Autonomous development of active binocular and motion vision through active efficient coding

  • We present a model for the autonomous and simultaneous learning of active binocular and motion vision. The model is based on the Active Efficient Coding (AEC) framework, a recent generalization of classic efficient coding theories to active perception. The model learns how to efficiently encode the incoming visual signals generated by an object moving in 3-D through sparse coding. Simultaneously, it learns how to produce eye movements that further improve the efficiency of the sensory coding. This learning is driven by an intrinsic motivation to maximize the system's coding efficiency. We test our approach on the humanoid robot iCub using simulations. The model demonstrates self-calibration of accurate object fixation and tracking of moving objects. Our results show that the model keeps improving until it hits physical constraints such as camera or motor resolution, or limits on its internal coding capacity. Furthermore, we show that the emerging sensory tuning properties are in line with results on disparity, motion, and motion-in-depth tuning in the visual cortex of mammals. The model suggests that vergence and tracking eye movements can be viewed as fundamentally having the same objective of maximizing the coding efficiency of the visual system and that they can be learned and calibrated jointly through AEC.

Download full text files

Export metadata

Metadaten
Author:Alexander Lelais, Jonas Mahn, Vikram Narayan, Chong Zhang, Bertram E. Shi, Jochen TrieschORCiD
URN:urn:nbn:de:hebis:30:3-507561
DOI:https://doi.org/10.3389/fnbot.2019.00049
ISSN:1662-5218
Pubmed Id:https://pubmed.ncbi.nlm.nih.gov/31379548
Parent Title (English):Frontiers in neurorobotics
Publisher:Frontiers Research Foundation
Place of publication:Lausanne
Contributor(s):Florian Röhrbein
Document Type:Article
Language:English
Year of Completion:2019
Date of first Publication:2019/07/16
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Release Date:2019/08/19
Tag:active perception; autonomous learning; binocular vision; efficient coding; intrinsic motivation; optokinetic nystagmus; smooth pursuit
Volume:13
Issue:Art. 49
Page Number:14
First Page:1
Last Page:14
Note:
Copyright © 2019 Lelais, Mahn, Narayan, Zhang, 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) and the copyright owner(s) 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:45400737X
Institutes:Physik / Physik
Wissenschaftliche Zentren und koordinierte Programme / Frankfurt Institute for Advanced Studies (FIAS)
Dewey Decimal Classification:5 Naturwissenschaften und Mathematik / 53 Physik / 530 Physik
Sammlungen:Universitätspublikationen
Licence (German):License LogoCreative Commons - Namensnennung 4.0