Browsing NTNU Open by Author "Lekkas, Anastasios"
Now showing items 41-60 of 61
-
Optimization-based Planning and Control for Autonomous Surface Vehicles
Martinsen, Andreas Bell (Doctoral theses at NTNU;2021:164, Doctoral thesis, 2021)With autonomy offering a number of benefits in robotics applications, such as increased safety, better consistency and reliability, reduced environmental impact and higher efficiency, it is not surprising that the topic ... -
Path Following and Collision Avoidance for Marine Vessels with Deep Reinforcement Learning
Vallestad, Ingunn Johanne (Master thesis, 2019)Interessen for fullt autonome kjøretøy har økt raskt i løpet av de siste årene, motivert av løfter om økt effektivitet samt reduserte kostnader og miljøpåvirkning. Innenfor fartøystyring er kollisjonsunngåelse en viktig ... -
Path Following in Simulated Environments using the A3C Reinforcement Learning Method
Lund, Emil Andreas (Master thesis, 2018)Using reinforcement learning as a part of a Guidance, Navigation and Control (GNC) system is a relatively unexplored field. This thesis explores the use of deep reinforcement learning in a path following control algorithm ... -
Path Planning and Guidance for Marine Surface Vessels
Dahl, Andreas Reason (Master thesis, 2013)Path planning and guidance for marine surface vesselsis the main topic of this thesis. The subject is of great relevance both for unmanned surface vehicles (USV) and for autopilot systems for manned vessels.A general ... -
Path Planning for Multi-Rotor Unmanned Aerial Vehicles (UAVs) Operating in Known Confined Space
Vennestrøm, Daniel (Master thesis, 2022)Denne masteroppgaven anser et bruksområde hvor en multi-rotor inspeksjons dronen autonomt skal inspisere et sett med punkter inne i en ballast tank på et skip. For å oppnå dette, så er et av de første stegene å implementere ... -
Path Planning for Vehicle Motion Control Using Numerical Optimization Methods
Roald, Ann Louise (Master thesis, 2015)Path planning is an important part of many systems, especially autonomous systems. Finding the optimal paths for various vehicles, given different optimization criteria such as the shortest, fastest, straightest or ... -
Perception and High-Level Control for Autonomous Drone Missions
Hove, Peter Bull (Master thesis, 2021)Denne oppgaven presenterer et autonomt drone-system som muliggjør for en drone å gjennomføre autonome oppdrag som starter og slutter på en bestemt landingsplattform. En tilstandsestimeringsalgorimte er laget for å estimere ... -
Planning, Scheduling and Control for Autonomous Passenger Ferry Operations in Urban Environments
Nilsen, Kristian (Master thesis, 2023)De fleste urbane områder er på en aller annen måte tilknyttet en vannvei, fordi dette har historisk sett vært viktig. I moderne tid har ikke vannveier blitt brukt like mye fordi det har vært ansett for å være for kostbart. ... -
Reinforcement Learning for Robotic Manipulation
Vagle, Anders Haver (Master thesis, 2019)Denne oppgaven tar for seg detaljer rundt implementasjon av PPO-algoritme for trening på egendefinerte miljøer designet for robotikk-basert manipulasjon. Resultatene er lovende for de forenklede miljøene i simulering, men ... -
Reinforcement Learning-based Control and State Estimation using Model Predictive Control and Moving Horizon Estimation
Esfahani, Hossein Nejatbakhsh (Doctoral theses at NTNU;2024:269, Doctoral thesis, 2024)A new Reinforcement Learning (RL) algorithm based on Model Predictive Control (MPC) has been recently proposed in which the optimal state (-action) value function and the optimal policy can be captured by a parameterized ... -
Reinforcement learning-based NMPC for tracking control of ASVs: Theory and experiments
Martinsen, Andreas Bell; Lekkas, Anastasios; Gros, Sebastien (Peer reviewed; Journal article, 2022)We present a reinforcement learning-based (RL) model predictive control (MPC) method for trajectory tracking of surface vessels. The proposed method uses an MPC controller in order to perform both trajectory tracking and ... -
Robotic manipulation using Deep Reinforcement Learning
Remman, Sindre Benjamin (Master thesis, 2020)Det å forbedre roboters autonomi har lenge vært et mål for forskere. Ulike verktøy har blitt brukt for å gjøre dette, og dagens roboter er mer autonome enn noen gang før. Det er imidlertid fortsatt noe som mangler. For at ... -
Static and dynamic multi-obstacle avoidance for docking of ASVs using computational geometry and numerical optimal control
Ødven, Petter Knutsen (Master thesis, 2022)Autonome system vil sannsynligvis ha stor innvirkning på vårt neste-generasjons moderne samfunn og ersatte mennesker i en rekke av dagens oppgaver. Automatisk dokking av autonome overflatefartøy er intet unntak. Å overmanne ... -
Synthesizing Photo-Realistic images from a Marine Simulator via Generative Adversarial Networks
Bekkeheien, Lone Marselia Werness (Master thesis, 2020)Det er dyrt å skaffe enorme mengder data fra den virkelig verden. Derfor er det rimelig å trene deteksjonsalgoritmer i et simulert miljø. Imidlertid er det en forskjell mellom simulert miljø og den virkelige verden referert ... -
Theoretical Properties of Learning-based Model Predictive Control
Kordabad, Arash Bahari (Doctoral theses at NTNU;2023:82, Doctoral thesis, 2023)Recently, the core idea of using Model Predictive Control (MPC) as a function approximator for the Reinforcement Learning (RL) methods has been proposed and justified. More specifically, it has been shown that a parameterized ... -
Towards mission planning for search and rescue at sea
Solbø, Øystein (Master thesis, 2023)Et redningsoppdrag kan foregå over store områder. Disse må gjennomsøkes nøye og effektivt, noe flygende droner er spesielt egnet til. Flygende droner blir overvåket av menneskelige operatører, og koordinert med henhold til ... -
Towards the Development of Autonomous Ferries
Bitar, Glenn Ivan (Master thesis, 2017)Autonomous ships is at the moment a heavily researched topic in the maritime industry. Development to introduce autonomous ferries in the Norwegian fjords is under way. This thesis is a study of technical and formal ... -
Trajectory Planning and Control for Automatic Docking of ASVs with Full-Scale Experiments
Bitar, Glenn Ivan; Martinsen, Andreas Bell; Lekkas, Anastasios; Breivik, Morten (Peer reviewed; Journal article, 2020)We propose a method for performing automatic docking of a small autonomous surface vehicle (ASV) by interconnecting an optimization-based trajectory planner with a dynamic positioning (DP) controller for trajectory tracking. ... -
Two Space-Time Obstacle Representations Based on Ellipsoids and Polytopes
Martinsen, Andreas Bell; Lekkas, Anastasios (Journal article; Peer reviewed, 2021)When operating autonomous surface vessels in uncertain environments with dynamic obstacles, planning safe trajectories and evaluating collision risk is key to navigating safely. In order to perform these tasks, it is ... -
Two-Stage Optimized Trajectory Planning for ASVs Under Polygonal Obstacle Constraints: Theory and Experiments
Bitar, Glenn Ivan; Martinsen, Andreas Bell; Lekkas, Anastasios; Breivik, Morten (Peer reviewed; Journal article, 2020)We propose a method for energy-optimized trajectory planning for autonomous surface vehicles (ASVs), which can handle arbitrary polygonal maps as obstacle constraints. The method comprises two stages: The first is a hybrid ...