Abstract
In this paper, we propose a novel visual learning framework for developmental robotics agents which mimics the developmental learning concept from human infants. It can be applied to an agent to autonomously perceive depths by simultaneously developing its visual sensory representation, eye movement control, and depth representation knowledge through integrating multiple visual depth cues during self-induced lateral body movement. Based on the active efficient coding theory (AEC), a sparse coding and a reinforcement learning are tightly coupled with each other by sharing a unify cost function to update the performance of the sensory coding model and eye motor control. The generated multiple eye motor control signals for different visual depth cues are used together as inputs for the multi-layer neural networks for representing the given depth from simple human-robot interaction. We have shown that the proposed learning framework, which is implemented on the Hoap-3 humanoid robot simulator, can effectively learn to autonomously develop the sensory visual representation, eye motor control, and depth perception with self-calibrating ability at the same time.
T. Prucksakorn and S. Jeong—Contributed equally.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Attneave, F.: Some informational aspects of visual perception. Psychol. Rev. 61(3), 183–193 (1954)
Barlow, H.B.: Possible Principles Underlying the Transformation of Sensory Messages. MIT Press, Cambridge (1961)
Bhatnagar, S., Sutton, R.S., Ghavamzadeh, M., Lee, M.: Natural actor-critic algorithms. Automatica 45(11), 2471–2482 (2009)
Field, D.J.: What is the goal of sensory coding? Neural Comput. 6(4), 559–601 (1994)
Frey, J., Ringach, D.L.: Binocular eye movements evoked by self-induced motion parallax. J. Neurosci. 31(47), 17069–17073 (2011)
Johansson, J., Seimyr, G.Ö., Pansell, T.: Eye dominance in binocular viewing conditions. J. vis. 15(9), 21–21 (2015)
Lonini, L., Zhao, Y., Chandrashekhariah, P., Shi, B., Triesch, J.: Autonomous learning of active multi-scale binocular vision. In: 2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL), pp. 1–6, August 2013
Mallat, S.G., Zhang, Z.: Matching pursuits with time-frequency dictionaries. IEEE Trans. Signal Process. 41(12), 3397–3415 (1993)
More, J.J.: The Levenberg-Marquardt algorithm: implementation and theory. In: Numerical Analysis, pp. 105–116. Springer, Berlin (1978)
Mugan, J., Kuipers, B.: Autonomous learning of high-level states and actions in continuous environments. IEEE Trans. Auton. Ment. Dev. 4(1), 70–86 (2012)
Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: a strategy employed by v1? Vision. Res. 37(23), 3311–3325 (1997)
Prucksakorn, T., Jeong, S., Triesch, J., Lee, H., Chong, N.Y.: Self-calibrating active depth perception via motion parallax. In: 2016 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob). IEEE (2016)
Shneor, E., Hochstein, S.: Eye dominance effects in feature search. Vision. Res. 46(25), 4258–4269 (2006)
Shneor, E., Hochstein, S.: Eye dominance effects in conjunction search. Vision. Res. 48(15), 1592–1602 (2008)
Teulière, C., Forestier, S., Lonini, L., Zhang, C., Zhao, Y., Shi, B., Triesch, J.: Self-calibrating smooth pursuit through active efficient coding. Robot. Auton. Syst. 71, 3–12 (2015)
Vikram, T., Teuliere, C., Zhang, C., Shi, B., Triesch, J.: Autonomous learning of smooth pursuit and vergence through active efficient coding. In: 2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob), pp. 448–453. IEEE (2014)
Weng, J., Luciw, M.: Brain-like emergent spatial processing. IEEE Trans. Auton. Ment. Develop. 4(2), 161–185 (2012)
Zhang, C., Zhao, Y., Triesch, J., Shi, B.E.: Intrinsically motivated learning of visual motion perception and smooth pursuit. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 1902–1908. IEEE (2014)
Zhao, Y., Rothkopf, C., Triesch, J., Shi, B.: A unified model of the joint development of disparity selectivity and vergence control. In: 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL), pp. 1–6, November 2012
Acknowledgement
This work was supported by Japan-Germany collaboration research project on computational neuroscience “Autonomous Learning of Active Depth Perception: from Neural Models to Humanoid Robots” from Japan Agency for Medical Research and Development (AMED) and was partially supported by EU-Japan coordinated R&D project on “Culture Aware Robots and Environmental Sensor Systems for Elderly Support” commissioned by the Ministry of Internal Affairs and Communications (MIC) of Japan and EC Horizon 2020.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Prucksakorn, T., Jeong, S., Chong, N.Y. (2017). A Joint Learning Framework of Visual Sensory Representation, Eye Movements and Depth Representation for Developmental Robotic Agents. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10636. Springer, Cham. https://doi.org/10.1007/978-3-319-70090-8_88
Download citation
DOI: https://doi.org/10.1007/978-3-319-70090-8_88
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70089-2
Online ISBN: 978-3-319-70090-8
eBook Packages: Computer ScienceComputer Science (R0)