Robust active binocular vision through intrinsically motivated learning

  • The efficient coding hypothesis posits that sensory systems of animals strive to encode sensory signals efficiently by taking into account the redundancies in them. This principle has been very successful in explaining response properties of visual sensory neurons as adaptations to the statistics of natural images. Recently, we have begun to extend the efficient coding hypothesis to active perception through a form of intrinsically motivated learning: a sensory model learns an efficient code for the sensory signals while a reinforcement learner generates movements of the sense organs to improve the encoding of the signals. To this end, it receives an intrinsically generated reinforcement signal indicating how well the sensory model encodes the data. This approach has been tested in the context of binocular vison, leading to the autonomous development of disparity tuning and vergence control. Here we systematically investigate the robustness of the new approach in the context of a binocular vision system implemented on a robot. Robustness is an important aspect that reflects the ability of the system to deal with unmodeled disturbances or events, such as insults to the system that displace the stereo cameras. To demonstrate the robustness of our method and its ability to self-calibrate, we introduce various perturbations and test if and how the system recovers from them. We find that (1) the system can fully recover from a perturbation that can be compensated through the system's motor degrees of freedom, (2) performance degrades gracefully if the system cannot use its motor degrees of freedom to compensate for the perturbation, and (3) recovery from a perturbation is improved if both the sensory encoding and the behavior policy can adapt to the perturbation. Overall, this work demonstrates that our intrinsically motivated learning approach for efficient coding in active perception gives rise to a self-calibrating perceptual system of high robustness.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Luca Lonini, Sébastien Forestier, Céline Teulière, Yu Zhao, Bertram E. ShiORCiD, Jochen TrieschORCiD
URN:urn:nbn:de:hebis:30:3-327938
DOI:https://doi.org/10.3389/fnbot.2013.00020
ISSN:1662-5218
Pubmed Id:https://pubmed.ncbi.nlm.nih.gov/24223552
Parent Title (English):Frontiers in neurorobotics
Publisher:Frontiers Research Foundation
Place of publication:Lausanne
Document Type:Article
Language:English
Date of Publication (online):2013/07/07
Date of first Publication:2013/07/07
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Release Date:2014/01/23
Tag:active perception; reinforcement learning; robotics; robustness; sparse coding; stereo vision; vergence
Volume:7
Issue:Article 20
Page Number:10
Note:
Copyright © 2013 Lonini, Forestier, Teulière, Zhao, Shi and Triesch. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
HeBIS-PPN:363413138
Institutes:Wissenschaftliche Zentren und koordinierte Programme / Frankfurt Institute for Advanced Studies (FIAS)
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
6 Technik, Medizin, angewandte Wissenschaften / 61 Medizin und Gesundheit / 610 Medizin und Gesundheit
Sammlungen:Universitätspublikationen
Licence (German):License LogoCreative Commons - Namensnennung 3.0