Ändra sökning
Avgränsa sökresultatet
1 - 31 av 31
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Almudhari, Haider
    Luleå tekniska universitet, Institutionen för ekonomi, teknik och samhälle.
    Effektivisering av materialhantering gällande plåtrullar i SSAB:s Stålhamn: En fallstudie på Oxelösunds Hamn AB2018Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Idag befinner sig produktionsföretag under konkurrenskraftiga och snabba förändringar i en global marknad. Det utmanar företag som jobbar med materialtillverkning och distributionsnät på en global nivå till att ständigt förbättra deras verksamhet. Aktörerna som verkar inom en och samma supply chain bör enas för att kunna bli konkurrenskraftiga och flexibla, som respons på globaliseringen. Genom att företag skapar gemensamma mål, delar information, risker och vinster kan alla aktörer inom kedjan gynnas.

    Denna fallstudie har genomförts på en av Oxelösunds Hamns verksamheter, nämligen SSAB:s Stålhamn, som de driver åt SSAB i Oxelösund kommun. Stålhamnen har en viktig roll i SSAB:s supply chain eftersom den agerar som SSAB:s skeppningshamn där material som kommer från SSAB i Borlänge och Oxelösund lagras tills de ska skeppas vidare till andra hamnar i världen. Idag upplever Oxelösunds Hamn ineffektiv information- och materialflöde inom Stålhamnens verksamhet.

    Syftet med studien är att undersöka materialhantering i form av vilka transport- och lagringsmetoder som sker inne i en av Stålhamnens verksamheter, Coilsterminalen. Därefter klargörs vilka slöserier som finns samt hitta förbättringar för att effektivisera information- och materialflödet vid hanteringar av plåtrullar i Coilsterminalen.

    Studien har primärt genomförts genom observationer, ostrukturerade och några strukturerade intervjuer samt strukturerade mejlkonversationer och insamling av data. Fokuset låg på att hitta de möjliga effektiviseringsområden i praktiken för att sedan hitta teori och litteratur som belyser de upphittade bristerna. Några teorier som kommer att betonas på grund av deras relevans är Lean, lager- och supply chain teori.

    Studiens resultat och analys visar att utmaningarna som hindrar effektivisering i Coilsterminalen är baserad på interna och externa faktorer. Interna faktorer består av onödig förflyttning av material, omarbetning i kontor och outnyttjat arbetsskift. Externa faktorer orsakas på grund av leverantörer i form av osäkerhet av informationsinput samt material input/output.

    Studien resulterar i att den optimala lösningen är att samarbetet mellan aktörerna i kedjan förbättras så att flöde av information blir bättre och förminska osäkerheten i leverans och utleverans. Vidare uppmuntrar studien Oxelösund Hamn att samla in data, i form av statistik, om dagliga händelser i Stålhamnen så att de belyser problem och kostnader som är dolda. Oxelösund Hamn uppmuntras också införa det outnyttjade arbetsskiftet under natten och förminskning av lagret.

  • 2.
    Andrikopoulos, George
    et al.
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Nikolakopoulos, George
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    HUmanoid Robotic Leg via pneumatic muscle actuators: implementation and control2018Ingår i: Meccanica (Milano. Print), ISSN 0025-6455, E-ISSN 1572-9648, Vol. 53, nr 1-2, s. 465-480Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In this article, a HUmanoid Robotic Leg (HURL) via the utilization of pneumatic muscle actuators (PMAs) is presented. PMAs are a pneumatic form of actuation possessing crucial attributes for the implementation of a design that mimics the motion characteristics of a human ankle. HURL acts as a feasibility study in the conceptual goal of developing a 10 degree-of-freedom (DoF) lower-limb humanoid for compliance and postural control, while serving as a knowledge basis for its future alternative use in prosthetic robotics. HURL’s design properties are described in detail, while its 2-DoF motion capabilities (dorsiflexion–plantar flexion, eversion–inversion) are experimentally evaluated via an advanced nonlinear PID-based control algorithm.

  • 3.
    Andrikopoulos, Georgios
    et al.
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Nikolakopoulos, George
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Vortex Actuation via Electric Ducted Fans: an Experimental Study2019Ingår i: Journal of Intelligent and Robotic Systems, ISSN 0921-0296, E-ISSN 1573-0409, Vol. 95, nr 3-4, s. 955-973Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The presented work investigates the potential of utilizing commercially available Electric Ducted Fans (EDFs) as adhesion actuators, while providing a novel insight on the analysis of the adhesion nature related to negative pressure and thrust force generation against a target surface. To this goal, a novel EDF-based Vortex Actuation Setup (VAS) is proposed for monitoring important properties such as adhesion force, pressure distribution, current draw, motor temperature etc. during the VAS’ operation when placed in variable distances from a test surface. In addition, this work is contributing towards the novel evaluation of different design variables and modifications to original EDF structures, with the goal of analyzing their effect on the prototype VAS, while optimizing its adhesion efficiency for its future incorporation in a wall-climbing robot for inspection and repair purposes.

  • 4.
    Barf, Jochen
    Luleå tekniska universitet, Institutionen för system- och rymdteknik.
    Development and Implementation of an Image-Processing-Based Horizon Sensor for Sounding Rockets2017Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
  • 5.
    Björnström, Albert
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Flödeskalibrering: Analys av kalibreringsprocesser2018Självständigt arbete på grundnivå (högskoleexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    I december 2015 undertecknades Parisavtalet i syfte att skapa ett bättre globalt klimat. Enligt avtalet ska alla länders utsläpp redovisas till FN. En förutsättning för att Sverige ska kunna redovisa utsläppen är att nuvarande utsläppsnivåer är kända, varför mätning och beräkning av utsläpp är nödvändig.

     

    Det statligt ägda gruvbolaget Luossavaara Kiirunavaara AB (LKAB) driver järnmalmsgruvor i Malmfälten. Den järnmalmspellets som tillverkas vid kulsinterverket KK4 i Kiruna består till viss del av tillsatsmedel, som vid förbränning bildar koldioxid. Hur mycket tillsatsmedel som förbränns mäts med hjälp av två flödesmätare. För att säkerställa att dessa mätare har godkänd noggrannhet utförs årliga kalibreringar där uppmätt volym jämförs med en referensvolym. I syfte att säkerställa att LKAB:s kalibreringsmetod fungerar har ett externt företag utfört kalibrering med en annan metod där mätsensorer placeras på tillsatsmedelledningen. Resultaten mellan de två kalibreringsmetoderna skiljer sig avsevärt, vilket föranlett denna rapport.

     

    Syftet med arbetet är att ta fram förbättringsåtgärder för LKAB:s kalibreringsmetod samt presentera förslag på hur LKAB kan skapa bättre förutsättningar för den andra så kallade pulshastighetsmetoden. Genom att analysera respektive kalibreringsmetod och utföra mätningar, tester och beräkningar tas svagheter fram. Tester visar att en svaghet med LKAB:s kalibrering är att den nivåmätningsmetod som används är personberoende. Nivåmätning med laseravståndsmätare testas med gott resultat varför denna typ av mätning rekommenderas framöver.

     

    En svaghet med pulshastigheten är att den är känslig för variation av rörens innerdiameter. För att denna metod ska ge tillförlitliga resultat krävs ombyggnation av ledningar samt noga uppmätt innerdiameter.

     

    Noggrann flödesmätning leder till att nuvarande koldioxidutsläpp kan beräknas vilket skapar förutsättningar för fortsatt arbete mot uppställda miljömål. Flödesmätarna har även en betydande roll för produktkvaliteten i KK4 vilket innebär att denna rapport kan bidra till högre kvalitet och ekonomisk lönsamhet.

  • 6.
    Eleftheroglou, Nick
    et al.
    Faculty of Aerospace Engineering, TU Delft, the Netherlands.
    Mansouri, Sina Sharif
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Loutas, Theodoros
    Department of Mechanical Engineering & Aeronautics, University of Patras, Greece.
    Karvelis, Petros
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Georgoulas, George
    Department of Mechanical Engineering & Aeronautics, University of Patras, Greece.
    Nikolakopoulos, George
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Zarouchas, Dimitrios
    Faculty of Aerospace Engineering, TU Delft, the Netherlands.
    Intelligent data-driven prognostic methodologies for the real-time remaining useful life until the end-of-discharge estimation of the Lithium-Polymer batteries of unmanned aerial vehicles with uncertainty quantification2019Ingår i: Applied Energy, ISSN 0306-2619, E-ISSN 1872-9118, Vol. 254, artikel-id 113677Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In this paper, the discharge voltage is utilized as a critical indicator towards the probabilistic estimation of the Remaining Useful Life until the End-of-Discharge of the Lithium-Polymer batteries of unmanned aerial vehicles. Several discharge voltage histories obtained during actual flights constitute the in-house developed training dataset. Three data-driven prognostic methodologies are presented based on state-of-the-art as well as innovative mathematical models i.e. Gradient Boosted Trees, Bayesian Neural Networks and Non-Homogeneous Hidden Semi Markov Models. The training and testing process of all models is described in detail. Remaining Useful Life prognostics in unseen data are obtained from all three methodologies. Beyond the mean estimates, the uncertainty associated with the point predictions is quantified and upper/lower confidence bounds are also provided. The Remaining Useful Life prognostics during six random flights starting from fully charged batteries are presented, discussed and the pros and cons of each methodology are highlighted. Several special metrics are utilized to assess the performance of the prognostic algorithms and conclusions are drawn regarding their prognostic capabilities and potential.

  • 7.
    Fredmer, Andreas
    Luleå tekniska universitet, Institutionen för teknikvetenskap och matematik.
    Application and Control of Robotic Manipulator through PLC2017Självständigt arbete på grundnivå (yrkesexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [en]

    This thesis analyses the background of the kinematics and control of an articulated robotic arm in order to control it’s motor controllers with a custom controller using PLC programming.

    The goal was to create a MATLAB simulation of a manipulator and then establish a working configuration. This would then later be used by the division of Signals and Systems at LTU to educate students in PLC programming for autonomous setups with the robotic manipulator.

    The thesis was successful following the schedule established at the beginning and most of the objectives were accomplished. The results were a functioning control framework of Siemens PLC that could control the manipulators motor controllers to preform pickand place tasks in conjunction with a conveyor belt.

  • 8.
    Gómez Rosal, Dulce Adriana
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Datavetenskap. Aalto University.
    Transfer of reinforcement learning for a robotic skill2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    In this work, we develop the transfer learning (TL) of reinforcement learning (RL) for the robotic skill of throwing a ball into a basket, from a computer simulated environment to a real-world implementation. Whereas learning of the same skill has been previously explored by using a Programming by Demonstration approach directly on the real-world robot, for our work, the model-based RL algorithm PILCO was employed as an alternative as it provides the robot with no previous knowledge or hints, i.e. the robot begins learning from a tabula rasa state, PILCO learns directly on the simulated environment, and as part of its procedure, PILCO models the dynamics of the inflatable, plastic ball used to perform the task. The robotic skill is represented as a Markov Decision Process, the robotic arm is a Kuka LWR4+, RL is enabled by PILCO, and TL is achieved through policy adjustments. Two learned policies were transferred, and although the results show that no exhaustive policy adjustments are required, large gaps remain between the simulated and the real environment in terms of the ball and robot dynamics. The contributions of this thesis include: a novel TL of RL framework for teaching the basketball skill to the Kuka robotic arm; the development of a pythonised version of PILCO; robust and extendable ROS packages for policy learning and adjustment in a simulated or real robot; a tracking-vision package with a Kinect camera; and an Orocos package for a position controller in the robotic arm.

  • 9.
    Heung, Tsz Hin
    Luleå tekniska universitet, Institutionen för system- och rymdteknik. Aalto University.
    Visual space navigation system for CubeSat using deep convolutional neural networks2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
  • 10.
    Hladký, Maroš
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Rymdteknik. Julius-Maximilians-University Würzburg, Informatics VII : Robotics and Telematics .
    Vision Based Attitude Control2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    The problematics of precise pointing and more specifically an attitude control is present sincethe first days of flight and Aerospace engineering. The precise attitude control is a matter ofnecessity for a great variety of applications. In the air, planes or unmanned aerial vehicles needto be able to orient precisely. In Space, a telescope or a satellite relies on the attitude control toreach the stars or survey the Earth. The attitude control can be based on various principles, pre-calculated variables, and measurements. It is common to use the gyroscope, Sun/Star/horizonsensors for attitude determination. While those technologies are well established in the indus-try, the rise in a computational power and efficiency in recent years enabled processing of aninfinitely more rich source of information - the vision. In this Thesis, a visual system is used forthe attitude determination and is blended together with a control algorithm to form a VisionBased Attitude Control system.A demonstrator is designed, build and programmed for the purpose of Vision Based AttitudeControl. It is based on the principle of Visual servoing, a method that links image measure-ments to the attitude control, in a form of a set of joint velocities. The intermittent steps arethe image acquisition and processing, feature detection, feature tracking and the computationof joint velocities in a closed loop control scheme. The system is then evaluated in a barrage ofpartial experiments.The results show, that the used detection algorithms, Shi&Tomasi and Harris, performequally well in feature detection and are able to provide a high amount of features for tracking.The pyramidal implementation of the Lucas&Kanade tracking algorithm proves to be a capablemethod for a reliable feature tracking, invariant to rotation and scale change. To further evaluatethe Visual servoing a complete demonstrator is tested. The demonstrator shows the capabilityof Visual Servoing for the purpose of Vision Based Attitude Control. An improvement in thehardware and implementation is recommended and planned to push the system beyond thedemonstrator stage into an applicable system.

  • 11.
    Jafari, Hedyeh
    et al.
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Nikolakopoulos, George
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Gustafsson, Thomas
    Replicating human brain mechanisms towards balancing2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    Understanding the performance of the human brain to stabilize the body remains an open fundamental research question. In this article, we study the hypothesis of internal model of the Central Nervous System (CNS) by a novel proposed architecture based on a recurrent neural network. The overall objective of the article and the main contribution stems from demonstrating the capability of replicating the balancing mechanisms of the brain by training the proposed bio-inspired network architecture with human balancing data and in the sequel applying the resulting control structure for controlling a single link inverted pendulum. Towards this direction, the body kinetics and kinematics measurements of forty-five subjects during upright stance trails were collected and utilized for training the proposed neural network. The efficacy of the proposed scheme will be proven through multiple simulation results with a single link inverted pendulum, where it will be demonstrated that the brain-inspired control scheme achieves a proper balance.

  • 12.
    Jerker, Bergström
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Rymdteknik.
    Path Planning with Weighted Wall Regions using OctoMap2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    In the work of the Control Engineering research group of the Department of Computer Science, Electrical and Space Engineering, Signals and systems at Luleå University of Technology a need had arisen for a path planning algorithm. The ongoing research with Unmanned Aerial Vehicles(UAVs) had so far been done with any complicated paths being created manually with waypoints set by the uses. To remove this labourious part of the experimental process a path should be generated automatically by simply providing a program with the position of the UAV, the goal to which the user wants it to move, as well as information about the UAV's surroundings in the form of a 3D map.In addition to simply finding an available path through a  3D environment the path should also be adapted to the risks that the physical environment poses to a flying robot. This was achieved by adapting a previously developed algorithm, which did the simple path planning task well, by adding a penalty weight to areas near obstacles, pushing the generated path away from them.The planner was developed working with the OctoMap map system which represents the physical world by segmenting it into cubes of either open or occupied space. The open segments of these maps could then be used as vertices of a graph that the planning algorithm could traverse.The algorithm itself was written in C++ as a node of the Robot Operating System(ROS) software framework to allow it to smoothly interact with previously developed software used by the Control Engineering Robotics Group.The program was tested by simulations where the path planner ROS node was sent maps as well as UAV position and intended goal. These simulations provided valid paths, with the performance of the algorithm as well as the quality of the paths being evaluated for varying configurations of the planners parameters.The planner works well in simulation and is deemed ready for use in practical experiments.

  • 13.
    Kanellakis, Christoforos
    et al.
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Mansouri, Sina Sharif
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Fresk, Emil
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Kominiak, Dariusz
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Nikolakopoulos, George
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Cooperative UAVs as a Tool for Aerial Inspection of Large Scale Aging Infrastructure2018Ingår i: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Piscataway, NJ: IEEE, 2018, s. 5040-5040Konferensbidrag (Refereegranskat)
    Abstract [en]

    This work presents an aerial tool towards the autonomous cooperative coverage and inspection of a large scale 3D infrastructure using multiple Unmanned Aerial Vehicles (UAVs). In the presented approach the UAVs are relying only on their onboard computer and sensory system, deployed for inspection of the 3D structure. In this application each agent covers a different part of the scene autonomously, while avoiding collisions. The autonomous navigation of each platform on the designed path is enabled by the localization system that fuses Ultra Wideband with inertial measurements through an Error- State Kalman Filter. The visual information collected from the aerial team is collaboratively processed to create the 3D model. The performance of the overall setup has been experimentally evaluated in realistic wind turbine inspection experiments, providing dense 3D reconstruction of the inspected structures.

  • 14.
    Koval, Anton
    et al.
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Mansouri, Sina Sharif
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Nikolakopoulos, George
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Online Multi-Agent Based Cooperative Exploration and Coverage in Complex Environment2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this article, an online collaborative exploration and coverage method is proposed for the unknown complex environment with multiple agents. The exploration and coverage is based on Boustrophedon motion, while the detection conditions for backtracking points have been modified based on mission requirements, the battery charge level of each agent is considered to reduce agent loss, and collision free paths are generated. The proposed method is evaluated in simulation, where complex environment with multiple branches is explored by multiple agents.

  • 15.
    Leblebici, Robin
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Rymdteknik.
    Development of an automated adjusting process for robotic end-effectors to handle dry textiles for preforming of carbon fiber reinforced plastics2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    In order to fulfill increasing production rates, new automated production technologies are required for manufacturing carbon fiber reinforced plastic components for the aerospace industry. Currently, large, double curved composite components have to be manufactured manually, which leads to high process times and poor scalability. As a consequence, a team of cooperating robots with passively adjustable end-effectors was developed, that is capable of handling dry carbon textiles and can be used for layups in double curved molds. This thesis deals with the implementation of a robot program, that performs an automated adjustment of each end-effector to the surface geometry of the manufactured part. The functional principle and the accuracy of the process are evaluated. Further, the automatically adjusted end-effectors are utilized to cooperatively layup carbon plies. The results show, that the accuracy of the automated adjusting process is sufficient to drape carbon fabrics during pick-up and automated layup is possible with this approach. In conclusion, the developed process can be integrated into a fully automated process for future experiments, but hardware inaccuracies should be improved, in order to further enhance the accuracy of the system.

  • 16.
    Lindqvist, Björn
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Rymdteknik.
    Combined Control and Path Planning for a Micro Aerial Vehicle based on Non-linear MPC with Parametric Geometric Constraints2019Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Using robots to navigate through un-mapped environments, specially man-made infrastructures, for the purpose of exploration or inspection is a topic that has gathered a lot of interest in the last years. Micro Aerial Vehicles (MAV's) have the mobility and agility to move quickly and access hard-to-reach areas where ground robots would fail, but using MAV's for that purpose comes with its own set of problems since any collision with the environment results in a crash. The control architecture used in a MAV for such a task needs to perform obstacle avoidance and on-line path-planning in an unknown environment with low computation times as to not lose stability. In this thesis a Non-linear Model Predictive Controller (NMPC) for obstacle avoidance and path-planning on an aerial platform will be established. Included are methods for constraining the available state-space, simulations of various obstacle avoidance scenarios for single and multiple MAVs and experimental validation of the proposed control architecture. The validity of the proposed approach is demonstrated through multiple experimental and simulation results. In these approaches, the positioning information of the obstacles and the MAV are provided by a motion-capture system. The thesis will conclude with the demonstration of an experimental validation of a centralized NMPC for collision avoidance of two MAV's.

  • 17. Lundell, Jens
    Dynamic movement primitives andreinforcement learning for adapting alearned skill2016Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Traditionellt sett har robotar blivit förprogrammerade för att utföra specifika uppgifter.Detta tillvägagångssätt fungerar bra i industriella miljöer var robotar måsteutföra mycket noggranna rörelser, som att svetsa. Förprogrammering av robotar ärdock dyrt, felbenäget och tidskrävande eftersom varje aspekt av uppgiften måstebeaktas. Dessa nackdelar kan till och med göra det omöjligt att förprogrammeraen robot att utföra komplexa uppgifter som att spela bollen-i-koppen spelet. Medallt detta i åtanke undersöker den här avhandlingen möjligheten att kombinera ettmodernt ramverktyg, kallat inläraning av demonstrationer, för att lära en robothur bollen-i-koppen-spelet ska spelas genom att demonstrera uppgiften för denoch sedan ha roboten att själv förbättra sin inlärda uppgift genom att användaförstärkande inlärning. Uppgiften som roboten måste lära sig är demonstreradmed kinestetisk undervisning, modellerad som dynamiska rörelseprimitiver, ochsenare förbättrad med den förstärkande inlärningsalgoritmen Policy Learning byWeighted Exploration with the Returns. Experiment utförda på den industriellaKUKA LWR4+ roboten visade att robotar är kapabla att framgångsrikt lära sigspela bollen-i-koppen spelet

  • 18.
    Mansouri, Sina Sharif
    et al.
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Kanellakis, Christoforos
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Fresk, Emil
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Kominiak, Dariusz
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Nikolakopoulos, George
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Cooperative UAVs as a tool for Aerial Inspection of the Aging Infrastructure2017Ingår i: Field and Service Robotics: Results of the 11th International Conference / [ed] Marco Hutter, Roland Siegwart, Cham: Springer, 2017, s. 177-189Konferensbidrag (Refereegranskat)
    Abstract [en]

    This article presents an aerial tool towards the autonomous cooperative coverage and inspection of a 3D infrastructure using multiple Unmanned Aerial Vehicles (UAVs). In the presented approach the UAVs are relying only on their onboard computer and sensory system, deployed for inspection of the 3D structure. In this application each agent covers a different part of the scene autonomously, while avoiding collisions. The visual information collected from the aerial team is collaboratively processed to create the 3D model. The performance of the overall setup has been experimentally evaluated in a realistic outdoor infrastructure inspection experiments, providing sparse and dense 3D reconstruction of the inspected structures.

  • 19.
    Mansouri, Sina Sharif
    et al.
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Karvelis, Petros
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Kanellakis, Christoforos
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Kominiak, Dariusz
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Nikolakopoulos, George
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.
    Vision-based MAV Navigation in Underground Mine Using Convolutional Neural Network2019Konferensbidrag (Refereegranskat)
    Abstract [en]

    This article presents a Convolutional Neural Network (CNN) method to enable autonomous navigation of low-cost Micro Aerial Vehicle (MAV) platforms along dark underground mine environments. The proposed CNN component provides on-line heading rate commands for the MAV by utilising the image stream from the on-board camera, thus allowing the platform to follow a collision-free path along the tunnel axis. A novel part of the developed method consists of the generation of the data-set used for training the CNN. More specifically, inspired from single image haze removal algorithms, various image data-sets collected from real tunnel environments have been processed offline to provide an estimation of the depth information of the scene, where ground truth is not available. The calculated depth map is used to extract the open space in the tunnel, expressed through the area centroid and is finally provided in the training of the CNN. The method considers the MAV as a floating object, thus accurate pose estimation is not required. Finally, the capability of the proposed method has been successfully experimentally evaluated in field trials in an underground mine in Sweden.

  • 20.
    Nesterud, Klara
    et al.
    Luleå tekniska universitet, Institutionen för system- och rymdteknik.
    Vålvik, Agnes
    Luleå tekniska universitet, Institutionen för system- och rymdteknik.
    Utmaningar och rekommendationer vid utvecklandet av robotstyrdprocessautomation inom en verksamhetsprocess2019Självständigt arbete på grundnivå (kandidatexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [sv]

    Företag strävar idag alltmer efter att automatisera och effektivisera sina verksamhetsprocesser. Till följd av den digitala transformationen av vårt samhälle skapas ständigt nya möjligheter och tekniska innovationer för att stödja automatiseringen av processer genom att göra saker på helt nytt sätt genom att använda sig av modern informations- och datorteknik. Denna studie undersöker en ny teknisk innovation i form av mjukvarutekniken RPA (robotstyrd processautomation) samt dess förmåga att automatisera arbetsuppgifter som vanligtvis utförs manuellt. Studien syftar till att belysa de utmaningar som riskerar att uppstå samt vad som bör beaktas vid utvecklandet av RPA inom en verksamhetsprocess vilket redovisas i form av rekommendationer. Studiens metod utgår från ett explorativt angreppssätt, en kvalitativ datainsamling samt har en abduktiv ansats då ett fenomen både undersöks och analyseras med hjälp av teori relaterat till RPA och automatiserandet av verksamhetsprocesser. De utmaningar och rekommendationer som tagits fram baseras på resultat från mötestillfällen i form av semistrukturerade workshops baserade på utvecklingsprocessens fyra steg samt på utvecklingsgruppens egna upplevelser kombinerat med den teori som använts som underlag för analys. Studiens viktigaste resultat är att processen noga bör kartläggas och optimeras innan utvecklandet inleds samt att en ständig uppföljning med slutanvändaren genomförs i syfte för att upptäcka eventuella förändringar av krav. Någon inom utvecklingsgruppen bör, utöver ett tekniskt perspektiv, även inneha ett processperspektiv samt grundläggande kunskap kring utvecklingen av en verksamhet.

  • 21.
    Papadimitriou, Andreas
    Luleå tekniska universitet, Institutionen för samhällsbyggnad och naturresurser, Drift, underhåll och akustik.
    Modeling, Identification and Control of a Wall Climbing Robot Based on Vortex Actuation2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
  • 22.
    Pomyen, Siriphat
    Luleå tekniska universitet, Institutionen för system- och rymdteknik.
    Indoor path planning and navigation of quadrotors via Ultra-WidebandWireless Technology2019Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    The interest in Unmanned Ariel Vehicles (UAVs) has been rising recently due to advances in technology such as battery capacity and miniaturization of microcontrollers.In addition, the reduction of the production cost of the quadrotors made them moreaccessible for various applications. Quadrotors find applications in military, agriculture, entertainment and surveillance. Most UAVs use GPS for navigation, limitingthe use of quadrotors to outdoors. In order to use the quadrotors indoors, an indoorpositioning system needs to be developed. Indoor localization can be developed usingnovel navigation algorithms along with the use of ranging sensors, cameras and radiowaves in addition to the sensors that are usually onboard. The development of anindoor navigation system allows the use of quadrotors in environments where GPS is unavailable, such as in factories or in underground areas. The aim of this thesis isto integrate a positioning system using Pozyx UWB wireless technology onto DJIMatrice 100 quadrotors in order to perform the indoor navigation and path planning.

  • 23.
    Ramavaram, Harish Rao
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Rymdteknik.
    Software and Control Design for 2-D Floating Satellite Simulator2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
  • 24.
    Rådman, Marcus
    Luleå tekniska universitet, Institutionen för system- och rymdteknik.
    Implementation and testing of a path tracker for a full-scale Unmanned Ground Vehicle2019Självständigt arbete på avancerad nivå (yrkesexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    This project is the implementation and testing of a path tracker for a car-sized Unmanned Ground Vehicle. The vehicle, a Toyota Land Cruiser, was provided by SSC and hadpreviously been modified for remote operation. The developed path tracker uses a "follow the carrot" algorithm and has been writtenin C using the Robot Operating Software (ROS) framework and has been integrated intothe vehicles existing ROS powered software. During the implementation, the Gazebo rigid body simulator was used to simulate a simplified vehicle. Integration with the real sensors was performed using a small-scalecar, both indoors with the aid of a Vicon motion capture system and outdoors utilizingonly sensors available to the full-size car. The small-scale tests showed promise, howeverwhen full-scale field tests were performed the results showed some problems and reasonsfor these are discussed.

  • 25.
    Sherly, Christina
    Luleå tekniska universitet, Institutionen för system- och rymdteknik. Aalto university.
    Visual Grasping of Unknown Objects2016Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    The objective of the thesis is to compare and study recent visual grasping techniques which areapplied on a robotic arm for grasping of unknown objects in an indoor environment.The novelty of the thesis is that the study has led to questioning the general approach used byresearchers to solve the grasping problem. The result can help future researchers in investing more onthe problem areas of grasping techniques and can also lead us to question ourselves on the approachwe are using to solve the grasping problem.

  • 26.
    Struckmeier, Oliver
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Rymdteknik. Aalto University.
    Generating Explanations of Robot Policies in Continuous State Spaces2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Transparency in HRI describes the method of making the current state of a robotor intelligent agent understandable to a human user. Applying transparencymechanisms to robots improves the quality of interaction as well as the userexperience. Explanations are an effective way to make a robot’s decision making transparent. We introduce a framework that uses natural language labels attached to a region inthe continuous state space of the robot to automatically generate local explanationsof a robot’s policy. We conducted a pilot study and investigated how the generated explanations helpedusers to understand and reproduce a robot policy in a debugging scenario.

  • 27.
    Tariq, Usama
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Rymdteknik.
    Robotic Grasping of Large Objects for Collaborative Manipulation2017Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    In near future, robots are envisioned to work alongside humans in professional anddomestic environments without significant restructuring of workspace. Roboticsystems in such setups must be adept at observation, analysis and rational de-cision making. To coexist in an environment, humans and robots will need tointeract and cooperate for multiple tasks. A fundamental such task is the manip-ulation of large objects in work environments which requires cooperation betweenmultiple manipulating agents for load sharing. Collaborative manipulation hasbeen studied in the literature with the focus on multi-agent planning and controlstrategies. However, for a collaborative manipulation task, grasp planning alsoplays a pivotal role in cooperation and task completion.In this work, a novel approach is proposed for collaborative grasping and manipu-lation of large unknown objects. The manipulation task was defined as a sequenceof poses and expected external wrench acting on the target object. In a two-agentmanipulation task, the proposed approach selects a grasp for the second agentafter observing the grasp location of the first agent. The solution is computed ina way that it minimizes the grasp wrenches by load sharing between both agents.To verify the proposed methodology, an online system for human-robot manipu-lation of unknown objects was developed. The system utilized depth informationfrom a fixed Kinect sensor for perception and decision making for a human-robotcollaborative lift-up. Experiments with multiple objects substantiated that theproposed method results in an optimal load sharing despite limited informationand partial observability.

  • 28.
    Terkovic, Richard
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Rymdteknik.
    Dynamic modelling of a landing gear2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Companies in the aerospace industry would benefit from a faster, more flexible wayto investigate physical system issues in the vehicles/aircraft during their lifetime.Current software and hardware provides us with the option of making a systemmodel to simulate investigated problems, saving money and time.This work focuses on a nose landing gear of the Airbus’ fighter jet - EurofighterTyphoon. The landing gear itself is a very complex system designed for highperformance rather than robust usage; it requires a lot of maintenance and testingduring its lifetime. A practical investigation tool is much needed.The primary objective of this work is developing of a simulation model for thenose landing gear in Matlab, Simulink using Simscape library. The model spreadsmainly across two domains: the hydraulic and the multibody domain.The resulting model can simulate extension and retraction behaviour of the realEurofighter nose landing gear under different in-flight conditions. Friction in thehydraulic actuator was derived from the model.Connecting the known parameters of the landing gear subsystems and adjustingthe model to mimic real system behaviour, it can be used to extract the derived parameters,which were previously unknown. The model solves the time-consuminginvestigations and is much more flexible than physical test benches. Finally, it canbe used for future development and planning by simple parameter adjustment.

  • 29.
    White, Jack
    Luleå tekniska universitet, Institutionen för system- och rymdteknik, Rymdteknik. Aalto University/Erasmus+.
    Guided policy search for a lightweight industrial robot arm2018Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    General autonomy is at the forefront of robotic research and practice. Earlier research has enabled robots to learn movement and manipulation within the context of a specific instance of a task and to learn from large quantities of empirical data and known dynamics. Reinforcement learning (RL) tackles generalisation, whereby a robot may be relied upon to perform its task with acceptable speed and fidelity in multiple---even arbitrary---task configurations. Recent research has advanced approximate policy search methods of RL, in which a function approximator is used to represent an optimal policy while avoiding calculation across the large dimensions of the state and action spaces of real robots. This thesis details the implementation and testing, on a lightweight industrial robot arm, of guided policy search (GPS), an RL algorithm that seeks to avoid the typical need, in machine learning, for lots of empirical behavioural samples, while maximising learning speed. GPS comprises a local optimal policy generator, here based on a linear-quadratic regulator, and an approximate general policy representation, here a feedforward neural network. A controller is written to interface an existing back-end implementation of GPS and the robot itself. Experimental results show that the GPS agent is able to perform basic reaching tasks across its configuration space with approximately 15 minutes of training, but that the local policies generated fail to be fully optimised within that timescale and that post-training operation suffers from oscillatory actions under perturbed initial joint positions. Further work is discussed and recommended for better training of GPS agents and making locally optimal policies more robust to disturbance while in operation.

  • 30.
    Zaenker, Tobias
    Luleå tekniska universitet, Institutionen för system- och rymdteknik. Aalto University, Department of Electrical Engineering and Automation.
    Hypermaps: Beyond occupancy grids2019Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Intelligent and autonomous robotic applications often require robots to have more information about their environment than provided by traditional occupancy maps. An example are semantic maps, which provide qualitative descriptions of the environment. While research in the area of semantic mapping has been performed, most robotic frameworks still offer only occupancy maps.

    In this thesis, a framework is developed to handle multi-layered 2D maps in ROS. The framework offers occupancy and semantic layers, but can be extended with new layer types in the future. Furthermore, an algorithm to automatically generate semantic maps from RGB-D images is presented.

    Software tests were performed to check if the framework fulfills all set requirements. It was shown that the requirements are accomplished. Furthermore, the semantic mapping algorithm was evaluated with different configurations in two test environments, a laboratory and a floor. While the object shapes of the generated semantic maps were not always accurate and some false detections occurred, most objects were successfully detected and placed on the semantic map. Possible ways to improve the accuracy of the mapping in the future are discussed.

  • 31.
    Zeltner, Felix
    Luleå tekniska universitet, Institutionen för system- och rymdteknik.
    Autonomous Terrain Classification Through Unsupervised Learning2016Självständigt arbete på avancerad nivå (masterexamen), 20 poäng / 30 hpStudentuppsats (Examensarbete)
    Abstract [en]

    A key component of autonomous outdoor navigation in unstructured environments is the classification of terrain. Recent development in the area of machine learning show promising results in the task of scene segmentation but are limited by the labels used during their supervised training.

    In this work, we present and evaluate a flexible strategy for terrain classification based on three components: A deep convolutional neural network trained on colour, depth and infrared data which provides feature vectors for image segmentation, a set of exchangeable segmentation engines that operate in this feature space and a novel, air pressure based actuator responsible for distinguishing rigid obstacles from those that only appear as such. Through the use of unsupervised learning we eliminate the need for labeled training data and allow our system to adapt to previously unseen terrain classes.

    We evaluate the performance of this classification scheme on a mobile robot platform in an environment containing vegetation and trees with a Kinect v2 sensor as low-cost depth camera. Our experiments show that the features generated by our neural network are currently not competitive with state of the art implementations and that our system is not yet ready for real world applications.

1 - 31 av 31
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf