Browsing Institutt for maskinteknikk og produksjon by Author "Egeland, Olav"

Now showing items 41-60 of 121

    • Efficient Perspective-n-Point With Graduated Non-Convexity for Outlier Robustness 

      Jåtun, Runar (Master thesis, 2023)
      Perspective-n-Point (PnP) er et fundamentalt problem innen datasyn. Problemet dreier seg om å estimere posisjon og orientering av et kamera i en kjent situasjon. Mer bestemt så kjenner man et sett av tredimensjonale punkter ...

    • Elimination of Reflections in Laser Scanning Systems with Convolutional Neural Networks 

      Alstad, Ola; Egeland, Olav (Peer reviewed; Journal article, 2022)
      This paper presents a machine learning approach for eliminating reflections in line laser scanning of aluminium workpieces to be welded. The elimination of reflections is important to obtain accurate laser scanning of ...

    • Elimination of Reflections in Laser Scanning Using Transfer Learning from Simulation-Based Data to Real-World Data 

      Holm, Amalie Berge; Kallseter, Kasper (Master thesis, 2022)
      Automatisering av robotsveising krever presis og korrekt informasjon. Laserskanning er en metode for å samle relevant data om sveiseområde, men laseren kan forårsake re- fleksjoner på skinnende materialer, som resulterer ...

    • Elimination of Reflections in Laser Scanning Using Transfer Learning from Simulation-Based Data to Real-World Data 

      Holm, Amalie Berge; Kallseter, Kasper (Master thesis, 2022)
      Automatisering av robotsveising krever presis og korrekt informasjon. Laserskanning er en metode for å samle relevant data om sveiseområde, men laseren kan forårsake re- fleksjoner på skinnende materialer, som resulterer ...

    • Enabling visual SLAM on low-cost hardware for drone control 

      Stokke, Bendik Rolf; Grønli, Simen Galland (Master thesis, 2023)
      Denne studien har som formål å utvikle et kostnadseffektivt dronesystem som benytter lett tilgjengelig maskinvare og åpen kildekode-programvare for å forbedre funksjonaliteten til en kommersielt tilgjengelig drone. Spesifikt, ...

    • Enabling visual SLAM on low-cost hardware for drone control 

      Grønli, Simen Galland; Stokke, Bendik Rolf (Master thesis, 2023)
      Denne studien har som formål å utvikle et kostnadseffektivt dronesystem som benytter lett tilgjengelig maskinvare og åpen kildekode-programvare for å forbedre funksjonaliteten til en kommersielt tilgjengelig drone. Spesifikt, ...

    • Estimating the Design Parameters of a Highly Skewed Ship Propeller by Automated 3D-scanning 

      Munthe-Kaas, Njål Haagensli (Master thesis, 2018)
      Ship propellers have a highly complex surface geometry. Certain design parameters are commonly used to describe this complex geometry. During production of the propeller blades there is a need for measuring the blade ...

    • Estimation of ship-deck motion using lidar, gyroscopes and cameras 

      Holen, Hans Kristian Raknerud; Sjøberg, Alexander Meyer; Egeland, Olav (Peer reviewed; Journal article, 2021)
      This paper presents a system for the estimation of ship deck motion using camera, lidar and gyroscopes. A camera is used in a vision system that is based on the detection of lines as input to a vanishing point detector. ...

    • Experimental Study of Hydraulic Accumulator Discharge 

      Stenhjem, Marcus Aleksander (Master thesis, 2018)
      This thesis aims to identify the behaviour of a 4 l hydraulic bladder accumulator undergoing discharge under various conditions and ultimately shed some light on irregularities that OneSubsea Processing is experiencing ...

    • Extrinsic calibration for motion estimation using unit quaternions and particle filtering 

      Sveier, Aksel; Egeland, Olav (Peer reviewed; Journal article, 2020)
      This paper presents a method for calibration of the extrinsic parameters of a sensor system that combines a camera with an inertial measurement unit (IMU) to estimate the pendulum motion of a crane payload. The camera ...

    • Identification of the geometric design parameters of propeller blades from 3D scanning 

      Njaastad, Eirik B; Steen, Sverre; Egeland, Olav (Peer reviewed; Journal article, 2022)
      This paper presents a new method for the identification of geometric design parameters of ISO 484 class propeller blades from scanned point cloud data. The method can be used for tolerance inspection and in-line measurement ...

    • Implicit Regularization in Machine Learning for Adaptive Control 

      Nilssen, Johannes Giercksky (Master thesis, 2021)
      Moderne maskinlæring bruker svært overparameteriserte modeller som kan tilpasses treningsettet feilfritt og fortsatt prestere godt på testsettet. Ny forskning knytter denne evnen til gradientmetodene brukt for å optimalisere ...

    • Industry 4.0 - Digital Twins and OPC UA 

      Øvern, Aksel (Master thesis, 2018)
      This project explores the term Industry 4.0 (I 4.0) and the use of Digital Twins (DTws) as an asset in this modern industrial revolution. A DTw can be described as a digital replica of a physical system including data about ...

    • Integritetsevaluering av Ring Joint flensforbindelse 

      Alnæs, Merethe (Master thesis, 2013)
      Med stadig høyere krav til redusert utslipp i olje- og gassindustrien er flensforbindelser en viktig komponent å sette fokus på. Flensforbindelser er blant annet brukt i subsea omgivelser til å skjøte sammen rørsystemer ...

    • Inverse kinematics for industrial robots using conformal geometric algebra 

      Kleppe, Adam Leon; Egeland, Olav (Journal article; Peer reviewed, 2016)
      This paper shows how the recently developed formulation of conformal geometric algebra can be used for analytic inverse kinematics of two six-link industrial manipulators with revolute joints. The paper demonstrates that ...

    • Investigation of Vision Transformers for Visual Place Recognition 

      Mjølhus, Øyvind Wormdal (Master thesis, 2021)
      Fremskritt innen autonom robotikk kan ha store konsekvenser for samfunnet som helhet i fremtiden. Et av de største hindrene som forhindrer virkelig autonome roboter er utfordringen med å skulle kunne sikkert lokalisere seg ...

    • Kinematic Feedback Control Using Dual Quaternions 

      Sjøberg, Alexander Meyer; Egeland, Olav (Chapter, 2018)
      This paper presents results on kinematic controllers for the stabilization of rigid body displacements using dual quaternions. The paper shows how certain results for quaternion stabilization of rotation can be extended ...

    • Kinematics and Dynamics of Flexible Robotic Manipulators Using Dual Screws 

      Cibicik, Andrej; Egeland, Olav (Peer reviewed; Journal article, 2020)
      In this article, we present a new procedure for the derivation of the linearized kinematics and dynamics of a flexible industrial robotic manipulator. We introduce the Lie groups of dual rotation and dual homogeneous ...

    • Laser Scanning and Parametrization of Weld Grooves with Reflective Surfaces 

      Cibicik, Andrej; Tingelstad, Lars; Egeland, Olav (Peer reviewed; Journal article, 2021)
      This paper presents a novel weld groove parametrization algorithm, which is developed specifically for weld grooves in typical stub and butt joints between large tubular elements. The procedure is based on random sample ...

    • Learning of Nonlinear Dynamics with Contraction-Based Regularization 

      Phan, Helena Thu; Kenworthy, Vilde Taklo (Master thesis, 2023)
      Å lære ukjente dynamiske systemer er en kompleks oppgave som involverer å utlede den underliggende systematferden fra observert data, uten forkunnskaper om de underliggende ligningene. Å forstå og nøyaktig lære dynamikken ...