TY  - JOUR
A1  - Lelais, Alexander
A1  - Mahn, Jonas
A1  - Narayan, Vikram
A1  - Zhang, Chong
A1  - Shi, Bertram E.
A1  - Triesch, Jochen
T1  - Autonomous development of active binocular and motion vision through active efficient coding
T2  - Frontiers in neurorobotics
N2  - 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.
KW  - autonomous learning
KW  - active perception
KW  - binocular vision
KW  - optokinetic nystagmus
KW  - smooth pursuit
KW  - efficient coding
KW  - intrinsic motivation
Y1  - 2019
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/50756
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30:3-507561
SN  - 1662-5218
N1  - 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.
VL  - 13
IS  - Art. 49
SP  - 1
EP  - 14
PB  - Frontiers Research Foundation
CY  - Lausanne
ER  -