The demand for collaborative, easy to use robots has increased during the last decades in hope of incorporating the use of robotics in smaller production scales, with easier and faster programming. Artificial intelligence (AI) and Machine learning (ML) are showing promising potential in robotics and this project has attempted to automatically solve a specific assembly task with Behavior trees (BTs). BTs can be used to elegantly divide a problem into different subtasks, while being modular and easy to modify. The main focus is put towards developing a Genetic algorithm (GA), that uses the fundamentals of biological evolution to produce BTs that solves the problem at hand. As a comparison to the GA result, a so-called Automated planner was developed to solve the problem and produce a benchmark BT. With a realistic physics simulation, this project automatically generated BTs that builds a tower of Duplo-like bricks and achieved successful results. The results produced by the GA showed a variety of possible solutions, a portion resembling the automated planner's results but also alternative, perhaps more elegant, solutions. As a conclusion, the approach used in this project shows promising signs and has many possible improvements for future research.

In the last decades research and development in the field of robotics has grown rapidly. This growth has resulted in the emergence of service robots that need to be able to physically interact with humans for different applications. One of these applications involves robots and humans cooperating in handling an object together. In such cases, there is usually an initial arrangement of how the robot and the humans hold the object and the arrangement stays the same throughout the manipulation task. Real-world scenarios often require that the initial arrangement changes throughout the task, therefore, it is important that the robot is able to recognize these changes and act accordingly. We consider a setting where a robot holds a large flat object with one or two humans. The aim of this research project is to detect the change in the number of agents grasping the object using only force and torque information measured at the robot's wrist. The proposed solution involves defining a transition sequence of four steps that the humans should perform to go from the initial scenario to the final one. The force and torque information is used to estimate the grasping point of the agents with a Kalman filter. While the humans are going from one scenario to the other, the estimated point changes according to the step of the transition the humans are in. These changes are used to track the steps in the sequence using a hidden Markov model (HMM). Tracking the steps in the sequence means knowing how many agents are grasping the object. To evaluate the method, humans that were not involved in the training of the HMM were asked to perform two tasks: a) perform the previously defined sequence as is, and b) perform a deviation of the sequence. The results of the method show that it is possible to detect the change between one human and two humans holding the object using only force and torque information.

This thesis deals with the general problem of robot motion planning and control. It proposes the hypothesis that it should bepossible to create a generic software framework capable of dealing with all robot motion planning and control problems, independent of the robot being used, the task being solved, the workspace obstacles or the algorithms employed. The thesis work then consisted of identifying the requirements and creating a design and implementation of such a framework. This report motivates and documents the entire process. The framework developed was tested on two different robot arms under varying conditions. The testing method and results are also presented.The thesis concludes that the proposed hypothesis is indeed valid.

Robotic exoskeleton technologies are one of the most active fields of robotics in recent years. Exoskeleton systems can give essential support for limb motions with enhanced strength and endurance, and they have a wide variety of therapeutic and supportive utility in life. These technologies have been extensively improved to be utilized for human power enhancement, worker injury prevention, human power assistance, and physical interface in augmented reality. Employees in the manufacturing and construction industries perform especially challenging duties, increasing their risk of health problems, disability, and medical leave, resulting in diminished job competitiveness and a shortage of qualified applicants. The usage of an exoskeleton might decrease muscular peak loads and lessen worker injury risks. This study includes a detailed analysis of employees wearing exoskeletons while doing various job-related duties. In this thesis, the tests assess the benefits of adopting exoskeletons in lowering human muscular activity and, as a result, weariness, and exhaustion. Unlike industrial robots, robotic exoskeleton technologies must be carefully built since they actually interact with actual users. The study used two widely available exoskeletons named Eksovest, an upper-body exoskeleton, and LegX, a lower-body exoskeleton. The study includes five applications: shoulder height weight-lifting, wall drilling, and roof drilling positions for the upper body Eksovest, and virtual chair and knee position for the lower body LegX. This application evaluated electromyography (EMG) signals which were collected using EMG sensors on the human body as supportive tools. Furthermore, the investigations compare the different volunteer’s body muscle data gathered by EMG sensors mounted on biceps, thigh, and calf muscles. The work also evaluates the accuracies of the data collecting procedures used in this study. Based on this study, it is discovered that by employing these exoskeletons may reduce muscular activity by up to 60%, hence enhancing the workforce's work life by reducing load and stresses on their body. This research will assist to raise the awareness by the outcomes of SMEs about the use of exoskeleton.

Lens distortions appear in almost all digital images and cause straight lines to appear curved in the image. This can contribute to errors in position estimations and 3D reconstruction and it is therefore of interest to correct for the distortion. If the camera is available, the distortion parameters can be obtained when calibrating the camera. However, when the camera is unavailable the distortion parameters can not be found with the standard camera calibration technique and other approaches must be used. Recently, variants of Perspective-n-Point (PnP) extended with lens distortionand focal length parameters have been proposed. Given a set of 2D-3D point correspondences, the PnP-based methods can estimate distortion parameters without the camera being available or with modified settings. In this thesis, the performance of PnP-based methods is compared to Zhang’s camera calibration method. The methods are compared both quantitatively, using the errors in reprojectionand distortion parameters, and qualitatively by comparing images before and after lens distortion correction. A test set for the comparison was obtained from a camera and a 3D laser scanner of an indoor scene.The results indicate that one of the PnP-based models can achieve a similar reprojection error as the baseline method for one of the cameras. It could also be seen that two PnP-based models could reduce lens distortion when visually comparing the test images to the baseline. Moreover, it was noted that a model can have a small reprojection error even though the distortion coefficient error is large and the lens distortion is not completely removed. This indicates that it is important to include both quantitative measures, such as reprojection error and distortion coefficient errors, as well as qualitative results when comparing lens distortion correction methods. It could also be seen that PnP-based models with more parameters in the estimation are more sensitive to noise.

This report is about the implementation of autonomy and control on a water quality measuring unmanned surface vehicle. The project was termed Catfish and involved five teams focusing on different aspects of the initial goal to create an autonomous three-part system; a surface drone, a submerged drone and flying drone. In this iteration of the Catfish project the focus laid on creating the surface drone and submerged drone as the Catfish project will improve over generations of thesis projects. The author of the report was in the Control and Autonomy team and had been tasked with giving the surface drone the autonomy needed to make this project viable. Existing advances made in autonomy was adopted and tested. With the help of estimation algorithms, and sensor fusion, a flight controller navigates the surface drone between a set of GPS waypoints. It is also able to counteract the external forces wind, waves and stream to keep its position. To reach this autonomy four test phases were conducted on a pre-prototype with progressively increased difficult autonomy starting with manual control and ending in advanced autonomy. When the advanced missions were executed the speed and accuracy of two different thruster configurations were examined and the best performing out of the two was implemented on the final prototype the other teams had designed. The project ended with a fully autonomous system that was able to execute all the navigational maneuvers required to operate autonomous water quality measuring missions. / Den här rapporten handlar om implementationen av autonomi och kontroll på en vattenkvalitetsmätande vattenburen drönare. Projektet fick namnet Catfish och blev indelat i fem teams som fokuserade på olika aspekter av ett 3-delsystem; en vattenburen, en undervattens och en flygande drönare. I denna iteration av Catfish projektet fokuserade medlemmarna på att utveckla den vattenburna och undervattens drönaren då projektet kommer fortsätta utvecklas under kommande generationer av Catfish projektrapporter. Författaren av den här rapporten ingick i ett team som hette "Control and Autonomy" och hade i uppgift att installera en autonom intelligens till den vattenburna drönaren för att göra Catfish prototypen användbar. Befintliga framsteg inom forskningsområdet blev granskade och testade. Genom att använda uppskattningsalgoritmer och "sensor fusion" lyckades en "flight controller" navigera drönaren mellan GPS waypoints och även behålla sin position genom att motverka krafterna från vind, vågor och strömmar. För att uppnå denna nivå av autonomi utför en förprototyp fyra test faser av ökad autonomisk svårhetsgrad. Under uppdraget blev hastigheten och precisionen av två olika motoruppsättningar undersöka och den som presterade bäst blev implementerad på den slutgiltig designen som de andra teamen hade utvecklat. Projektet avslutades med att ett fullt autonomt system blev utvecklat som var kapabel till att utföra alla navigationsmanövrar nödvändiga för att genomföra autonoma vattenkvalitetsmätningsuppdrag.

Examensrapporten redovisar resultatet av ett uppdrag från Linnéuniversitetet gällande utbyte och modernisering av ett felfungerande maskinlarmsystem på M/S Calmare Nyckel, ett utbildningsfartyg utan klasscertifikat, för nationell sjöfart. Uppdraget påbörjades med en kravsammanställning som hanterade både beställarkrav och externa krav från myndigheter och andra gällande regelverk. Därefter undersöktes det befintliga systemet i samband med en förstudie för att avgöra vad som kunde återanvändas i olika grad för olika tekniska lösningar som gick att implementera. Efter beställaren valde teknisk lösning från förstudien fortsatte arbetet med att ta fram en ny mjukvara och ett nytt användargränssnitt. Den totala lösningen resulterade i ett fungerande maskinlarmsystem som installerades och provades av utförarna ombord M/S Calmare Nyckel, och därefter utfördes en protokollbaserad provning av fartygets befälhavare. Hela konstruktions och utvecklingsprocessen skedde i samråd med beställaren i en iterativ process över hela utförandeperioden. En provning av maskinlarmsystemet kommer att utföras av Transportstyrelsen innan systemet blir helt godkänt för framdrift med obemannat maskinrum. / This bachelor's thesis shows the result of an assignment given by Linnaeus university regarding exchange and modernization of a faulty machine alarmsystem onboard M/S Calmare Nyckel, a training vessel without class certificate, for national shipping. The assignment started with a requirements specification that summarized both client specific requirements and external rules and regulations from governments and organizations. After this the existing alarmsystem was examined in conjunction with a pilot study to determine what equipment could be reused and in what degree for the different technical solutions. After the client chose a technical solution from the pilot study, the work continued with programming a new software and a graphical user interface. The assignment resulted in a new and functional machine alarmsystem that was installed and tested by the participants onboard M/S Calmare Nyckel, and thereafter a protocol-based test was conducted by the ships commander. The construction and development process were done in conjunction with the ship’s commander in an iterative process during the entire development period. A test of the machine alarmsystem will be conducted by the Transportstyrelsen before the system will be approved for use of unmanned engine room.

The industry of UAVs has experienced a boost in recent years, and developments on both the hardware and algorithmic side have enabled smaller and more accessible drones with increased functionality. This thesis investigates the possibilities of autonomous target recognition and tracking in small, low-cost drones that are commercially available today. The design and deployment of an object recognition and tracking algorithm on a Crazyflie 2.1, a palm-sized quadcopter with a weight of a few tens of grams, is presented. The hardware is extended with an expansion board called the AI-deck featuring a fixed, front-facing camera and a GAP8 processor for machine learning inference. The aim is to create a vision-based autonomous control system for target recognition and following, with all computations being executed onboard and without any dependence on external input. A MobileNet-SSD object detector trained for detecting human bodies is used for detecting a person in images from the onboard camera. Proportional controllers are implemented for motion control of the Crazyflie, that process the output from the detection algorithm to move the drone to the desired position. The final implementation is tested indoors and proved to be able to detect a target and follow simple movements of a human moving in front of the drone. However, the reliability and speed of the detection need to be improved to achieve a satisfactory result.

Genom att använda sig av robotar kan processer automatiseras på ett enkelt och kostnadseffektivt sätt. Tidigare forskning visar på att Robotic Process Automation (RPA) är ett attraktivt sätt för företag att investera i ny teknik som ger snabb avkastning. RPA kan även avlasta anställda inom företag där processer upplevs manuella och repetitiva. Å andra sidan visar även forskningen på att utmaningar finns vid implementationen av RPA, som att anställda inte vill acceptera den nya teknologin samt att ledning har svårt att kommunicera ut vad RPA ska bidra med. Syftet med denna studie är att öka förståelse kring implementeringsprocessen av RPA och vilka utmaningar som finns. Vidare ämnar studien att ge riktlinjer kring hur det går att underlätta implementationen av RPA och öka anställdas acceptans. Teoretiskt bidrar denna studie till ökad kunskap och förståelse i hur företag ska gå till väga för att öka anställas acceptans vid implementation av RPA. Genom litteratursökningar har relevanta teorier samlats in; RPA,Automation, Projektledning, IT-Projekt, Förändringsarbete och Technology Acceptance Model (TAM). Utifrån en kvalitativ ansats genomfördes fyra semistrukturerade intervjuer för att samla in empiri. Intervjuerna utfördes med fyra olika anställda på ett företag med olika roller. Genom en tematisk dataanalys identifierades tre teman; gemensam vision om RPA, saknad designfas och ansvar efter implementation. Resultatet visar på att det idag finns brister inom kommunikationen, förarbete och efterarbete vid implementeringen av RPA. Slutligen presenterar studien tre riktlinjer som ska hjälpa företaget att underlätta framtida implementationer av RPA.

Abstract  Context. In machine learning, ensemble methods continue to receive increased attention. Since machine learning approaches that generate a single classifier or predictor have shown limited capabilities in some contexts, ensemble methods are used to yield better predictive performance. One of the most interesting and effective ensemble algorithms that have been introduced in recent years is Random Forests. A common approach to ensure that Random Forests can achieve a high predictive accuracy is to use a large number of trees. If the predictive accuracy is to be increased with a higher number of trees, this will result in a more complex model, which may be more difficult to interpret or analyse. In addition, the generation of an increased number of trees results in higher computational power and memory requirements.  Objectives. This thesis explores automatic simplification of Random Forest models via post-pruning as a means to reduce the size of the model and increase interpretability while retaining or increasing predictive accuracy. The aim of the thesis is twofold. First, it compares and empirically evaluates a set of state-of-the-art post-pruning techniques on the simplification task. Second, it investigates the trade-off between predictive accuracy and model interpretability.  Methods. The primary research method used to conduct this study and to address the research questions is experimentation. All post-pruning techniques are implemented in Python. The Random Forest models are trained, evaluated, and validated on five selected datasets with varying characteristics.  Results. There is no significant difference in predictive performance between the compared techniques and none of the studied post-pruning techniques outperforms the other on all included datasets. The experimental results also show that model interpretability is proportional to model accuracy, at least for the studied settings. That is, a positive change in model interpretability is accompanied by a negative change in model accuracy.  Conclusions. It is possible to reduce the size of a complex Random Forest model while retaining or improving the predictive accuracy. Moreover, the suitability of a particular post-pruning technique depends on the application area and the amount of training data available. Significantly simplified models may be less accurate than the original model but tend to be perceived as more comprehensible. / Sammanfattning  Kontext. Ensemble metoder fortsätter att få mer uppmärksamhet inom maskininlärning. Då maskininlärningstekniker som genererar en enskild klassificerare eller prediktor har visat tecken på begränsad kapacitet i vissa sammanhang, har ensemble metoder vuxit fram som alternativa metoder för att åstadkomma bättre prediktiva prestanda. En av de mest intressanta och effektiva ensemble algoritmerna som har introducerats under de senaste åren är Random Forests. För att säkerställa att Random Forests uppnår en hög prediktiv noggrannhet behöver oftast ett stort antal träd användas. Resultatet av att använda ett större antal träd för att öka den prediktiva noggrannheten är en komplex modell som kan vara svår att tolka eller analysera. Problemet med det stora antalet träd ställer dessutom högre krav på såväl lagringsutrymmet som datorkraften.  Syfte. Denna uppsats utforskar möjligheten att automatiskt förenkla modeller som är genererade av Random Forests i syfte att reducera storleken på modellen, öka dess tolkningsbarhet, samt bevara eller förbättra den prediktiva noggrannheten. Syftet med denna uppsats är tvåfaldigt. Vi kommer först att jämföra och empiriskt utvärdera olika beskärningstekniker. Den andra delen av uppsatsen undersöker sambandet mellan den prediktiva noggrannheten och modellens tolkningsbarhet.  Metod. Den primära forskningsmetoden som har använts för att genomföra den studien är experiment. Alla beskärningstekniker är implementerade i Python. För att träna, utvärdera, samt validera de olika modellerna, har fem olika datamängder använts.  Resultat. Det finns inte någon signifikant skillnad i det prediktiva prestanda mellan de jämförda teknikerna och ingen av de undersökta beskärningsteknikerna är överlägsen på alla plan. Resultat från experimenten har också visat att sambandet mellan tolkningsbarhet och noggrannhet är proportionellt, i alla fall för de studerade konfigurationerna. Det vill säga, en positiv förändring i modellens tolkningsbarhet åtföljs av en negativ förändring i modellens noggrannhet.  Slutsats. Det är möjligt att reducera storleken på en komplex Random Forests modell samt bibehålla eller förbättra den prediktiva noggrannheten. Dessutom beror valet av beskärningstekniken på användningsområdet och mängden träningsdata tillgänglig. Slutligen kan modeller som är signifikant förenklade vara mindre noggranna men å andra sidan tenderar de att uppfattas som mer förståeliga.