Deep reinforcement learning for high precision assembly tasks

  title={Deep reinforcement learning for high precision assembly tasks},
  author={Tadanobu Inoue and G. Magistris and A. Munawar and T. Yokoya and Ryuki Tachibana},
  journal={2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  • Tadanobu Inoue, G. Magistris, +2 authors Ryuki Tachibana
  • Published 2017
  • Computer Science, Engineering
  • 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • The high precision assembly of mechanical parts requires precision that exceeds that of robots. Conventional part-mating methods used in the current manufacturing require numerous parameters to be tediously tuned before deployment. We show how a robot can successfully perform a peg-in-hole task with a tight clearance through training a recurrent neural network with reinforcement learning. In addition to reducing manual effort, the proposed method also shows a better fitting performance with a… CONTINUE READING
    94 Citations
    Deep Reinforcement Learning for Robotic Assembly of Mixed Deformable and Rigid Objects
    • 19
    Model accelerated reinforcement learning for high precision robotic assembly
    Manipulation Skill Acquisition for Robotic Assembly using Deep Reinforcement Learning
    • 2
    Imitation Learning for High Precision Peg-in-Hole Tasks
    • 1
    • PDF
    Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly
    • 32
    • PDF
    Assembly robots with optimized control stiffness through reinforcement learning
    • Highly Influenced
    • PDF
    Contact Skill Imitation Learning for Robot-Independent Assembly Programming
    • 5
    • PDF
    A Learning Framework for High Precision Industrial Assembly
    • 12
    • PDF
    A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning
    • 37
    • PDF


    Data-efficient Deep Reinforcement Learning for Dexterous Manipulation
    • 147
    • PDF
    Autonomous alignment of peg and hole by force/torque measurement for robotic assembly
    • 26
    • PDF
    Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates
    • 658
    • PDF
    Teaching a Robot Pick and Place Task using Recurrent Neural Network
    • 4
    • PDF
    A neural-network-based flexible assembly controller
    • 9
    Continuous control with deep reinforcement learning
    • 4,309
    • PDF
    Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours
    • Lerrel Pinto, A. Gupta
    • Computer Science
    • 2016 IEEE International Conference on Robotics and Automation (ICRA)
    • 2016
    • 679
    • PDF
    Intelligent and environment-independent Peg-In-Hole search strategies
    • 20
    Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection
    • 1,074
    • PDF
    Reinforcement learning in robotics: A survey
    • 1,577
    • PDF