|Publisher DOI:||10.23919/ECC.2019.8795916||Title:||Towards reinforcement learning-based control of an energy harvesting pendulum||Language:||English||Authors:||Cyr, Caralyn
|Issue Date:||Jun-2019||Source:||European Control Conference, ECC 2019 : 8795916 (2019-06)||Abstract (english):||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.||Conference:||18th European Control Conference, ECC 2019||URI:||http://hdl.handle.net/11420/3365||ISBN:||978-390714400-8||Institute:||Mechanik und Meerestechnik M-13||Type:||InProceedings (Aufsatz / Paper einer Konferenz etc.)||Funded by:||This work was supported by the German Research Foundation (DFG) under grant Kr 752/36-1.|
|Appears in Collections:||Publications without fulltext|
Show full item record
checked on Sep 23, 2020
Add Files to Item
Note about this record
Items in TORE are protected by copyright, with all rights reserved, unless otherwise indicated.