Affordance Learning for End-to-End Visuomotor Robot Control

Aleksi Hamalainen, Karol Arndt, Ali Ghadirzadeh, Ville Kyrki

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Training end-to-end deep robot policies requires a lot of domain-, task-, and hardware-specific data, which is often costly to provide. In this work, we propose to tackle this issue by employing a deep neural network with a modular architecture, consisting of separate perception, policy, and trajectory parts. Each part of the system is trained fully on synthetic data or in simulation. The data is exchanged between parts of the system as low-dimensional latent representations of affordances and trajectories. The performance is then evaluated in a zero-shot transfer scenario using Franka Panda robot arm. Results demonstrate that a low-dimensional representation of scene affordances extracted from an RGB image is sufficient to successfully train manipulator policies. We also introduce a method for affordance dataset generation, which is easily generalizable to new tasks, objects and environments, and requires no manual pixel labeling.

Original languageEnglish
Title of host publicationProceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019
PublisherIEEE
Pages1781-1788
Number of pages8
ISBN (Electronic)9781728140049
DOIs
Publication statusPublished - 1 Nov 2019
MoE publication typeA4 Article in a conference publication
EventIEEE/RSJ International Conference on Intelligent Robots and Systems - The Venetian Macao, Macau, China
Duration: 4 Nov 20198 Nov 2019
https://www.iros2019.org/

Publication series

NameProceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherIEEE
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

ConferenceIEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated titleIROS
CountryChina
CityMacau
Period04/11/201908/11/2019
Internet address

Keywords

  • Control engineering computing
  • Learning (artificial intelligence)
  • Manipulators
  • Neural nets

Fingerprint Dive into the research topics of 'Affordance Learning for End-to-End Visuomotor Robot Control'. Together they form a unique fingerprint.

Cite this