Leveraging Deep Reinforcement Learning for Reaching Robotic Tasks

Kapil Katyal, I. Jeng Wang, Philippe Burlina

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

Abstract

This work leverages Deep Reinforcement Learning (DRL) to make robotic control immune to changes in the robot manipulator or the environment and to perform reaching, collision avoidance and grasping without explicit, prior and fine knowledge of the human arm structure and kinematics, without careful hand-eye calibration, solely based on visual/retinal input, and in ways that are robust to environmental changes. We learn a manipulation policy which we show takes the first steps toward generalizing to changes in the environment and can scale and adapt to new manipulators. Experiments are aimed at a) comparing different DCNN network architectures b) assessing the reward prediction for two radically different manipulators and c) performing a sensitivity analysis comparing a classical visual servoing formulation of the reaching task with the proposed DRL method.

Original languageEnglish (US)
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
PublisherIEEE Computer Society
Pages490-491
Number of pages2
ISBN (Electronic)9781538607336
DOIs
StatePublished - Aug 22 2017
Event30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States
Duration: Jul 21 2017Jul 26 2017

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2017-July
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Other

Other30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
CountryUnited States
CityHonolulu
Period7/21/177/26/17

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Leveraging Deep Reinforcement Learning for Reaching Robotic Tasks'. Together they form a unique fingerprint.

  • Cite this

    Katyal, K., Wang, I. J., & Burlina, P. (2017). Leveraging Deep Reinforcement Learning for Reaching Robotic Tasks. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 (pp. 490-491). [8014805] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2017-July). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2017.71