English

Deep Reinforcement Learning for High Precision Assembly Tasks

Robotics 2017-09-25 v2 Artificial Intelligence

Abstract

High precision assembly of mechanical parts requires accuracy exceeding the robot precision. Conventional part mating methods used in the current manufacturing requires tedious tuning of numerous parameters before deployment. We show how the robot can successfully perform a tight clearance peg-in-hole task through training a recurrent neural network with reinforcement learning. In addition to saving the manual effort, the proposed technique also shows robustness against position and angle errors for the peg-in-hole task. The neural network learns to take the optimal action by observing the robot sensors to estimate the system state. The advantages of our proposed method is validated experimentally on a 7-axis articulated robot arm.

Keywords

Cite

@article{arxiv.1708.04033,
  title  = {Deep Reinforcement Learning for High Precision Assembly Tasks},
  author = {Tadanobu Inoue and Giovanni De Magistris and Asim Munawar and Tsuyoshi Yokoya and Ryuki Tachibana},
  journal= {arXiv preprint arXiv:1708.04033},
  year   = {2017}
}

Comments

Conference: Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, September 24-28, 2017. Video: https://youtu.be/b2pC78rBGH4

R2 v1 2026-06-22T21:13:47.413Z