Line-of-Sight Control of a Spherical Parallel Manipulator via Deep Reinforcement Learning

Aviram Yanover, Daniel Choukroun

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

Abstract

In this paper, controllers solving a rest-to-rest line-of-sight orientation problem are developed in a deep reinforcement learning framework and applied to a particular spherical parallel manipulator. Perfect kinematic information is assumed for the development and training of the neural networks. Extensive Monte Carlo simulations are performed to test the novel controllers in noisy environments and to compare their performances with an efficient unconstrained feedback controller. Results from an experiment with sole joint position readings are shown to validate the proposed control approach.

Original languageEnglish
Title of host publication2024 IEEE 19th Conference on Industrial Electronics and Applications, ICIEA 2024
PublisherInstitute of Electrical and Electronics Engineers
ISBN (Electronic)9798350360868
DOIs
StatePublished - 1 Jan 2024
Event19th IEEE Conference on Industrial Electronics and Applications, ICIEA 2024 - Kristiansand, Norway
Duration: 5 Aug 20248 Aug 2024

Publication series

Name2024 IEEE 19th Conference on Industrial Electronics and Applications, ICIEA 2024

Conference

Conference19th IEEE Conference on Industrial Electronics and Applications, ICIEA 2024
Country/TerritoryNorway
CityKristiansand
Period5/08/248/08/24

Keywords

  • Deep reinforcement learning
  • Robotics
  • Spherical parallel manipulator

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Control and Optimization
  • Mechanical Engineering
  • Instrumentation

Fingerprint

Dive into the research topics of 'Line-of-Sight Control of a Spherical Parallel Manipulator via Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this