Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Flying High: Deep Imitation Learning of Optimal Control for Unmanned Aerial Vehicles
KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, perception and learning, RPL.
2018 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Far & Flyg: Djup Imitationsinlärning av Optimal Kontroll för Obemannade Luftfarkoster (Swedish)
Abstract [en]

Optimal control for multicopters is difficult in part due to the low processing power available, and the instability inherent to multicopters. Deep imitation learning is a method for approximating an expert control policy with a neural network, and has the potential of improving control for multicopters. We investigate the performance and reliability of deep imitation learning with trajectory optimization as the expert policy by first defining a dynamics model for multicopters and applying a trajectory optimization algorithm to it. Our investigation shows that network architecture plays an important role in the characteristics of both the learning process and the resulting control policy, and that in particular trajectory optimization can be leveraged to improve convergence times for imitation learning. Finally, we identify some limitations and future areas of study and development for the technology.

Abstract [sv]

Optimal kontroll för multikoptrar är ett svårt problem delvis på grund av den vanligtvis låga processorkraft som styrdatorn har, samt att multikoptrar är synnerligen instabila system. Djup imitationsinlärning är en metod där en beräkningstung expert approximeras med ett neuralt nätverk, och gör det därigenom möjligt att köra dessa tunga experter som realtidskontroll för multikoptrar. I detta arbete undersöks prestandan och pålitligheten hos djup imitationsinlärning med banoptimering som expert genom att först definiera en dynamisk modell för multikoptrar, sedan applicera en välkänd banoptimeringsmetod på denna modell, och till sist approximera denna expert med imitationsinlärning. Vår undersökning visar att nätverksarkitekturen spelar en avgörande roll för karakteristiken hos både inlärningsprocessens konvergenstid, såväl som den resulterande kontrollpolicyn, och att särskilt banoptimering kan nyttjas för att förbättra konvergenstiden hos imitationsinlärningen. Till sist påpekar vi några begränsningar hos metoden och identifierar särskilt intressanta områden för framtida studier.

Place, publisher, year, edition, pages
2018.
Series
TRITA-EECS-EX ; 2018:504
Keywords [en]
imitation learning, deep learning, neural networks, quadrotor, quadcopter, multicopter, multirotor, uav, mav, dagger, dynamics, physical dynamics, simulation
Keywords [sv]
djupinlärning, neuronnät, kvadrotor, multikopter, simulation
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-233326OAI: oai:DiVA.org:kth-233326DiVA, id: diva2:1241848
Educational program
Master of Science in Engineering - Computer Science and Technology
Presentation
2018-06-18, 304, Teknikringen 14, plan 3, Stockholm, 10:15 (English)
Supervisors
Examiners
Available from: 2018-08-31 Created: 2018-08-24 Last updated: 2018-08-31Bibliographically approved

Open Access in DiVA

OptimQuadControl(4605 kB)89 downloads
File information
File name FULLTEXT01.pdfFile size 4605 kBChecksum SHA-512
ca3a8c4f4d774c1d957559be496ef0de0a61cb03bd8afc6c419020f4a705cb7b0e00de3dcaf6d3e6ecc0772ad59e750bfae16c7a96b99180da65e01911d94ac2
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Ericson, Ludvig
By organisation
Robotics, perception and learning, RPL
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 89 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 384 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf