Social robots and artificial intelligence are radical innovations at the cutting edge of technology. Touted as the fourth industrial revolution, the future is looking bright for social robotics, and for the markets which can benefit from this technology. However, despite a wealth of research regarding technical functionality, there has been little research conducted into the future strategies required to ensure the successful diffusion of these innovations into society or effective methods of influencing rapid adoption rates in target markets.  The following research questions have been designed to identify potential solutions to existing and future problems facing the social robotics industry: What are the barriers to the early stages of the diffusion of innovation for social robotics start-ups? How can these innovative companies cross the chasm? In order to formulate the findings, primary research was conducted in the form of interviews within three categories: academics, practitioners and social robotics experts. Secondary research was undertaken to analyse and compare primary findings. The research is purely qualitative as quantitative data was purposefully disregarded due to limitations on time and scope.  In summary, social robotics start-ups face significant barriers to diffusion such as inherently expensive products and misaligned customer expectations. Attracting ‘pragmatists in pain’ is vital to be able to cross the chasm and a strong reference base is necessary for social robots to be adopted in the mainstream market. Start-ups need to meet the demands of the ‘expected product’ to attract the early majority (pragmatist) segment, providing a greater possibility of crossing the chasm and enabling rapid adoption. It is assumed that either a mass or niche strategy can be chosen, depending on the type of product in subject. An adaptation to the technology adoption life cycle has been made in the form of the ‘double-bell curve’ and the ‘V’ in the chasm has been identified within the process of successful diffusion. Methods of improving the rate of adoption have been applied in consideration of the ‘technology acceptance model’, with a heavy focus on increasing trialability and observability. There is a risk of potential ‘overadoption’ in the social robotics industry, however the changing shift in customer attitudes towards technology adoption lowers boundaries to diffusion.

Navigation is the fundamental capability of mobile robots which allows them to move fromone point to another without any human interference. The autonomous operation of theserobots is depended on reliable, robust, and intelligent navigation system. With the recenttechnological progress, autonomous mobile robots are being deployed and used in differentareas and scenarios. Conventional navigation approaches depend on predefined accurateobstacle maps and costly high-end precise laser sensors. These maps are difficult and expensiveto acquire and degrade due changes in the environment. This limits the overall use of mobilerobots in dynamic settings. In this research, we investigate the end-to-end learning-basedapproach using vision and ranging sensors while using Deep Reinforcement Learning formobile robot navigation for indoor environments. Different state-of-the-art DRL algorithms were trained and compared in 3D-simulation in termsof sample efficiency and cumulative reward. Next, extensive experiments were carried outusing 10-dimensional sparse distance data from vision and ranging sensor. The trained modelswere evaluated in different environments of varying complexity to analyze the strength andgeneralizability of the learnt policies. Our results showed that ranging sensor approach was able to learn a robust navigation policywhich was able to generalize in unseen virtual environments without any additional trainingwith a high success rate. Whereas vision-based approach performed poorly due to insufficientinformation and hardware constraints. Moreover, all the experiment were carried out only insimulation. However, they should be directly transferable to an actual robot since abstractobservation space was used.

Autonomous lawn mowers and floor cleaning robots are today easily accessible and areutilizing well-studied Coverage Path Planning algorithms. They operate in single-floorenvironments that are small with simple geometry compared to general urban environments such as city parking garages, highway bridges or city crossings. A next step for autonomous cleaning is road sweeping of these complex urban environments. In this work,a new Coverage Path Planning approach, Sampled BA* & Inward Spiral , handling this taskwas compared with existing well-performing algorithms BA* and Inward Spiral. The proposed approach combines the strengths of existing algorithms and demonstrates state-of-the-art performance on three large-scale 3D environments. It generated paths with lessrotation, while keeping the length of the path on the same level. For a given starting point,the new approach had consistently lower cost (length + rotation) for all environments. Forrandom starting points, randomness in the new approach caused less robustness, givingsignificantly higher cost. To improve the performance of the algorithms and remove biasfrom manual tuning, the parameters were automatically tuned using Bayesian Optimization. This makes the evaluation more robust and the results stronger.

Ontology-based technologies like Semantic Web and Knowledge Graphs are promising for knowledge management in manufacturing industries. In the literature there are abundant of publications related to using ontologies to represent and capture knowledge in manufacturing. Many of them cover the use of ontologies for managing knowledge in different aspects of Product Lifecycle Management (PLM). Nevertheless, very few of them cover how ontologies can be used with virtual factory models, data and information as well as the knowledge generated from using these models and their corresponding engineering activities. An “extension” of existing ontologies is badly needed as digital, virtual models in terms of simulation and digital twins have become more popular in the industry. Without such an extended knowledge management process and system, it is difficult to re-use the artefacts and knowledge generated from the expensive and valuable virtual engineering activities. Relying on the cutting-edge graph database technologies and what they can offer regarding knowledge management, and also recent developments in the domain ontology field, an extended knowledge management implementation, specifically designed for virtual engineering has been done. Moreover, a clear roadmap for establishment of knowledge bases around production systems armed with Virtual Factory(VF) and Multi-Objective Optimization (MOO) processes has been provided. This, includes defining key elements of manufacturing procedures, constructing an ontology, defining data structure in preferably a graph database, and accessing valuable historical (provenance) data regarding different engineering entities and/or activities.

Over the last decade, the integration of robots into various applications has seen significant advancements fueled by Machine Learning (ML) algorithms, particularly in autonomous and independent operations. While robots have become increasingly proficient in various tasks, object instance recognition, a fundamental component of real-world robotic interactions, has witnessed remarkable improvements in accuracy and robustness. Nevertheless, most existing approaches heavily rely on prior information, limiting their adaptability in unfamiliar environments. To address this constraint, this thesis introduces the Segment and Learn Semantics (SaLS) framework, which combines video object segmentation with Continual Learning (CL) methods to enable semantic understanding in robotic applications. The research focuses on the potential application of SaLS in mobile robotics, with specific emphasis on the TORO robot developed at the Deutsches Zentrum für Luft- und Raumfahrt (DLR). Evaluation of the proposed method is conducted using a diverse dataset comprising various terrains and objects encountered by the TORO robot during its walking sessions. The results demonstrate the effectiveness of SaLS in classifying both known and previously unseen objects, achieving an average accuracy of 78.86% and 70.78% in the CL experiments. When running the whole method in the image sequences collected with TORO, the accuracy scores were of 75.54% and 84.75%, for known and unknown objects respectively. Notably, SaLS exhibited resilience against catastrophic forgetting, with only minor accuracy decreases observed in specific cases. Computational resource usage was also explored, indicating that the method is feasible for practical mobile robotic systems, with GPU memory usage being a potential limiting factor. In conclusion, the SaLS framework represents a significant step forward in enabling robots to autonomously understand and interact with their surroundings. This research contributes to the ongoing development of robotic systems that can operate effectively in unstructured environments, paving the way for more versatile and capable autonomous robots.

Sjöfartshögskolan i Kalmar har ett långtgående studentprojekt att bygga en modell av skolfartyget M/S Calmare Nyckel som autonomt ska köra runt i en damm på skolan för att visa upp skolans profil. Projektet är tänkt att sammanfoga kunskaper från många olika delar av utbildningen såsom elektronik, programmering, och stabilitet. Detta arbete syftar till att undersöka Ultra Wideband som teknik för positionering av modellen för att i framtiden kunna använda positionen för att navigera i dammen. Specifikt så användes tre chip av typen ESP32 UWB som implementation av Ultra Wideband då det var ett billigt alternativ som verkade lovande. Två av chippen var stillastående på kända positioner och positionen för det tredje chippet räknas ut med hjälp av triangulering. Den uppmätta noggrannheten för systemet anses inte vara tillräckligt bra för att fortsätta med ESP32 UWB i fortsättningen av projektet.En båtmodell av M/S Calmare Nyckel togs fram med hjälp av CAD programmet Autodesk Fusion 360 och tanken är att båtmodellen ska 3D printas på universitetet och sedan byggas ut med RC komponenter så båtmodellen kan göra fart genom vatten. Tanken är även att båtmodellen ska kunna manövrera helt autonomt till en laddstation för att sedan återvända ut på sin planerade rutt. Med hjälp av forum och experter online så har alternativ till vilka typer av komponenter såsom, elmotor, styrservo, propeller och annat som behövs för driften tagits fram. Alternativen är bara förslag på vilka komponenter som rekommenderas och inga exakta modeller. / The Kalmar Maritime Academy have an ongoing student project to build a model of the academy’s training ship M/S Calmare Nyckel. The model is supposed to autonomously sail around a pond located in the academy’s premises to show off the academy’s profile. The project is intended to combine knowledge from many different parts of the program such as electronics, programming, and stability. This project aims to investigate Ultra Wideband as a technology for positioning the model to be able to use the position to navigate the pond. Three ESP32 UWB chips were used as an implementation of Ultra Wideband as it was a cheap alternative that showed promise. Two of the chips were stationary at known positions and the position of the third chip is then calculated using triangulation. The measured accuracy of the system is not considered good enough to continue with the ESP32 UWB in the continuation of the project.A boat model of M/S Calmare Nyckel was produced using the CAD program Autodesk Fusion 360 and the idea is that the boat model can be 3D printed at the university and then expanded with RC components so that the boat model can make speed through water. The idea is also that the boat model should be able to maneuver completely autonomously to a charging station and then return to its planned route. With the help of online forums and experts, alternatives to the types of components such as electric motor, steering servo, propeller, and other things needed for operation have been developed. The options are only suggestions of which components are recommended and not exact models.

Over the years, the Artificial Intelligence and Integrated Computer Systems (AIICS) Division at Linköping University has developed a high-level architecture for collaborative robotic systems that includes a delegation system capable of defining complex missions to be executed by a team of agents. This architecture has been used as a part of a research arena for developing and improving public safety and security using ground, aerial, surfaceand underwater robotic systems. Recently, the division decided to purchase a Boston Dynamics Spot robot to further progress into the public safety and security research area.The robot has a robotic arm and navigation functionalities such as map building, motion planning, and obstacle avoidance. This thesis investigates how the Boston Dynamics Spot robot can be integrated into the high-level architecture for collaborative robotic systems from the AIICS division. Additionally, how the robot’s functionalities can be extended so that it is capable of determining which actions it should take to achieve high-level behavioursconsidering its capabilities and current state. In this context, higher-level behaviours include picking up and delivering first aid supplies, which can be beneficial in specific emergency situations. The study was divided and done in an iterative approach.The system was tested in various scenarios that represent its intended future use. The result demonstrated the robot’s ability to plan and accomplish the desired high-level behaviours. However, there were instances when achieving the desired behaviours proved challenging due to various limiting factors, including limitations posed by the robot’s internal controller.

The process of grading code submissions in programming courses is time-consuming and error-prone. To address this issue, we propose a project that automates the testing and grading process for Java code submissions at Halmstad University. Our approach leverages property-based testing using the JUnit Quick-Check library to generate tests and test reports automatically.   The tool we demonstrate in this project is designed to provide students with immediate feedback on their code submissions and reduce the workload for instructors. By automatically generating tests and test reports, our approach ensures that code submissions meet the required specifications and are free from common errors. The com.pholser library is utilized to implement the property-based testing approach.   We believe that our project has the potential to improve the grading process for programming courses and provide a more efficient and effective way of assessing student code submissions. Our implementation can be easily extended to support other programming languages and can be integrated with existing learning management systems to provide a seamless experience for instructors and students alike. / Processen för att bedöma kodinlämningar i programmeringskurser är vara tidskrävande. För att lösa problemet, vill vi automatisera testerna och generera en testrapport för Javainlämningar vid Högskolan i Halmstad. Vi tillhandahåller ett verktyg som med hjälp av Property-Based Testing och JUnit Quick-check biblioteket underlättar denna process för lärarna. Verktyget är utformat för att kunna ge studenterna direkt återkoppling på deras inlämningar. Genom att automatiskt generera tester och testrapporter säkerställer vi att inlämningarna uppfyller de krav som läraren specificerar.   Detta projekt har potential att förbättra rättningsprocesser i programmerings- kurser genom att testa inlämningar på ett systematiskt och likvärdigt sätt och genom att vara ett mer effektivt sätt att bedöma studenternas inlämningar. Verktyget skulle kunna integreras med en Learning Management System för att även automatisera nerladdning av inlämningar och uppladdning av resultat.

The use of micro aerial vehicles (MAV) for civilian use such as exploration and inspection of varying structures, equipment and areas have garnered some interest as of late. MAVs have the mobility and agility to traverse three dimensional space quickly and access hard to reach areas where other alternatives would struggle, but a flying platform such as a MAV comes with it’s own set of distinct problems. Almost any collision with the environment results in a complete failure of the platform. Any exploratory framework would need to perform obstacle avoidance and online path planning in a fully unknown environment with low computation times to ensure that the limited battery resources on the MAV is used in the most efficient way. In this thesis the exploratory rapidly-exploring random tree (ERRT) framework will be further optimized and an efficient strategy for finding valid exploration paths which are not in the immediate vicinity of the MAV will be developed and integrated. The method is demonstrated and proven through results from simulations and real life experiments.

The manufacturing industry faces new challenges after the emersion of the fourth industrial revolution having brought with it a new knowledge-based and digital era. Among the most important factors for survival of today´s manufacturing companies are efficiency, flexibility, and responsiveness to the changing market. The technological development certainly raises the bar as far as demands go, but it also introduces new solutions to deal with the increase in demand. Opportunities for a higher degree of automation in manufacturing is one such thing. ABB Electrification Sweden AB are interested in introducing a higher degree of automation in an assembly cell where contactors are manufactured. Currently there is no sure way to assess to what extent it is possible to increase the level of automation within the assembly system. The purpose of this study is to explore opportunities for streamlining the assembly process through automation, to increase productivity. The research question to be answered in this study reads as follows: RQ: How can automation be used to increase productivity in an existing assembly cell where contactors are manufactured? This study was conducted in the form of a case study based on a product development process in two stages. Interactive research was also conducted during three workshops where practitioners from the company joined the researcher in analysing data and contributing with prior experiences. Through analysing the data collected from the assembly process, a common ground for knowledge could be achieved which contributed to introducing decision criteria regarding actions for automation implementation. The study resulted in a proposition of an updated assembly process with a higher degree of automation than previously. This proposed solution consisted of several specifications ranging from an estimation of cycle time for each assembly process to the cost of acquiring new equipment. Furthermore, a layout was suggested as well as an estimation of labour costs and resources. A 25 % increase in productivity could also be estimated based on the reduced cycle time. Automation can be used as a measure to streamline the manufacturing process of contactors in an assembly cell. To achieve this, knowledge and understanding of the specific assembly unit is required to identify available opportunities. This knowledge can be acquired based on a combination of prior experiences and evaluation of the current assembly system. Other conclusions from the study were that previous research regarding automation of assembly cells could be applied to the case of an assembly cell where contactors are manufactured as well. Furthermore, actions for automation are easier to implement for products that are adapted for automated assembly. Finally, automation is most useful when regarded as a tool for optimization and should not be thought of as a framework to be applied on a larger scale. Key words: contactor manufacturing, assembly cell, automation, streamlining, productivity