English

Sim-to-Real Transfer of Robotic Assembly with Visual Inputs Using CycleGAN and Force Control

Robotics 2022-08-31 v1

Abstract

Recently, deep reinforcement learning (RL) has shown some impressive successes in robotic manipulation applications. However, training robots in the real world is nontrivial owing to sample efficiency and safety concerns. Sim-to-real transfer is proposed to address the aforementioned concerns but introduces a new issue called the reality gap. In this work, we introduce a sim-to-real learning framework for vision-based assembly tasks and perform training in a simulated environment by employing inputs from a single camera to address the aforementioned issues. We present a domain adaptation method based on cycle-consistent generative adversarial networks (CycleGAN) and a force control transfer approach to bridge the reality gap. We demonstrate that the proposed framework trained in a simulated environment can be successfully transferred to a real peg-in-hole setup.

Keywords

Cite

@article{arxiv.2208.14104,
  title  = {Sim-to-Real Transfer of Robotic Assembly with Visual Inputs Using CycleGAN and Force Control},
  author = {Chengjie Yuan and Yunlei Shi and Qian Feng and Chunyang Chang and Zhaopeng Chen and Alois Christian Knoll and Jianwei Zhang},
  journal= {arXiv preprint arXiv:2208.14104},
  year   = {2022}
}

Comments

7 pages