Corpus ID: 14147627

Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control

  title={Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control},
  author={Fangyi Zhang and J. Leitner and Michael Milford and B. Upcroft and P. Corke},
  • Fangyi Zhang, J. Leitner, +2 authors P. Corke
  • Published 2015
  • Computer Science, Mathematics
  • ArXiv
  • 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… CONTINUE READING
    155 Citations

    Figures, Tables, and Topics from this paper

    Leveraging Deep Reinforcement Learning for Reaching Robotic Tasks
    • K. Katyal, I. Wang, P. Burlina
    • Computer Science
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
    • 2017
    • 15
    • PDF
    3D Simulation for Robot Arm Control with Deep Q-Learning
    • 56
    • PDF
    Vision-based deep reinforcement learning to control a manipulator
    • 1
    Vision-Based Reaching Using Modular Deep Networks: from Simulation to the Real World
    • 13
    • PDF
    Transferring Vision-based Robotic Reaching Skills from Simulation to Real World
    • 1
    • PDF
    Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics
    • 6
    • PDF
    Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods
    • 83
    • PDF
    Robotic Arm Control and Task Training through Deep Reinforcement Learning
    • 2
    • PDF


    End-to-End Training of Deep Visuomotor Policies
    • 1,951
    • PDF
    Playing Atari with Deep Reinforcement Learning
    • 4,596
    • PDF
    Reinforcement Learning in Robotics: Applications and Real-World Challenges
    • 99
    • PDF
    Curiosity driven reinforcement learning for motion planning on humanoids
    • 59
    • PDF
    Imitation Learning of Dual-Arm Manipulation Tasks in Humanoid Robots
    • 124
    • PDF
    Learning contact-rich manipulation skills with guided policy search
    • 234
    • PDF
    Human-level control through deep reinforcement learning
    • 11,012
    • PDF
    Reinforcement Learning for Humanoid Robotics
    • 347
    • PDF
    Vision for robotic object manipulation in domestic settings
    • 115
    • PDF
    Survey on Visual Servoing for Manipulation
    • 206
    • PDF