Towards vision-based deep reinforcement learning for robotic motion control

Zhang, Fangyi, Leitner, Jürgen, Milford, Michael, Upcroft, Ben, & Corke, Peter (2015) Towards vision-based deep reinforcement learning for robotic motion control. In Australasian Conference on Robotics and Automation 2015, 2-4 December 2015, Canberra, A.C.T.

View at publisher (open access)


This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real hardware and real observation in a naive approach failed, but experiments show that the network works when replacing camera images with synthetic images.

Impact and interest:

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

17 since deposited on 27 Jan 2016
17 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 92332
Item Type: Conference Paper
Refereed: Yes
Additional URLs:
Keywords: Robotic Manipulation, Motion Control, Target Reaching, Deep Reinforcement Learning, DQN
Subjects: Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100) > Adaptive Agents and Intelligent Robotics (080101)
Australian and New Zealand Standard Research Classification > ENGINEERING (090000) > ELECTRICAL AND ELECTRONIC ENGINEERING (090600) > Control Systems Robotics and Automation (090602)
Divisions: Current > Research Centres > ARC Centre of Excellence for Robotic Vision
Current > Schools > School of Electrical Engineering & Computer Science
Current > QUT Faculties and Divisions > Science & Engineering Faculty
Facilities: Science and Engineering Centre
Copyright Owner: Copyright 2015 [Please consult the author]
Deposited On: 27 Jan 2016 22:37
Last Modified: 28 Jan 2016 22:00

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page