TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. Towards reinforcement learning-based control of an energy harvesting pendulum
 
Options

Towards reinforcement learning-based control of an energy harvesting pendulum

Publikationstyp
Conference Paper
Date Issued
2019-06
Sprache
English
Author(s)
Cyr, Caralyn  
Dostal, Leo  
Dücker, Daniel-André 
Kreuzer, Edwin  
Institut
Mechanik und Meerestechnik M-13  
TORE-URI
http://hdl.handle.net/11420/3365
Start Page
3934
End Page
3939
Article Number
8795916
Citation
European Control Conference, ECC 2019 : 3934-3939 (2019-06)
Contribution to Conference
18th European Control Conference, ECC 2019  
Publisher DOI
10.23919/ECC.2019.8795916
Scopus ID
2-s2.0-85071551553
Harvesting energy from the environment, e.g. ocean waves, is a key capability for the long-term operation of remote electronic systems where standard energy supply is not available. Rotating pendulums can be used as energy converters when excited close to their eigenfrequency. However, to ensure robust operation of the harvester, the energy of the dynamic system has to be controlled. In this study, we deploy a light-weight reinforcement learning algorithm to drive the energy of an Acrobot pendulum towards a desired value. We analyze the algorithm in an extensive series of simulations. Moreover, we explore the real world application of our energy-based reinforcement learning algorithm using a computationally constrained hardware setup based on low-cost components, such as the Raspberry Pi platform.
Subjects
MLE@TUHH
DDC Class
620: Ingenieurwissenschaften
Funding(s)
Dezentrale kooperative Exploration von nichtstationären räumlich und zeitlich verteilten Feldern mit autonomen Unterwasserfahrzeugen  
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback