Browsing Institutt for teknisk kybernetikk by Title
Now showing items 1109-1128 of 3698
-
Disturbance Rejection using Conditional Integrators: Applications to path manoeuvring under environmental disturbances for single vessels and vessel formations
(Doktoravhandlinger ved NTNU, 1503-8181; 2011:4, Doctoral thesis, 2011)In this thesis, two main topics are discussed: the application of conditional integrators for disturbance rejection, and how to apply this to path following and trajectory tracking of single marine vehicles and vehicle ... -
A divided and prioritized experience replay approach for streaming regression
(Peer reviewed; Journal article, 2021)In the streaming learning setting, an agent is presented with a data stream on which to learn from in an online fashion. A common problem is catastrophic forgetting of old knowledge due to updates to the model. Mitigating ... -
DNN-based anomaly prediction for the uncertainty in visual SLAM
(Chapter, 2023)The method described in this paper proposes a supervised Deep Neural Network (DNN) approach for the prediction of anomalies in camera-based navigation. The method is inspired by the unsolved issues of Integrity Monitors ... -
Do it yourself hyperspectral imager for handheld to airborne operations
(Journal article; Peer reviewed, 2018)This study describes rapid prototype construction of small and lightweight push broom Hyper Spectral Imagers (HSI). The dispersive element housings are printed by a thermoplastic 3D printer combined with S-mount optical ... -
Do-it-yourself VIS/NIR pushbroom hyperspectral imager with C-mount optics
(Peer reviewed; Journal article, 2022)This paper describes a new optomechanical design based on a previously presented do-it-yourself pushbroom hyperspectral imager (HSI) using commercial off-the-shelf (COTS) components. The new design uses larger aperture ... -
Dokking av AUV ved bruk av feiltilstands-kalmanfilter
(Master thesis, 2017)Det er et økende behov for algoritmer for dokking av AUVer. Det som finnes i litteraturen i dag er løsninger på konkrete problemer, noe som gjør dem mer komplisert enn dokkingproblemet i seg selv. Denne oppgaven gjør et ... -
Domain Adaptation for Detection of Maritime Vessels in Images
(Master thesis, 2021)Deteksjon av objekter er imperativt for situasjonsforståelse i autonome systemer og bidrar til trygg og kontrollert autonom navigasjon. I maritime miljøer er kamerabaserte detektorer et av de viktigste systemene som gir ... -
Domain Adaptation for Maritime Instance Segmentation: From Synthetic Data to the Real-World
(Master thesis, 2019)Denne avhandlingen tar sikte på å utforske praktiske implikasjoner ved bruk av en maritim simulator for rask generering av syntetiske instans-baserte sannhets-merkede bilder med det formål å trene modeller basert på ... -
Domain Knowledge in Real-Time Programming
(Master thesis, 2020)Bruk av domenekunnskap er generelt sett på som systemspesifikke løsninger som ikke kan tilby noe generalitet for strategier innen sanntidsprogrammering. Formålet med denne avhandlingen var å undersøke hva uttrykket ... -
Double Moving Horizon Estimation: Linearization by a Nonlinear Transformation
(Chapter, 2018)Moving horizon estimation (MHE) is a con- strained non-convex optimization problem in principle, which needs to be solved online. One approach to avoid dealing with several local minima is to linearize the nonlinear dynamics. ... -
DP and the Art of Perfect Positioning
(Journal article; Peer reviewed, 2022) -
DrillFeel - Haptic Feedback for Enhancing Drillers Situational Awareness
(Master thesis, 2023)Offshore drilling er en risikofylt operasjon med potensielt dødelige konsekvenser hvis et system svikter eller operatøren mister situasjonsbevisstheten og derfor gjør feil. Dagens løsninger for drilling og boring innebærer ... -
Drilling mud property estimator
(Master thesis, 2013)In 1969 the first petroleum discovery was made on the Norwegian continental shelf. This founding marks the beginning of what has become the most important contribution to the Norwegian economy. Advanced research within the ... -
Drillstring Washout Diagnosis using Friction Estimation and Statistical Change Detection
(Journal article; Peer reviewed, 2015)In oil and gas drilling, corrosion or tensile stress can give small holes in the drillstring, which can cause leakage and prevent sufficient flow of drilling fluid. If such \emph{washout} remains undetected and develops, ... -
Driver Interface for Shell Eco Marathon Vehicles
(Master thesis, 2015)The goal of this thesis was to create a touch-screen system for the driver in the new DNV GL Fuel Fighter Urban Concept vehicle. The screen was to display relevant information for the driver, as well as a video-stream from ... -
Driving Strategy Optimisation in DNV GL Fuel Fighter
(Master thesis, 2021)Denne oppgaven utforsker forskjellige metoder for å finne en kjøre-strategi for DNV GL Fuel Fighter i Shell Eco-Marathon(SEM) konkurransen. Oppgaven går gjennom stiplanlegging, kjørestrategi og matematisk modellering av ... -
Drone Design and Construction for Indoor Inspection Scenarios
(Master thesis, 2018)The need for using drones for indoor inspection scenarios is sought after. The benefits of reducing both time and risk are to big to not pursue a solution. This project has proven that a functional drone prototype for ... -
Drop and Recovery of Sensor Nodes Using UAVs
(Master thesis, 2014)The goal of this project is to make a system able of executing drop and recovery of sensor nodes at sea by the use of UAVs.The sensor node will be a lightweight packet that can contain different sensors depending on the ... -
Dual Active Sampling: A batch-mode active learning method
(Master thesis, 2019)Nylig har CNN vist enestående suksess innen datasyn, spesielt for utfordrende bildeklassifiseringsoppgaver ved å basere seg på en universal tilnærming, mao. trene en dyp model på et massivt datasett med veiledende eksempler. ... -
Dual adaptive model predictive control
(Journal article; Peer reviewed, 2017)We present an adaptive dual model predictive controller (dmpc) that uses current and future parameter-estimation errors to minimize expected output error by optimally combining probing for uncertainty reduction with control ...