Blar i NTNU Open på forfatter "Moe, Signe"
-
Robustness and Stability of Long Short-Term Memory Recurrent Neural Networks
Peci, Edmond (Master thesis, 2021)Denne masteroppgaven har som mål å studere robusthet og stabilitet i lys av den populære rekurrente nevrale nettverkstypen 'lang kortidsminne' (long short-term memory) i møte med perturbert inngangsdata and pertubasjoner ... -
Set-based collision avoidance applications to robotic systems
Moe, Signe; Pettersen, Kristin Ytterstad; Gravdahl, Jan Tommy (Peer reviewed; Journal article, 2020)A robotic system can consist of a single or multiple agents with a fixed or mobile base, with full or under-actuation, and possibly redundancy. Collision avoidance is a crucial task for any robotic system and is necessary ... -
Set-Based Control for Autonomous Spray Painting
Moe, Signe; Gravdahl, Jan Tommy; Pettersen, Kristin Ytterstad (Journal article; Peer reviewed, 2018)In this paper, a method is presented for lowering the energy consumption and/or increasing the speed of a standard manipulator spray painting a surface. The approach is based on the observation that a small angle between ... -
Set-Based Line-of-Sight (LOS) Path Following with Collision Avoidance for Underactuated Unmanned Surface Vessel
Moe, Signe; Pettersen, Kristin Ytterstad (Journal article, 2016)A cornerstone ability of an autonomous unmanned surface vessel (USV) is to avoid collisions with stationary obstacles and other moving vehicles while following a predefined path. USVs are typically underactuated, and this ... -
Set-Based Line-of-Sight (LOS) Path Following with Collision Avoidance for Underactuated Unmanned Surface Vessels under the Influence of Ocean Currents
Moe, Signe; Pettersen, Kristin Ytterstad (Chapter, 2017)An essential ability of an autonomous unmanned surface vessel (USV) is to follow a predefined path in the presence of unknown ocean currents while avoiding collisions with both stationary and dynamic obstacles. This paper ... -
Set-based path following and obstacle avoidance for underwater snake robots
Kohl, Anna M; Moe, Signe; Kelasidi, Eleni; Pettersen, Kristin Ytterstad; Gravdahl, Jan Tommy (Chapter, 2017)This article presents a set-based guidance strategy for path following with obstacle avoidance for underwater snake robots conducting planar sinusoidal motion. The guidance scheme is designed such that the robot follows a ... -
Set-based Tasks within the Singularity-robust Multiple Task-priority Inverse Kinematics Framework: General Formulation, Stability Analysis and Experimental Results
Moe, Signe; Antonelli, Gianluca; Teel, Andrew R.; Pettersen, Kristin Ytterstad; Schrimpf, Johannes (Journal article; Peer reviewed, 2016)Inverse kinematics algorithms are commonly used in robotic systems to transform tasks to joint references, and several methods exist to ensure the achievement of several tasks simultaneously. The multiple task-priority ... -
Stability Analysis for Set-based Control within the Singularity-robust Multiple Task-priority Inverse Kinematics Framework
Moe, Signe; Teel, Andrew R.; Antonelli, Gianluca; Pettersen, Kristin Ytterstad (Chapter, 2015)Inverse kinematics algorithms are commonly used in robotic systems to accomplish desired behavior, and several methods exist to ensure the achievement of several tasks simultaneously. The multiple task-priority inverse ... -
Stable and robust neural network controllers
Sterud, Camilla; Moe, Signe; Gravdahl, Jan Tommy (Chapter, 2021)Neural networks are expressive function approimators that can be employed for state estimation in control problems. However, control systems with machine learning in the loop often lack stability proofs and performance ... -
Wire-arc additive manufacturing of structures with overhang: Experimental results depositing material onto fixed substrate
Evjemo, Linn Danielsen; Langelandsvik, Geir; Moe, Signe; Danielsen, Morten Høgseth; Gravdahl, Jan Tommy (Peer reviewed; Journal article, 2022)As additive manufacturing (AM) technology grows both more advanced and more available, the challenges and limitations are also made more evident. Most existing solutions for AM build structures layer by layer using strictly ...