of the 8th European Conference on Computer Vision, Part IV, Prague, Czech Republic, May 2004. Berlin: Springer-Verlag, 2004:25–36.
• 24. I. Rechenberg, Evolutionsstrategie ’94. Stuttgart: frommannholzboog, 1994.
• 25. Luke S. The ECJ owner’s manual. A user manual for the ECJ Evolutionary Computation Library, 2015. Available at: https://cs.gmu.edu/~eclab/projects/ecj/docs/manual/manual.pdf
• 26. Winkeler JF, Manjunath BS. Genetic programming for object detection. In: Koza JR, Deb K, Dorigo M, Fogel DB, Garzon M, Iba H, Riolo RL, editors. Genetic Programming 1997, Proceedings of the Second Annual Conference, Stanford University,July 13–16, 1997. San Francisco, CA: Morgan Kaufmann, 1997:330–5.
• 27. Johnson MP, Maes P, Darrell T. Evolving visual routines. In: Brooks RA, Maes P, editors. Artificial Life IV, Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems. Cambridge, MA: MIT Press, 1994:198–209.
• 28. Ebner M, Tiede T. Evolving driving controllers using genetic programming. In: IEEE Symposium on Computational Intelligence & Games, Politecnico di Milano, Milano, Italy, September 7–10. Piscataway, NJ: IEEE, 2009:279–86.
• 29. Koutník J, Cuccu G, Schmidbuber J, Gomez F. Evolving largescale neural networks for vision-based reinforcement learning. In: Proceedings of the Genetic and Evolutionary Computation Conference, Amsterdam, The Netherlands, July 6–10, 2013. ACM, NY, 2001.
• 30. Tanev IT, Shimohara K. On human competitiveness of the evolved agent operating a scale model of a car. In: Proceedings of the IEEE Congress on Evolutionary Computation, Singapore, September 25–28, 2007. Piscataway, NJ: IEEE, 2007:3646–53.
• 31. Tanev I, Shimohara K. Evolution of agent, remotely operating a scale model of a car through a latent video feedback. J Intell Robot Syst 2008;52:263–83.
• 32. Bellemare MG, Naddaf Y, Veness J, Bowling M. The arcade learning environment: an evaluation platform for general agents (extended abstract). In: Proceedings of the 24th International Joint Conference on Artificial Intelligence, 2015:4148–52.
• 33. Hausknecht M, Lehman J, Miikkulainen R, Stone P. A neuroevolution approach to general Atari game playing. IEEE Trans Comput Intell AI Games 2014;6:355–66.
• 34. Hausknecht M, Khandelwal P, Miikkulainen R, Stone P. Hyperneat-ggp: a hyperneat-based Atari general game player. In: Proceedings of the Genetic and Evolutionary Computation Conference, Philadelphia, PA, July 7–11, 2012.
• 35. Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, et al. Human-level control through deep reinforcement learning. Nature 2015;518:529–33.
• 36. Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, et al. Playing Atari with deep reinforcement learning. In: NIPS Deep Learning Workshop, 2013.
• 37. Guo X, Singh S, Lee H, Lewis R, Wang X. Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning. In: Ghahramani Z, Welling M, Cortes C, Lawrence N, Weinberger K, editors. Adv Neural Inf Process Syst 27. Curran Associates, 2014:3338–46.
• 38. Parker M, Bryant BD. Visual control in quake ii with a cyclic controller. In: Hingston P, Barone L, editors. Proceedings of the 2008 IEEE Symposium on Computational Intelligence and Games. Piscataway, NJ: IEEE Press, 2008:151–8.
• 39. Parker M, Bryant BD. Visual control in quake ii with a cyclic controller. In: Proceedings of the 2009 IEEE Symposium on Computational Intelligence and Games. Piscataway, NJ: IEEE Press, 2009:287–93.
• 40. Montana DJ. Strongly typed genetic programming. Evol Comput 1995;3:199–230.
• 41. Srinivasan MV. How bees exploit optic flow: behavioural experiments and neural models. Philos Trans R Soc Lond B 1992;337:253–9.
• 42. Srinivasan MV. Distance perception in insects. Curr Direct Psychol Sci 1992;1:22–6.
• 43. Santos-Victor J, Sandini G, Curotto F, Garibaldi S. Divergent stereo for robot navigation: learning from bees. In: Proceedings of Computer Vision and Pattern Recognition, New York, 1993:434–9.
• 44. Ebner M, Zell A. Centering behavior with a mobile robot using monocular foveated vision. Robot Auton Syst 2000;32:207–18.
• 45. Zeki S. A vision of the brain. Oxford: Blackwell Science, 1993.
• 46. Arndt PA, Mallot HA, Bülthoff HH. Human stereovision without localized image features. Biol Cybern 1995;72:279–93.

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.