Browsing Institutt for teknisk kybernetikk by Title
Now showing items 897-916 of 3663
-
Deep Reinforcement Learning Applied to Targeted Oceanographic Sampling for an Autonomous Underwater Vehicle: Comparing Machine Learning and Model Based Approaches in a Simulated Environment
(Master thesis, 2021)Dyp forsterkende læring ble benyttet i et forsøk på å få en autonom under-vannsdrone til å oppsøke biologiske varmepunkter ("hotspots") av plankton iet simulert miljø. Prosedyrisk generert planktondata ble benyttet for å ... -
Deep Reinforcement Learning Attitude Control of Fixed Wing UAVs Using Proximal Policy Optimization
(Chapter, 2019)Contemporary autopilot systems for unmanned aerial vehicles (UAVs) are far more limited in their flight envelope as compared to experienced human pilots, thereby restricting the conditions UAVs can operate in and the types ... -
A deep reinforcement learning based approach towards generating human walking behavior with a neuromuscular model
(Peer reviewed; Journal article, 2019)A gait model capable of generating human-like walking behavior at both the kinematic and the muscular level can be a very useful framework for developing control schemes for humanoids and wearable robots such as exoskeletons ... -
Deep Reinforcement Learning Controller for 3D Path-following and Collision Avoidance by Autonomous Underwater Vehicles
(Peer reviewed; Journal article, 2020)In this article, we explore the feasibility of applying proximal policy optimization, a state-of-the-art deep reinforcement learning algorithm for continuous control tasks, on the dual-objective problem of controlling an ... -
Deep Reinforcement Learning for Model-Free Continuous Control with an Emphasis on Trust Region Policy Optimization
(Master thesis, 2017)Reinforcement learning is a general framework for optimizing the behavioural policy of an agent in an environment that issues a scalar reward indicating how well the agent is performing. Reinforcement learning algorithms ... -
Deep Reinforcement Learning for Valve Manipulation
(Master thesis, 2019)Denne oppgaven er inspirert av den raske utviklingen innen kunstig intelligens, særlig forsterkende læring, og den økte anvendelsen for praktiske formål, blant annet til undervannsoperasjoner i olje- og gassindustrien, og ... -
Deep-learning algorithms for estimation of fish-population parameters from stereo vision video data
(Master thesis, 2023)Denne masteroppgaven fokuserer på å analysere hvordan fiskeadferd påvirkes av undervannsstrukturer med varierende former og farger, hovedsakelig målt i form av avstanden de opprettholder fra strukturen. For å sikre robusthet ... -
Deep-learning algorithms for estimation of fish-population parameters from video data
(Master thesis, 2022)Denne hovedoppgaven presenterer en metode for å estimere distansen og hastigheten til fisk ved å bruke to dyplæring metoder og et stereoskopisk kamera i samarbeid med SINTEF Ocean. Stereobilder er fanget av kameraet og ... -
DefiFunds - A Dapp on Radix
(Master thesis, 2023)I denne masteroppgaven har en desentralisert applikasjon (Dapp) kalt DefiFunds blitt videreutviklet. Et konseptbevis for denne Dappen ble laget på Radix under mitt spesialiseringsprosjekt høsten 2022. Radix er fremdeles i ... -
Defining Three Distribution System Scenarios for Microgrid Applications
(Chapter, 2020)Power systems, especially distribution systems, are undergoing the most drastic overhauls with the growing integration of renewable energy and digitalization. One of the most efficient technological solutions to address ... -
Degradation in Barch Reactors – Data-driven Modeling and Optimal Operation
(Doctoral theses at NTNU;2020:92, Doctoral thesis, 2020) -
Demonstrering av konsept for innsamling og sammenstilling av data fra flere vannmålere ved bruk av trådløs M-Bus
(Master thesis, 2018)Flere typer måleinstrumenter kommer med et grensesnitt for trådløs avlesning, deriblant trykkmålere, gassmålere, eller strømmålere. For overføring av måledata fra disse sensorene er trådløs M-Bus blitt en mye brukt standard. ... -
Deployment of a Mobile Sensor Network using different control methods
(Master thesis, 2020)Førsterespondere er de første til å ankomme et åsted og i mange situasjoner utsetter de seg selv i stor fare for å hjelpe andre. Ny teknologi kan øke sikkerheten og gjøre arbeidet lettere for de som ankommer åstedet. ... -
Depth Estimation and Object Detection using Stereo Vision for Autonomous Ferry
(Master thesis, 2021)I denne avhandlingen evaluerers flere methoder for løsing av korrespondanseproblemet og objektdeteksjon ved bruk av stereokamera. For løsing av korrespondanseproblemet ble den lokale metoden Sum of Absolute Differences og ... -
Derivation of flow rate and calibration method for high-volume air samplers
(Journal article; Peer reviewed, 2019)High-volume air sampling is a key measurement technique for investigating the concentration of atmospheric pollutants. Despite being a mature technique, a detailed description of how to derive flow rates and how to calibrate ... -
Design and Analysis of a Hybrid Position/Force Controller for Robotic Rehabilitation of Upper Limb after Stroke
(Master thesis, 2016)There is an increasing number of stroke victims, leading to an increasing number of motor deficits as a result of stroke. Rehabilitation is an important factor in trying to improve the life quality of stroke victims. General ... -
Design and comparison of adaptive estimators for Under-balanced Drilling
(Book, 2014)Real time knowledge of total mass of gas and liquid in the annulus and geological properties of the reservoir is very useful in many active controllers, fault detection systems and safety applications in the well during ... -
Design and comparison of adaptive estimators for Under-Balanced Drilling
(Journal article, 2014)Real time knowledge of total mass of gas and liquid in the annulus and geological properties of the reservoir is very useful in many active controllers, fault detection systems and safety applications in the well during ... -
Design and Comparison of Constrained MPC with PID Controller for Heave Disturbance Attenuation in Offshore Managed Pressure Drilling Systems
(Journal article, 2014)This paper presents a constrained finite horizon model predictive control (MPC) scheme for regulation of the annular pressure in a well during managed pressure drilling from a floating vessel subject to heave motion. In ... -
Design and Construction of a Package Scanning System
(Master thesis, 2021)Abstract will be available on 2024-05-31