UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

A Deep Probabilistic Framework for Heterogeneous Self-Supervised Learning of Affordances

Dehban, A; Jamone, L; Kampff, AR; Santos-Victor, J; (2017) A Deep Probabilistic Framework for Heterogeneous Self-Supervised Learning of Affordances. In: Proceedings of the 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids). (pp. pp. 476-483). IEEE: Piscataway, NJ, USA. Green open access

[img]
Preview
Text
adehban-humanoids2017.pdf - ["content_typename_Accepted version" not defined]

Download (2MB) | Preview

Abstract

The perception of affordances provides an action-centered parametric representation of the environment. By perceiving an object's visual features in terms of what actions they afford, novel behavior opportunities can be inferred about previously unseen objects. In this paper, a flexible deep probabilistic framework is proposed which allows an explorative agent to learn tool-object affordances in continuous space. To this end, we use a deep variational auto-encoder with heterogeneous probabilistic distributions to infer the most probable action that achieves a desired effect or to predict a parametric probability distribution over action consequences i.e. effects. Our experiments show the generalization of the method to unseen objects and tools and we have analyzed the influence of different design choices. Our framework goes beyond other proposals by incorporating various probability distributions tailored for each individual modality and by eliminating the need for any pre-processing of the data.

Type: Proceedings paper
Title: A Deep Probabilistic Framework for Heterogeneous Self-Supervised Learning of Affordances
ISBN-13: 978-1-5386-4679-3
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/HUMANOIDS.2017.8246915
Publisher version: https://doi.org/10.1109/HUMANOIDS.2017.8246915
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Tools, Probability distribution, Training, Probabilistic logic, Robot sensing systems, Computational modeling
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > The Sainsbury Wellcome Centre
URI: http://discovery.ucl.ac.uk/id/eprint/10071288
Downloads since deposit
27Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item