Real2Sim or Sim2Real: Robotics Visual Insertion Using Deep Reinforcement Learning and Real2Sim Policy Adaptation

Real2Sim or Sim2Real: Robotics Visual Insertion Using Deep Reinforcement Learning and Real2Sim Policy Adaptation

Lecture Notes in Networks and Systems

10.1007/978-3-031-22216-0_41

https://doi.org/10.1007/978-3-031-22216-0_41

Yiwen Chen, Xue Li, Sheng Guo, Xian Yao Ng, Marcelo H. Ang

17 January 2023

Chen, Y., Li, X., Guo, S., Ng, X. Y., & Ang, M. H. (2023). Real2Sim or Sim2Real: Robotics Visual Insertion Using Deep Reinforcement Learning and Real2Sim Policy Adaptation. In Intelligent Autonomous Systems 17 (pp. 617–629). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-22216-0_41

Reinforcement learning has shown a wide usage in robotics tasks, such as insertion and grasping. However, without a practical sim2real strategy, the policy trained in simulation could fail on the real task. There are also wide researches in the sim2real strategies, but most of those methods rely on heavy image rendering, domain randomization training, or tuning. In this work, we solve the insertion task using a pure visual reinforcement learning solution with minimum infrastructure requirement. We also propose a novel sim2real strategy, Real2Sim, which provides a novel and easier solution in policy adaptation. We discuss the advantage of Real2Sim compared with Sim2Real.

Publisher Copyright

This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - Advanced Manufacturing and Engineering (AME) Programmatic Grant
Grant Reference no. : A18A2b0046

This is a post-peer-review, pre-copyedit version of an article published in Lecture Notes in Networks and Systems. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-031-22216-0_41

https://oar.a-star.edu.sg/communities-collections/articles/21419

9783031222160

9783031222153

Institute of High Performance Computing