Sim2Real Deep Reinforcement Learning of Compliance-based Robotic Assembly Operations
Authors:
- 22 August 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 300-305
Abstract
Reinforcement learning (RL) enables robots to learn goal-oriented behavior. In production processes with high variances, such as joining operations in end-of-line assembly, this is particularly interesting to save significant programming effort. Due to a large amount of required training data, simulative training is becoming increasingly important. In this paper, we present an approach to learn a contact-rich peg-in-hole assembly task utilizing deep reinforcement learning (DRL) and a compliant robot controller. The DRL-Agent learns directly in the Cartesian space (task space) and not in the joint space of the robot, to increase the robustness and efficiency of the algorithms. To further increase the robustness of the policy and to shorten training times, geometric limitations are imposed by introducing an admissible workspace using a trajectory generator. Furthermore, these limitations result in nearly identical behavior in the simulation and on the real robot, allowing the DRL training process to be purely simulative. The learned policy is experimentally investigated both in the simulation environment and on a real robot, to evaluate its transferability from simulation to reality (sim2real).Keywords
This publication has 12 references indexed in Scilit:
- Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks2020
- Crossing the Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamics2020
- Variable Compliance Control for Robotic Peg-in-Hole Assembly: A Deep-Reinforcement-Learning ApproachApplied Sciences, 2020
- Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich TasksIEEE Transactions on Robotics, 2020
- Training in Task Space to Speed Up and Guide Reinforcement Learning2019
- Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience2019
- Deep Reinforcement Learning: A Brief SurveyIEEE Signal Processing Magazine, 2017
- Forward Dynamics Compliance Control (FDCC): A new approach to cartesian compliance for robotic manipulators2017
- Deep reinforcement learning for high precision assembly tasks2017
- Design and use paradigms for gazebo, an open-source multi-robot simulator2005