The demand for robots to work in environments together with humans is growing. This calls for new requirements on robots systems, such as the need to be perceived as responsive and accurate in human interactions. This thesis explores the possibility of using AI methods to predict the movement of a human and evaluating if that information can assist a robot with human interactions. The AI methods that were used is a Long Short Term Memory(LSTM) network and an artificial neural network(ANN). Both networks were trained on data from a motion capture dataset and on four different prediction times: 1/2, 1/4, 1/8 and a 1/16 second. The evaluation was performed directly on the dataset to determine the prediction error. The neural networks were also evaluated on a robotic arm in a simulated environment, to show if the prediction methods would be suitable for a real-life system. Both methods show promising results when comparing the prediction error. From the simulated system, it could be concluded that with the LSTM prediction the robotic arm would generally precede the actual position. The results indicate that the methods described in this thesis report could be used as a stepping stone for a human-robot interactive system.

A growing body of international research on urban transport shows that women from all over the world are experiencing safety issues within today’s transport systems. Furthermore, these reports shed light on and discuss how gender bias within the transport sector contributes to this problem. To design future mobility services that everyone will use and enjoy, it is thus important to understand women’s travel needs and to involve a diverse group of users in the development process. With a vision of shaping mobility for a sustainable future NationalElectric Vehicles Sweden (NEVS) is developing a mobility solution consisting of connected, autonomous, and electrified vehicles designed and optimized for shared mobility within city environments. To address this issue in NEVS service this thesis applied an exploitative research approach to examining factors that affect women’s willingness to share rides with others(potential strangers) in a context where there is no driver physically present. The methodology, inspired by the ’Design Thinking’ framework consisted of two main phases:(I) Problem definition and (II) Concept development. To understand women’s safety issues within today’s transport system and frame the design challenge an extensive literature study covering the topics of women’s safety in public transport, technology acceptance, trust, and human-centered design was conducted. To further define user needs and encourage the end-users to take an active role in co-designing solutions for themselves two focus group workshops were held. The initial research and the results from the workshops further formed the basis for the subsequent Concept Development phase. A need for control over the shared travel situation revealed by the participants’ great demand for information led this phase to examine passengers' needs in relation to an In-Vehicle Information System (IVIS). Two prototypes were developed and further tested together with users to evaluate the proposed solutions. The results showed that the anthropomorphic system features used to create a more human-like interaction had a positive impact on the participants’ overall user experience and their perceived safety during a ’shared ride’ scenario. Having a female voice communicating system information made the participants feel less nervous, more comfortable, and more secure compared to when the same information was communicated solely by a visual interface. Other factors that had a major impact on the user experience in general and the perceived security were perceived Ease of Use (PEOU) and freedom of choice. The results showed how not understanding how to interact with the vehicle’s physical features had a negative impact on perceived safety while freedom of choice such as being able to book a specific seat in the vehicle is indicated to have a positive impact on people’s willingness to share their journey with a stranger.

The present thesis aims to establish ideas and technical solutions that can have a positive impact on women's perceived safety while traveling in autonomous vehicles, made for sharing with strangers. The method follows the Design Thinking model which contributes to a user-centered design approach. Initial literature research was performed to understand the problem area, which included women's issues in public transportation, the development of autonomous vehicles, the foundation of a trusting behavior and authentication technologies for identifying users. Following ideation workshops with eight potential users of the service contributed with ideas based on the female perspective and their expectations of traveling in a shared mobility alternative. These results provide a foundation that contributes to a specific purpose of the thesis to create and evaluate strategies for authentication of co-passengers due to being advocated by the participants. Two versions of a high-fidelity mobile application prototype were created in Figma with different strategies for how to interact with the service and authentication methods to align with the autonomous vehicle prototype provided by NEVS during the following tests.  The final user tests, with 14 participants, indicate that an identification method should be included in the service, especially during the night. Six of seven female participants appreciate a combination of Bank ID while requesting a ride and facial recognition when boarding the vehicle. However, the results of the male participants vary to a larger extent. The results do not indicate where the identification technology should be implemented, in the private phone or the vehicle doors. To create a solution available to a larger target group, the mobile application need to adopt and provide option alternatives regarding identification methods due to individual differences and previous experiences which lays a foundation for the users' ability to contribute to a trusting behavior. Furthermore, an onboarding process for the first-time user is proposed to prepare the user and describe how the service could be used and what is expected by them.

Denna studie handlar om robotarna Blue-bot och Bee-bot. Syftet är att ta reda på hur robotar används av utbildade pedagoger samt vilka färdigheter och kunskaper de beskriver att barnen utvecklar av att använda robotar. Frågeställningarna studien har är: “Hur beskriver de utbildade pedagogerna att de undervisar med Blue-bot eller Bee-bot?” och “Vilka färdigheter och kunskaper beskriver de utbildade pedagogerna att barnen utvecklar av att använda Blue-bot eller Bee-bot?”. Datainsamlingen gjordes via en kvalitativ metod med en fokusgrupp och tre intervjuer samt utfördes digitalt via Teams. Studien använder sig av den sociokulturella teorin för att granska resultatet. Resultatet visar att deltagarnas huvudsakliga syfte med arbetet med robotarna är att arbeta med matematik, vilket även involverar problemlösning, uppskattning av avstånd samt öva på rumsuppfattning och sekvensering. Alla delar inom matematik är färdigheter Kiliç (2022) kopplar till datalogiskt tänkande och det kan därmed sägas att det deltagarna vill att barnen ska utveckla i användandet av robotarna är datalogiskt tänkande. Resultatet visar också på att om syftet med att använda robotarna är att lära barnen programmeringsbegrepp och matematiskt tänkande är den analoga programmeringen bättre att använda än robotarna. Resultatet visar även att pedagogers frånvaro kan ge barnen större möjlighet till att utveckla det sociala samspelet samt utveckla fler färdigheter genom stöttning av andra barn.

ROS2 is an increasingly popular middleware framework for developing robotic applications. A ROS2 applicationbasically is composed of nodes that run concurrently and can be deployed distributedly. ROS2 nodes communicatewith each other through asynchronous interfaces; they reside in memory and wait to respond events that circulatearound the system during the interactions between the robot(s) and the environment. Rebeca is an actor-basedlanguage for modelling asynchronous, concurrent applications. Timed Rebeca added timing features to Rebeca todeal with timing requirements of real-time systems. The similarities in the concurrency and message-basedasynchronous interactions ofreactive nodes justify the relevance of using Timed Rebeca to assist the developmentand verification of ROS2 applications. Model-based development and model checking allow quicker prototypingand earlier detection ofsystem errors without the requirement of developing the entire real system. However, thereare challenges in bridging the gaps between continuous behaviours in a real robotic system and discrete behavioursin a model, between complex computations in a robotic system and the inequivalent programming facilities in amodelling language. There have been previous attempts in mapping Rebeca to ROS, however they could not beput into practice due to over-simplifications or improper modelling approaches. This thesis addresses the problemfrom a more systematic perspective and has been successful in modelling a realistic multiple autonomous mobilerobots system, creating corresponding ROS2 demonstration code, showing the synchronization between the modeland the program to prove the values of the model in driving development and automatic verification of correctnessproperties (freedom ofdeadlocks, collisions, and congestions). Stability of model checking results confirms designproblems that are not always detected by simulation. The modelling principles, modelling and implementingtechniques that are invented and summarized in this work can be reused for many other cases.

Cybercriminals' digital threats to security are increasing, and organisations seek smarter solutions to combat them. Many organisations are using artificial intelligence (AI) to protect their assets. Statistics show that the adoption of AI in cyber security worldwide has grown steadily over the past few years, demonstrating that more and more companies are searching for more effective methods than traditional ones. At the same time, some are cautious about its implementation. Previous research shows this is a topic of discussion in the cyber security branch. Researchers seek to understand further how AI is used, uncovering how it may benefit security and the challenges organisations face. Sweden is a country known for its high level of technological advancement and innovation, and it has seen a particularly significant increase in the integration of AI in cyber security practices. Using semi-structured interviews as the primary research method, a diverse range of companies, were interviewed regarding their viewpoints on the topic, both those implementing AI-based cyber security solutions and those who do not. The research objectives were to examine how companies in Sweden understand and perceive AI in cyber security, identify their perceived risks associated with any potential opportunities with AI adoption, and explore possible future developments in the field. Through in-depth interviews, participants discussed their experiences, concerns, and expectations surrounding the topic, showing anywhere from mixed to negative opinions from companies not utilising AI cyber security. This study shows how more research is needed to advance our understanding of AI cyber security and how it is implemented in companies. The study concludes that when showing interest in strengthening their security with the help of AI, organisations should consider the ethical and legal issues as well as the importance of choosing the right AI solutions. Professionals recommend AI implementation for companies wishing to increase cyber security defences in the rising and ever-changing cyber threats landscape. / Cyberbrottslingarnas digitala hot mot säkerheten ökar, och organisationer söker smartare lösningar för att bekämpa dem. Många organisationer använder artificiell intelligens (AI) för att skydda sina tillgångar. Statistik visar att användningen av AI inom cybersäkerhet världen över har ökat stadigt under de senaste åren, vilket visar att allt fler företag söker efter mer effektiva metoder än de traditionella. Samtidigt är vissa försiktiga vad gäller AI:s implementering. Tidigare forskning visar att detta är ett diskussionsämne inom cybersäkerhetsbranschen. Forskarna vill förstå mer om hur AI används, hur det kan gynna säkerheten och vilka utmaningar organisationerna står inför. Sverige är ett land som är känt för sin höga nivå av teknisk utveckling och innovation och man har sett en särskilt betydande ökning av integrationen av AI i cybersäkerhetspraxis i landet. Med hjälp av semistrukturerade intervjuer som primär forskningsmetod intervjuades en rad olika företag om deras syn på ämnet, både de som implementerar AI-baserade cybersäkerhetslösningar och de som inte gör det. Målet var att undersöka hur företag i Sverige förstår och uppfattar AI inom cybersäkerhet, att identifiera deras upplevda risker i samband med eventuella möjligheter med AI-adoption och utforska möjlig framtida utveckling inom området. Genom djupintervjuer diskuterade deltagarna sina erfarenheter, farhågor och förväntningar i ämnet, som visade allt från blandade till negativa åsikter från företag som inte använder AI i cybersäkerhet. Studien visar att det behövs ytterligare forskning för att öka vår förståelse för AI-cybersäkerhet och hur den ska implementeras i företag. Studien drar slutsatsen att organisationer som visar intresse för att stärka sin säkerhet med hjälp av AI bör ta hänsyn till etiska och juridiska frågor samt vikten av att välja rätt AI-lösningar. Experter rekommenderar att AI implementeras för företag som vill stärka sin cybersäkerhet i det ständigt ökande och föränderliga cyberhotslandskapet.

This thesis demonstrates a technique for developing efficient applications interpreting spacial deep learning output using Hyper Dimensional Computing (HDC), also known as Vector Symbolic Architecture (VSA). As a part of the application demonstration, a novel preprocessing technique for motion using state machines and spacial semantic pointers will be explained. The application will be evaluated and run on a Google Coral edge TPU interpreting real time inference of a compressed object detection model.

The testing of software for robot controllers has become increasingly difficult as robotic systems become more complex. As the complexity of the systems increases, the number of hardware systems that the robot relies on also grows. This poses a challenge in testing robot controllers, which is crucial to ensure that robots function safely and effectively in their intended applications. While simulation can be used as a platform for software testing, it is not feasible to simulate everything in a virtual environment, especially when test cases require physical connections to hardware for input and output signals sent to robot controllers. Therefore, the objective of this thesis is to replicate I/O device network communication in order to enhance virtual testing processes. The approach employed involves capturing real-time network traffic, modifying and rebuilding it, and subsequently replaying it. The work examines existing academic research on these approaches and technologies, and investigates the specific challenges in the testing process by conducting research within a company leading globally in industrial robot development. A conceptual model is proposed, and a prototype is developed. The solution demonstrates potential in addressing the current challenges in robot controller testing by enabling network capture, modification, and level 4 network traffic replay. However, experimental results reveal various limitations, such as significant delays in generating responses. Therefore, further research and development are required if the solution is to be implemented in a real-world setting.

Obstacle avoidance is a well researched area, however most of the works only consider a 2D environment. Drones can move in three dimensions. It is therefore of interest to develop a system that ensures safe flight in these three dimensions. Obstacle avoidance is of highest importance for drones if they are intended to work autonomously and around humans, since drones are often fragile and have fast moving propellers that can hurt humans. This project is based on the obstacle restriction algorithm in 3D, and uses OctoMap to conveniently use the sensor data from multiple sensors simultaneously and to deal with their limited field of view. The results show that the system is able to avoid obstacles in 3D. / Hinderundvikande är ett utforskat område, dock för det mesta har forskningen fokuserat på 2D-miljöer. Eftersom drönare kan röra sig i tre dimensioner är det intressant att utveckla ett system som garanterar säker rörelse i 3D. Hinderundvikande är viktigt för drönare om de ska arbeta autonomt runt människor, eftersom drönare ofta är ömtåliga och har snabba propellrar som kan skada människor. Det här projektet är baserat på Hinderrestriktionsmetoden (ORM), och använder OctoMap för att använda information från många sensorer samtidigt och för att hantera deras begränsade synfält. Resultatet visar att systemet kan undvika hinder i 3D.

Domestic chores are one of the most tedious and time consuming tasks in a person’s life. A lot of time can be saved and put to better use if these tasks can be automated. One such chore is the routine task of vacuuming the house every day. Robotic vacuum cleaners that clean the house are thus one of the most widely used domestic robots. These robots have the ability to clean the entire house almost autonomously with little or no human intervention. However, most of these robots do not have a system to report the real-time pick up of dirt which can be useful to the user in knowing which parts of his house are dirty and maybe investigate the reason behind it. This information can be useful to the robot as well in determining efficient cleaning patterns based on the dirt localization in the house. In this thesis a prototype was developed to measure the real-time pick-up of dirt by a robotic vacuum cleaner. It uses light sensing technology to measure the amount of dirt picked up and can thus be used to glean which parts of the house are dirtier than the others. The signals can also potentially be used to understand the size of the dirt picked up by the robotic vacuum cleaner. Research was done to investigate the different sensing technologies that can be used and to select the appropriate one. The system was tested and conclusions were made regarding its performance. Additional functions that can be implemented and improvements that can be made have also been suggested as future work. / Att städa hemmet är en av de mest tråkiga och tidskrävande uppgifterna i en persons liv. Mycket tid kan sparas och användas bättre om dessa uppgifter kan automatiseras. Robotdammsugare som städar golvet i hemmet är en av de mest använda inhemska robotarna, då dessa robotar har möjlighet att rengöra hela huset nästan autonomt med liten eller ingen mänsklig intervention. De flesta av dessa robotar har dock inte ett system för att rapportera realtidsupphämtning av smuts som kan vara användbart, då användaren kan få reda på vilka delar av huset som är smutsiga och då ha möjlighet att undersöka orsaken bakom. Denna information kan också vara användbart för roboten för att bestämma effektiva rengöringsmönster baserat på lokalisering av smuts i huset. I denna avhandling utvecklades en prototyp för att mäta upptagning av smuts i realtid av en robotdammsugare. Den använder IR-teknik för att mäta mängden smuts som hämtas upp och kan därmed använda informationen för att avgöra vilka delar av huset som är smutsigare än andra. Signalerna kan också potentiellt användas för att förstå storleken på smuts som tas upp. Forskning av olika tekniker utfördes för att kunna välja den mest lämpliga. Systemet testades därefter och slutsatser gjordes avseende dess prestanda. Ytterligare utredningar och förbättringar som kan genomföras har också föreslagits som framtida arbete.