Blar i NTNU Open på forfatter "Moe, Signe"
-
Accelerating Reinforcement Learning with Suboptimal Guidance
Bøhn, Eivind Eigil; Moe, Signe; Johansen, Tor Arne (Peer reviewed; Journal article, 2020)Reinforcement learning in domains with sparse rewards is a difficult problem, and a large part of the training process is often spent searching the state space in a more or less random fashion for learning signals. For ... -
Additive Manufacturing by Robot: An Overview of the State-of-the-Art and Proof-of-Concept Results
Evjemo, Linn Danielsen; Moe, Signe; Gravdahl, Jan Tommy; Roulet-Dubonnet, Olivier; Brøtan, Vegard; Gellein, Lars Tore (Chapter, 2017)For the last decades, additive manufacturing (AM) has become an ever increasing part of the development of new technology and devices. However, it is still challenging to use this technology on a larger scale. This paper ... -
Additive manufacturing of thin-walled structures by robot manipulator : An experimental approach focusing on arc welding
Evjemo, Linn Danielsen (Doctoral theses at NTNU;2022:208, Doctoral thesis, 2022)Additive manufacturing (AM) has, over recent decades, become a quickly evolving and ever more present part of production and manufacturing. It has gone from being a simple prototyping method to building more complex ... -
Collision Avoidance for Autonomous Surface Vehicles Using Velocity Obstacle and Set-Based Guidance.
Myre, Helene (Master thesis, 2016)A good and reliable collision avoidance method is essential when operating Autonomous Surface Vehicles (ASVs) at sea. But even though avoiding collisions is the most important part, making sure the ASV's evasive maneuvers ... -
Compressor Surge Control Using Lyapunov Neural Networks
Neverlien, Åse; Moe, Signe; Gravdahl, Jan Tommy (Peer reviewed; Journal article, 2020)In this paper surge control in a compression system using a close-coupled valve (CCV) is proposed. The control design is based on Lyapunov control theory in combination with neural networks (NNs) and focuses on minimization ... -
Deep Reinforcement Learning Attitude Control of Fixed Wing UAVs Using Proximal Policy Optimization
Bøhn, Eivind Eigil; Coates, Erlend Magnus Lervik; Moe, Signe; Johansen, Tor Arne (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 ... -
Experimental Results for Set-based Control within theSingularity-robust Multiple Task-priority Inverse KinematicsFramework
Moe, Signe; Antonelli, Gianluca; Pettersen, Kristin Ytterstad; Schrimpf, Johannes (Journal article; Peer reviewed, 2015)Inverse kinematics algorithms are commonly used in robotic systems to achieve desired behavior, and several methods exist to ensure the achievement of numerous tasks simultaneously. The multiple task priority inverse ... -
Guidance and Control of Robot Manipulators and Autonomous Marine Robots
Moe, Signe (Doctoral theses at NTNU;2016:322, Doctoral thesis, 2016)This thesis is motivated by the increasing use of robots within numerous fields and in a vast range of applications. The use of robots provides several advantages, e.g. reduced labor costs, increased production and ... -
Incorporating set-based control within the singularity-robust multiple task-priority inverse kinematics
Antonelli, Gianluca; Moe, Signe; Pettersen, Kristin Ytterstad (Journal article; Peer reviewed, 2015)Inverse kinematics is an active research domain in robotics since several years due to its importance in multiple robotics application. Among the various approaches, differential inverse kinematics is widely used due to ... -
Kinematic singularity avoidance for robot manipulators using set-based manipulability tasks
Sverdrup-Thygeson, Jørgen; Moe, Signe; Pettersen, Kristin Ytterstad; Gravdahl, Jan Tommy (Chapter, 2017)This paper proposes a novel method for kinematic singularity avoidance for robot manipulators. Using set-based singularity avoidance tasks within the singularity-robust multiple task priority framework, avoidance of kinematic ... -
Line-of-Sight Curved Path Following for Underactuated USVs and AUVs in the Horizontal Plane under the influence of Ocean Currents
Fossen, Thor I.; Moe, Signe; Pettersen, Kristin Ytterstad; Gravdahl, Jan Tommy (Journal article; Peer reviewed, 2016)An essential ability of autonomous unmanned surface vessels (USVs) and autonomous underwater vehicles (AUVs) moving in a horizontal plane is to follow a general two-dimensional path in the presence of unknown ocean currents. ... -
Linear Antisymmetric Recurrent Neural Networks
Moe, Signe; Remonato, Filippo; Grøtli, Esten Ingar; Gravdahl, Jan Tommy (Peer reviewed; Journal article, 2020)Recurrent Neural Networks (RNNs) have a form of memory where the output from a node at one timestep is fed back as input the next timestep in addition to data from the previous layer. This makes them highly suitable for ... -
Moisture Estimation using Discrete ElementMethod Simulations of Granular Materials
Brungot, Kristoffer (Master thesis, 2021)Abstract will be available on 2024-06-30 -
Neural Network-based Model Predictive Control with Input-to-State Stability
Seel, Katrine; Grøtli, Esten Ingar; Moe, Signe; Gravdahl, Jan Tommy; Pettersen, Kristin Ytterstad (Peer reviewed; Journal article, 2021)Learning-based controllers, and especially learning-based model predictive controllers, have been used for a number of different applications with great success. In spite of good performance, a lot of these cases lack ... -
Null-Space-Based Behavior Guidance of PlanarDual-Arm UVMS
Moe, Signe; Antonelli, Gianluca; Pettersen, Kristin Ytterstad (Chapter, 2014) -
Optimization of the model predictive control meta-parameters through reinforcement learning
Bøhn, Eivind Eigil; Gros, Sebastien Nicolas; Moe, Signe; Johansen, Tor Arne (Peer reviewed; Journal article, 2023)Model predictive control (MPC) is increasingly being considered for control of fast systems and embedded applications. However, MPC has some significant challenges for such systems, such as its high computational complexity. ... -
Path Following of Underactuated Marine Surface Vessels in the Presence of Unknown Ocean Currents
Moe, Signe; Caharija, Walter; Pettersen, Kristin Ytterstad; Schjølberg, Ingrid (Journal article; Peer reviewed, 2014)This paper considers path following control of snake robots and has two contributions. The first contribution is a description of how a straight line path following controller previously proposed by the authors can be ... -
Path Following of Underactuated Marine Vessels in the Presence of Ocean Currents
Moe, Signe (Master thesis, 2013)The use of marine vessels, especially underwater vehicles, is rapidly increasing. Autonomous marine vehicles are a huge focus area within the oil and gas industry, and can also be utilized for scientific, environmental and ... -
Path Following, Obstacle Detection and Obstacle Avoidance for Thrusted Underwater Snake Robots
Kelasidi, Eleni; Moe, Signe; Pettersen, Kristin Ytterstad; Kohl, Anna M; Liljebäck, Pål; Gravdahl, Jan Tommy (Journal article; Peer reviewed, 2019)The use of unmanned underwater vehicles is steadily increasing for a variety of applications such as mapping, monitoring, inspection and intervention within several research fields and industries, e.g., oceanography, marine ... -
Robotised Wire Arc Additive Manufacturing Using Set-based Control: Experimental Results
Evjemo, Linn Danielsen; Moe, Signe; Gravdahl, Jan Tommy (Peer reviewed; Journal article, 2020)Additive manufacturing (AM) is a term that covers a variety of techniques for building custom-made, three dimensional structures. Such methods have moved from initially being used for creating simpli_ed models to enable ...