Robot Control Using Model-Based Reinforcement Learning With Inverse Kinematics

Dario Luipers, Nicolas Kaulen, Oliver Chojnowski, Sebastian Schneider, Anja Richert, Sabina Jeschke

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

This work investigates the complications of robotic learning using reinforcement learning (RL). While RL has enormous potential for solving complex tasks its major caveat is the computation cost- and time-intensive training procedure. This work aims to address this issue by introducing a humanlike thinking and acting paradigm to a RL approach. It utilizes model-based deep RL for planning (think) coupled with inverse kinematics (IK) for the execution of actions (act). The approach was developed and tested using a Franka Emika Panda robot model in a simulated environment using the PyBullet physics engine Bullet. It was tested on three different simulated tasks and then compared to the conventional method using RL-only to learn the same tasks. The results show that the RL algorithm with IK converges significantly faster and with higher quality than the applied conventional approach, achieving 98%, 99% and 98% success rates for tasks 1-3 respectively. This work verifies its benefit for use of RL-IK with multi-joint robots.
Original languageEnglish
Title of host publication2022 IEEE International Conference on Development and Learning (ICDL)
PublisherIEEE
DOIs
Publication statusPublished - 30 Nov 2022
Externally publishedYes
Event2022 IEEE International Conference on Development and Learning, ICDL 2022 - Queen Mary University of London, London, United Kingdom
Duration: 12 Sept 202215 Sept 2022

Conference

Conference2022 IEEE International Conference on Development and Learning, ICDL 2022
Abbreviated titleICDL
Country/TerritoryUnited Kingdom
CityLondon
Period12/09/2215/09/22

Keywords

  • n/a OA procedure
  • NLA

Fingerprint

Dive into the research topics of 'Robot Control Using Model-Based Reinforcement Learning With Inverse Kinematics'. Together they form a unique fingerprint.

Cite this