uu.seUppsala universitets publikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
A Deep Reinforcement Learning Framework where Agents Learn a Basic form of Social Movement
Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion.
2018 (engelsk)Independent thesis Advanced level (professional degree), 20 poäng / 30 hpOppgave
Abstract [en]

For social robots to move and behave appropriately in dynamic and complex social contexts they need to be flexible in their movement behaviors. The natural complexity of social interaction makes this a difficult property to encode programmatically. Instead of programming these algorithms by hand it could be preferable to have the system learn these behaviors. In this project a framework is created in which an agent, through deep reinforcement learning, can learn how to mimic poses, here defined as the most basic case of social movements. The framework aimed to be as agent agnostic as possible and suitable for both real life robots and virtual agents through an approach called "dancer in the mirror". The framework utilized a learning algorithm called PPO and trained agents, as a proof of concept, on both a virtual environment for the humanoid robot Pepper and for virtual agents in a physics simulation environment. The framework was meant to be a simple starting point that could be extended to incorporate more and more complex tasks. This project shows that this framework was functional for agents to learn to mimic poses on a simplified environment.

sted, utgiver, år, opplag, sider
2018. , s. 55
Serie
UPTEC F, ISSN 1401-5757 ; 18008
Emneord [en]
machine learning, deep learning, Pepper, neural network, reinforcement learning
HSV kategori
Identifikatorer
URN: urn:nbn:se:uu:diva-349381OAI: oai:DiVA.org:uu-349381DiVA, id: diva2:1201614
Fag / kurs
Computer Systems Sciences
Utdanningsprogram
Master Programme in Engineering Physics
Veileder
Examiner
Tilgjengelig fra: 2018-05-14 Laget: 2018-04-26 Sist oppdatert: 2018-05-14bibliografisk kontrollert

Open Access i DiVA

fulltext(6871 kB)210 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 6871 kBChecksum SHA-512
4b48680c9602c4fc4790278864f926096dbdab96b5cd2d050c47b3fc669460dfab7107972e2cbf5cdb9e2347d1575040db04dd55bf1f0222df2a4fcc48d51083
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 210 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 430 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf