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
A Study on Long Short-Term Memory Networks Applied to Local Positioning
KTH, School of Industrial Engineering and Management (ITM), Machine Design (Dept.).
KTH, School of Industrial Engineering and Management (ITM), Machine Design (Dept.).
2018 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
En studie om Long Short-Term Memory nätverk applicerade på lokal positionering (Swedish)
Abstract [en]

Numerical approaches to lateration and sensor fusion are limited by inherent measurementerrors and the positioning performance may benefit from alternative approaches.This thesis studies the applicability of deep learning to an Ultra Wide Band (UWB)based local positioning problem in a combination of readings from an Inertial MeasurementUnit (IMU). Relying on the Robotic Operating System (ROS) and a roboticvacuum cleaner, sensor data was gathered and time stamped in the presence of aground truth derived from a motion capture system. The gathered time series wereprocessed and then used to train Long Short-Term Memory networks (LSTMs) forpredicting two-dimensional coordinates and orientation in a plane. In a series of tests,accuracy and precision of the LSTM predictions were assessed and compared with twoconventional approaches to positioning and orientation respectively. Results suggestthat LSTMs can be applied well to positioning, however the study failed to establishbenefits regarding orientation. It is concluded that the implemented LSTM increasedpositioning accuracy with 79.9% and precision with 71.8% compared to that of theconventional non-linear least mean squares approach. Comparing to the best recordedperformance of the LSTM the on-chip sensor fusion with the utilised IMU was 15.8%more accurate and 70.8% more precise in estimating orientation from accelerometer,gyroscope and magnetometer readings. Despite this conclusion the study has found results indicating that significant improvements regarding orientating with LSTMsare within close reach.

Abstract [sv]

Numeriska metoder för laterering och sensorfusion är begränsade av inneboende mätfeloch det är möjligt att alternativa tillvägagångssätt skulle gynna prestanda inompositionering. Denna avhandling söker utvärdera frågan genom att undersöka djupinlärningoch dess tillämpning i ett lokalt positioneringssystem baserat på Ultra-Wide-Band (UWB) radio och data från en Inertial Measurement Unit (IMU). Med hjälp avRobotic Operating System (ROS) och en självkörande plattform samlades tidsstämpladsensordata in i kombination med den sanna positionen erhållen av ett referenssystem.Därefter tränades ett neuronnätverk av typen Long Short-Term Memory(LSTM) till att tillhandahålla uppskattningar av plattformens tvådimensionella koordinateroch orientering i planet. Neuronnätverkets prestanda utvärderades sedan itermer av noggrannhet som därefter jämfördes med konventionella tillvägagångssättför positionering och orientering. Resultaten pekar på att nätverket applicerar välpå positioneringsproblemet, däremot kan inte studien entydigt påvisa förmåga attestimera en orientering. Slutsatserna från denna avhandling är att nätverket ökarnoggrannheten för positionering med 79.9% och precisionen med 71.8% i jämförelsemed ickelinjär minsta kvadratmetod. Jämförelsevis presterar IMU:ns inbyggda sensorfusionbättre än nätverket i termer av orienteringsförmåga med 15.8% och 70.8%i noggrannhet respektive precision. Trots denna slutsats identifieras resultat som antyder att signifikanta förbättringar avseende orientering med LSTM är inom nära räckhåll.

Place, publisher, year, edition, pages
2018. , p. 91
Series
TRITA-ITM-EX ; 2018:200
National Category
Mechanical Engineering
Identifiers
URN: urn:nbn:se:kth:diva-232842OAI: oai:DiVA.org:kth-232842DiVA, id: diva2:1236637
External cooperation
Cybercom AB
Supervisors
Examiners
Available from: 2018-08-03 Created: 2018-08-03 Last updated: 2018-08-03Bibliographically approved

Open Access in DiVA

fulltext(13736 kB)8 downloads
File information
File name FULLTEXT01.pdfFile size 13736 kBChecksum SHA-512
2af1d6709aca6cb90b14c07fd68f2957259b02bf46d779fb23609cbde851865df45669f6bb4a004247199eedee2d40186155a0880c9ce1d840e11ec2bdf336e5
Type fulltextMimetype application/pdf

By organisation
Machine Design (Dept.)
Mechanical Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 8 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: 5 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