• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Artikel
  4. Curriculum Design and Sim2Real Transfer for Reinforcement Learning in Robotic Dual-Arm Assembly
 
  • Details
  • Full
Options
September 29, 2024
Journal Article
Title

Curriculum Design and Sim2Real Transfer for Reinforcement Learning in Robotic Dual-Arm Assembly

Abstract
Robotic systems are crucial in modern manufacturing. Complex assembly tasks require the collaboration of multiple robots. Their orchestration is challenging due to tight tolerances and precision requirements. In this work, we set up two Franka Panda robots performing a peg-in-hole insertion task of 1 mm clearance. We structure the control system hierarchically, planning the robots’ feedback-based trajectories with a central policy trained with reinforcement learning. These trajectories are executed by a low-level impedance controller on each robot. To enhance training convergence, we use reverse curriculum learning, novel for such a two-armed control task, iteratively structured with a minimum requirements and fine-tuning phase. We incorporate domain randomization, varying initial joint configurations of the task for generalization of the applicability. After training, we test the system in a simulation, discovering the impact of curriculum parameters on the emerging process time and its variance. Finally, we transfer the trained model to the real-world, resulting in a small decrease in task duration. Comparing our approach to classical path planning and control shows a decrease in process time, but higher robustness towards calibration errors.
Author(s)
Wrede, Konstantin  orcid-logo
Fraunhofer-Institut für Integrierte Schaltungen IIS  
Zarnack, Sebastian
Fraunhofer-Institut für Integrierte Schaltungen IIS  
Lange, Robert
Fraunhofer-Institut für Integrierte Schaltungen IIS  
Donath, Oliver  
Fraunhofer-Institut für Integrierte Schaltungen IIS  
Wohlfahrt, Tommy  
Fraunhofer-Institut für Integrierte Schaltungen IIS  
Feldmann, Ute  
TU Dresden  
Journal
Machines  
Project(s)
Digitales Robotertraining zur Ausschussminimierung im 3D-Druck - Teilvorhaben: Reale und virtuelle Kollaboration von Greifrobotern  
Funder
Bundesministerium für Umwelt, Naturschutz, nukleare Sicherheit und Verbraucherschutz  
Open Access
DOI
10.3390/machines12100682
Additional full text version
Landing Page
Language
English
Fraunhofer-Institut für Integrierte Schaltungen IIS  
  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024