On the impact of gravity compensation on reinforcement learning in goal-reaching tasks for robotic manipulators

Jonathan Fugal, Jihye Bae, Hasan A. Poonawala

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

Advances in machine learning technologies in recent years have facilitated developments in autonomous robotic systems. Designing these autonomous systems typically requires manually specified models of the robotic system and world when using classical control-based strategies, or time consuming and computationally expensive data-driven training when using learning-based strategies. Combination of classical control and learning-based strategies may mitigate both requirements. However, the performance of the combined control system is not obvious given that there are two separate controllers. This paper focuses on one such combination, which uses gravity-compensation together with reinforcement learning (RL). We present a study of the effects of gravity compensation on the performance of two reinforcement learning algorithms when solving reaching tasks using a simulated seven-degree-of-freedom robotic arm. The results of our study demonstrate that gravity compensation coupled with RL can reduce the training required in reaching tasks involving elevated target locations, but not all target locations.

Original languageEnglish
Article number46
JournalRobotics
Volume10
Issue number1
DOIs
StatePublished - Mar 2021

Bibliographical note

Publisher Copyright:
© 2021 by the authors.

Keywords

  • Control
  • Physics-based machine learning
  • Reinforcement learning
  • Robotics

ASJC Scopus subject areas

  • Mechanical Engineering
  • Control and Optimization
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'On the impact of gravity compensation on reinforcement learning in goal-reaching tasks for robotic manipulators'. Together they form a unique fingerprint.

Cite this