Digitala Vetenskapliga Arkivet

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
Development and Study of 3D Printed Compliant Sensors for Robot Proprioception
KTH, School of Industrial Engineering and Management (ITM).
2023 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Utveckling och studier av 3D-utskrivna sensorer för robotproprioception (Swedish)
Abstract [en]

This thesis focused on the development of a novel embedded sensor for the existing continuum actuator for the Honda Haru robot. The newly developed sensor will enable the sensing to Roll and Pitch without modifying the actuator’s external geometry. The sensor will serve as a basis for future dynamic load sensing capabilities for the robot.

After development the sensor was embedded to the actuator of the robot. The newly developed sensor was thoroughly modeled and provides Roll and Pitch sensing capabilities on Simulink. Linear models and neural network models were developed to enable the use of sensors in different scenarios.

With continual learning, the newly developed sensor array model can dynamically evolve while providing an accurate model with respect to ground truth.An incremental learning model is also developed to enable future expansion of capability of the sensor with Python.

Abstract [sv]

Den här masteruppsatsen fokuserade på utvecklingen av en ny inbyggd sensor för den befintliga kontinuum aktuatorn för Honda Haru-roboten. Den nyutvecklade sensorn kommer att möjliggöra avkänning av rollning och stigning utan att ändra aktuatorns externa geometri. Sensorn kommer att tjäna som grund för framtida dynamiska lastavkänningsförmågor för roboten. Efter utvecklingen är sensorn inbäddad i robotens aktuator. Den nyligen utvecklade sensorn modellerades noggrant och erbjuder förmågor att avkänna rollning och stigning i Simulink. Linjära modeller och neurala nätverksmodeller utvecklades för att möjliggöra användning av sensorer i olika scenarier. Med kontinuerligt lärande kan den nyligen utvecklade ”sensor array”-modellen dynamiskt utvecklas samtidigt som den ger en exakt modell i förhållande till verklig data. En inkrementell inlärningsmodell har också utvecklats för att möjliggöra framtida utvidgning av sensorns förmågor med Python. 

Place, publisher, year, edition, pages
2023. , p. 48
Series
TRITA-ITM-EX ; 2023:639
Keywords [en]
Soft Robotics, Continual learning, 3D-printing, Soft sensor, Sensor modelling, Proprioception
Keywords [sv]
Mjuk robotik, kontinuerlig inlärning, 3d-utskrivning, Mjuk sensor, Sensormodellering, Proprioception
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-342433OAI: oai:DiVA.org:kth-342433DiVA, id: diva2:1829500
Subject / course
Mechatronics
Educational program
Master of Science - Industrial Engineering and Management
Supervisors
Examiners
Available from: 2024-07-18 Created: 2024-01-19 Last updated: 2024-01-19

Open Access in DiVA

fulltext(2537 kB)356 downloads
File information
File name FULLTEXT01.pdfFile size 2537 kBChecksum SHA-512
53d1e91e4dbd248a42feb1ca09f393e546d4f210c35a6e7c5339ff519226adcff3d544df72d57c852d358328b0a9d1c15d042ac8fffb92291f335545ed6df6bc
Type fulltextMimetype application/pdf

By organisation
School of Industrial Engineering and Management (ITM)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 357 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: 405 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