Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Learning-Based Auto-Tuning for Motion Controllers of Mobile Robots
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

An auto-tuner of the parameters of a mobile robots motion controlleris developed to improve its performance. The generality of the auto-tunerallows for similar applications on other robots or controllers. The performanceis defined by a proprietary objective function for the purpose ofreducing positional error, wear and energy consumption while retainingstability. The function evaluates data recorded during simulated runs ofthe robot. Sequential model-based Bayesian optimization (SMBO) is evaluatedwith different design choices. Classic black box optimizers, namelygrid search, random search and Latin hypercube sampling are used asbenchmarks, as well as manual tuning. It is found that SMBO performson par with manual tuning after less than 1000 iterations searching avery large feature space, making use of no prior knowledge for settingthe boundaries. When instead guided by relatively narrow boundariesaround the manually chosen parameter values less than 5 iterations areneeded and the performance continues improving for another 600 iterations.The SMBO demands much fewer evaluations than grid search; itoutperformed grid search even when running 20 times more iterations.However, the difference in performance of different design choices for theSMBO was negligible.

Abstract [sv]

En metod för att automatiskt ställa in parametervärden hos en mobil robots rörelsestyrenhet tas fram för att förbättra prestandan. Generaliteten hos metoden möjliggör tillampning på andra robotars styrsystem. Prestandan definieras av en målfunktion framtagen med ändamålet att minimera det positionella felet, slitage och energiförbrukning med behållen stabilitet. Funktionen evaluerar registrerad data från simulerade körningar av roboten. Sekventiell modelbaserad Bayesisk optimering (SMBO) av olika design undersöks. Klassiska ’black box’ optimerare, nämligen ’grid search’, slumpmässig sökning och ’Latin hypercube sampling’ används som utgångsläge, tillsammans med att manuellt ställa in parametervärden. Det konstateras att SMBO presterar i nivå med manuell inställning inom 1000 iterationer när optimeringen sker i ett vidsträckt parameterrum, utan användning av tillgänglig kunskap för att sätta gränserna. När optimeraren istället leds av relativt snäva gränser kring de parametervärden som valts manuellt krävs färre än 5 iterationer och prestandan förbättras under ytterligare 600 iterationer. For samma prestanda kräver ’grid search’ mer än 20 gånger fler iterarationer jämfört med SMBO. Dock ärskillnaden mellan olika designval obetydlig för SMBO-prestandan.

Place, publisher, year, edition, pages
2019. , p. 41
Series
TRITA-EECS-EX ; 2019:250
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-265673OAI: oai:DiVA.org:kth-265673DiVA, id: diva2:1380803
Educational program
Master of Science - Sustainable Energy Engineering
Supervisors
Examiners
Available from: 2019-12-19 Created: 2019-12-19 Last updated: 2019-12-19Bibliographically approved

Open Access in DiVA

fulltext(1994 kB)9 downloads
File information
File name FULLTEXT01.pdfFile size 1994 kBChecksum SHA-512
d56263d58b2ceccb4421de853f60a0df4e68afce4bf465e04cf71d32b096d761dcf34c5e1980cdbf1254555505115d6267573fc6ce34042aa1bfab5ee03731c4
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 9 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: 37 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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