Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control

2015/11/12 by Zhang, Fangyi, Leitner, Jürgen, Milford, Michael +2 · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Robotics (cs.RO)

paper · doi:10.48550/arxiv.1511.03791

Abstract

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.

Cited by

• Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning

Related

• Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
• Robotic Grasping using Deep Reinforcement Learning
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics
• Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods