Sigurd Aksnes Fjerdingen
SINTEF
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Sigurd Aksnes Fjerdingen.
intelligent robots and systems | 2009
Sigurd Aksnes Fjerdingen; Pål Liljebäck; Aksel Andreas Transeth
This paper presents a mechanism for navigating complex pipe structures, both horizontally and vertically. The mechanism consists of a series of identical modules interconnected by two degree of freedom active joints. A set of active wheels on each module provides propulsion. Horizontal motion is achieved through a train-like scheme, while vertical motion is achieved through spanning the pipe alternatingly with the modules. The design and the capability of horizontal and vertical motion is validated through experiments.
intelligent robots and systems | 2012
Øystein Skotheim; Morten Lind; Pål Ystgaard; Sigurd Aksnes Fjerdingen
We present a flexible system that can scan and localize workpieces in 3D for assembly and pick and place operations. The system contains a vision robot that acquires 3D point clouds by performing sweeps with a laser triangulation sensor. Because the sensor is mounted on a robot, we can choose a viewpoint and a scanner trajectory that is optimal for a given task. For example, we can sweep along a semicircular trajectory in order to recognize and grasp parts from a pallet. With the same vision robot, we can perform a sweep of the packaging container in order to recognize and manipulate elements of cardboard. The system also incorporates software that recognizes and localizes objects based on an acquired 3D point cloud and a CAD model of the object to search for. The core matching algorithm is based on oriented point pairs and a Hough-like voting scheme. The method has been improved with a robust clustering algorithm as well as methods for pose verification and pose refinement that significantly increase the accuracy and robustness of the system. As an application of the system, an industrial prototype workcell is presented. The task is to recognize, grasp and transfer parts of office chairs, such as seats, seat backs and armrests, from a pallet to a cardboard container. It demonstrates how the vision system is easily set up to recognize three different components by using CAD models. The prototype workcell further demonstrates how the pose estimation results can be fed directly to a separate handling robot in order to grasp a chair seat. A series of ten experiments was performed where the chair seat was placed in arbitrary poses in the pallet. Pose estimations were performed in just over one second per experiment, and the obtained accuracy was well within the tolerances for the grasp operation in all ten cases.
Applied Ergonomics | 2016
Marialena Vagia; Aksel Andreas Transeth; Sigurd Aksnes Fjerdingen
In this paper we present a literature review of the evolution of the levels of autonomy from the end of the 1950s up until now. The motivation of this study was primarily to gather and to compare the literature that exists, on taxonomies on levels of automation. Technical developments within both computer hardware and software have made it possible to introduce autonomy into virtually all aspects of human-machine systems. The current study, is focusing on how different authors treat the problem of different levels of automation. The outcome of this study is to present the differences between the proposed levels of automation and the various taxonomies, giving the potential users a number of choices in order to decide which taxonomy satisfies their needs better. In addition, this paper surveys deals with the term adaptive automation, which seems to be a new trend in the literature on autonomy.
intelligent robots and systems | 2009
Boathymathava Murugendran; Aksel Andreas Transeth; Sigurd Aksnes Fjerdingen
Snake robots with active wheels provide interesting opportunities within many areas such as inspection and maintenance and search and rescue operations. The highly-articulated body of a snake robot combined with the advantages of wheeled locomotion makes it ideal for locomotion in, for example, pipes and other narrow or constricted structures. In this paper we present a mathematical model of the dynamics of a snake robot with active wheels together with a novel path-following approach for such robots. The path-following approach includes both how to find a desired turning angle for the snake robot head given a reference path, together with a module coordination strategy based on a n-trailer kinematic model. The path-following approach is tested and verified by simulations with the dynamic model. In addition, simulations suggest that the proposed approach results in reduced commanded joint and wheels shaft torques and, in most cases, a reduced path-following error compared to an implementation of a follow-the-leader algorithm.
EUROS | 2008
Sigurd Aksnes Fjerdingen; J. R. Mathiassen; Henrik Schumann-Olsen; Erik Kyrkjebø
A benchmarking facility for snake robot locomotion is presented, including the design of a snake-like robot extended with a sensor setup combining three-dimensional vision and an array of force sensors to register friction and impulse forces. A surrounding, modular environment consisting of a reconfigurable obstacle course and a ceiling mounted camera system is also presented. This enables research into adaptive obstacle-based and non-obstacle-based movement patterns for robotic snakes. Experimental results show possibilities for detailed data analysis of snake robot locomotion. Thus, the facility may be a common reference on which to experiment and evaluate future ideas.
oceans conference | 2015
Esten Ingar Grøtli; Marialena Vagia; Sigurd Aksnes Fjerdingen; Magnus Bjerkeng; Aksel Andreas Transeth; Eirik Svendsen; Per Rundtop
Increased use of autonomy is considered crucial for continued growth in maritime industries like oil- and gas, waterborne transport, and fisheries- and aquaculture. This article presents a method called Autonomous Job Analysis (AJA), which purpose is to guide the design of autonomous marine operations. AJA breaks down the operation, and focuses on autonomy early in the design phase. The method uses elements from Hierarchical Task Analysis (HTA), and the execution of the analysis is influenced by HAZard and OPerability (HAZOP) studies. The proposed method is illustrated through application on two different case studies: Inspection of mooring lines in a sea-based fish-farm, and imaging of plume extension caused by discharge from a waste water plant.
IFAC Proceedings Volumes | 2012
Sigurd Aksnes Fjerdingen; Magnus Bjerkeng; Aksel Andreas Transeth; Erik Kyrkjebø; Anders Røyrøy
Abstract Robot manipulators may be used as flexible camera platforms by mounting cameras on the wrist of the robot. In this paper we present a new way of interaction between an operator and the camera platform, where the operator wants to get a visual overview of a remote operation. The goal is to relieve the operator from controlling both the operation and the camera platform simultaneously, and allow the operator to focus only on the operation while the camera plaform is automatically controlled based on learned operator preferences. We describe an architecture for learning from operator inputs, and use an active camera control algorithm as a base for learning. An M-RAN sequential function approximator is used as memory function. Experimental results on a demonstration case indicate that the camera platform responds to and remembers differences in operator preference.
international workshop on robot motion and control | 2013
Serge Gale; Siri Vestheim; Jan Tommy Gravdahl; Sigurd Aksnes Fjerdingen; Ingrid Schjølberg
This paper presents two simple and efficient methods for pruning a Radial Basis Network (RBF) used in an adaptive controller architecture for a robotic manipulator. The methods presented in this paper are Weight Magnitude Pruning (WMP) and Node Output Pruning (NOP). The above pruning methods are simulated on a trajectory tracking task of a three degree of freedom robotic manipulator arm. The RBF based inverse dynamics controller is presented with a task of learning the inverse dynamics of the plant in a closed loop control. Simulation study shows that implementation of an inverse dynamics control law in such manner makes the controller more robust towards uncertainties and disturbances. Pruning RBF network improves controller performance in the case of modelling errors and reduces computational costs, thus making such controller more suitable for implementation.
international conference on mechatronics | 2013
Aksel Andreas Transeth; Sigurd Aksnes Fjerdingen; Pål Liljebäck
Snake robots have the potential of similar traversability capabilities as biological snakes by utilizing terrain irregularities for efficient propulsion, i.e. obstacle-aided locomotion (OAL). In order to realistically model and understand this issue we present a mathematical model for wheel-less snake robot OAL on inclined planes. The model is based on the framework of convex analysis and non-smooth dynamics, which facilitates true stick-slip descriptions as well as efficient numerical integration of the normal contact forces involved with robot-obstacle and robot-ground contact. In addition to the model, we present a shape curve-based approach to OAL where new push-points for robot-obstacle contact are identified online and a corresponding robot shape curve is calculated. Simulation results show that shape-curves are suitable for OAL both on inclined and vertical planes.
international conference on intelligent robotics and applications | 2012
Sigurd M. Albrektsen; Sigurd Aksnes Fjerdingen
Online robot learning has been a goal for researchers for several decades. A problem arises when learning algorithms need to explore the environment as actions cannot easily be anticipated. Because of this, safety is a major issue when using learning algorithms. This paper presents a framework for safe robot learning by the use of region-classification and energy limitation. The main task of the framework is to ensure safety regardless of a learning algorithms input to a system. This is necessary to allow a learning robot to explore environments without damaging itself or its surroundings. To ensure safety, the state-space is divided into fatal, supercritical, critical and safe regions, depending on the energy of the system. To show the adaptability of the framework it is used on two different systems; an actuated swinging pendulum and a mobile platform. In both cases obstacles with unknown locations must are avoided successfully.