Autonomous learning of active multi-scale binocular vision

Luca Lonini, Yu Zhao, Pramod Chandrashekhariah, Bertram E. Shi, Jochen Triesch

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Scopus citations

Abstract

We present a method for autonomously learning representations of visual disparity between images from left and right eye, as well as appropriate vergence movements to fixate objects with both eyes. A sparse coding model (perception) encodes sensory information using binocular basis functions, while a reinforcement learner (behavior) generates the eye movement, according to the sensed disparity. Perception and behavior develop in parallel, by minimizing the same cost function: the reconstruction error of the stimulus by the generative model. In order to efficiently cope with multiple disparity ranges, sparse coding models are learnt at multiple scales, encoding disparities at various resolutions. Similarly, vergence commands are defined on a logarithmic scale to allow both coarse and fine actions. We demonstrate the efficacy of the proposed method using the humanoid robot iCub. We show that the model is fully self-calibrating and does not require any prior information about the camera parameters or the system dynamics.

Original languageEnglish (US)
Title of host publication2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings
DOIs
StatePublished - Dec 31 2013
Externally publishedYes
Event2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Osaka, Japan
Duration: Aug 18 2013Aug 22 2013

Publication series

Name2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings

Conference

Conference2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013
CountryJapan
CityOsaka
Period8/18/138/22/13

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Software

Fingerprint Dive into the research topics of 'Autonomous learning of active multi-scale binocular vision'. Together they form a unique fingerprint.

Cite this