User: Guest  Login
Title:

Deep Reinforcement Learning for Formation Control

Document type:
Konferenzbeitrag
Author(s):
Aykın, Can; Knopp, Martin; Diepold, Klaus
Pages contribution:
1124-1128
Abstract:
Continuing our work on using reinforcement learning for formation control, we present an end-to-end deep learning system which uses only camera images to learn to control the individual system's correct position within the formation. Mnih et al. created AIs playing video games utilizing the same visual input as a human player by employing convolutional neural networks for automatic feature extraction on images. This published work inspired us to employ a similar approach for processing the c...     »
Dewey Decimal Classification:
620 Ingenieurwissenschaften
Editor:
Institute of Electrical and Electronics Engineers (IEEE)
Book / Congress title:
27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2018)
Congress (additional information):
Nanjing, China
Organization:
Institute of Electrical and Electronics Engineers (IEEE)
Date of congress:
27.-31. August 2018
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Date of publication:
29.08.2018
Year:
2018
Year / month:
2018-08
Month:
Aug
Pages:
1124-1128
Print-ISBN:
978-1-5386-7981-4
E-ISBN:
978-1-5386-7980-7
Reviewed:
ja
Language:
en
Fulltext / DOI:
doi:10.1109/ROMAN.2018.8525765
TUM Institution:
Lehrstuhl für Datenverarbeitung
Copyright statement:
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
 BibTeX