With all the advancements in autonomous and connected cars, there is a developing body of research around the security and robustness of driving automation systems. Attacks and mitigations for said attacks have been explored, but almost always solely in software simulations. For this thesis, I led a team to build the foundation for an open source platoon of scale semi-autonomous vehicles. This work will enable future research into implementing theoretical attacks and mitigations. Our 1/10 scale car leverages an Nvidia Jetson, embedded microcontroller, and sensors. The Jetson manages the computer vision, networking, control logic, and overall system control; the embedded microcontroller directly controls the car. A lidar module is responsible for recording distance to the preceding car, and an inertial measurement unit records the velocity of the car itself. I wrote the software for the networking, interprocess, and serial communications, as well as the control logic and system control.

Background: Self-driving cars, also known as automated cars are a form of vehicle that can move without a driver or human involvement to control it. They employ numerous pieces of equipment to forecast the car’s navigation, and the car’s path is determined depending on the output of these devices. There are numerous methods available to anticipate the path of self-driving cars. Pedestrian detection is critical for autonomous cars to avoid fatalities and accidents caused by self-driving cars. Objectives: In this research, we focus on the algorithms in machine learning and deep learning to detect pedestrians on the roads. Also, to calculate the most accurate algorithm that can be used in pedestrian detection in automated cars by performing a literature review to select the algorithms. Methods: The methodologies we use are literature review and experimentation, literature review can help us to find efficient algorithms for pedestrian detection in terms of accuracy, computational complexity, etc. After performing the literature review we selected the most efficient algorithms for evaluation and comparison. The second methodology includes experimentation as it evaluates these algorithms under different conditions and scenarios. Through experimentation, we can monitor the different factors that affect the algorithms. Experimentation makes it possible for us to evaluate the algorithms using various metrics such as accuracy and loss which are mainly used to provide a quantitative measure of performance. Results: Based on the literature study, we focused on pedestrian detection deep learning models such as CNN, SSD, and RPN for this thesis project. After evaluating and comparing the algorithms using performance metrics, the outcomes of the experiments demonstrated that RPN was the highest and best-performing algorithm with 95.63% accuracy & loss of 0.0068 followed by SSD with 95.29% accuracy & loss of 0.0142 and CNN with 70.84% accuracy & loss of 0.0622. Conclusions: Among the three deep learning models evaluated for pedestrian identification, the CNN, RPN, and SSD, RPN is the most efficient model with the best performance based on the metrics assessed.

During the last decade, self-driving technology has become increasingly visible in the news, with the vision that people would enter vehicles that drive themselves, and that people could instead rest, read the newspaper, or have a meeting. However, these visions have mainly focused on the potential for car usage, even though public transport could benefit greatly from self-driving technology. For bus traffic, the bus driver accounts for half of the cost of driving, and savings on personnel costs could, for example, be reinvested in expanded public transport service or used to lower taxes. At the same time, more research has shown potential problems linked to self-driving technology, for example that more comfortable driving would lead to more traffic, which in turn would lead to increased emissions, higher noise levels in cities or further focus on car-centric infrastructure. For public transport, the driver's role in creating safety and acting as problem solvers has also been emphasized - who should I ask for directions if there is no knowledgeable driver on board? Various methods have previously been used to explore the social effects of self-driving technology and in this dissertation I have used so-called "four-stage models", more specifically the Swedish transport model Sampers. Four-stage models have been used for 50 years to evaluate effects on the transport system from e.g. infrastructure changes, but these models face new challenges, handling vehicles that drive by themselves. In my research, I have adjusted the model to simulate self-driving technology and investigated what effects this has on, for example, traffic volumes and emissions. In the three articles that are part of the dissertation, I have four main conclusions: Self-driving technology can mean large savings in costs for public transport, primarily for bus traffic but also to some extent for rail traffic. In addition, a smoother driving behaviour would mean more comfortable travel, which would increase the attractiveness of public transport. In addition, public transport not limited by, for example, driver schedules or current commercial conditions, could develop new types of services, such as on-demand public transport. Four-stage models have previously been used to model the transport system and have been shown to have good results, at least at an overall level. Within my research, I have made some adaptations of these models to mimic self-driving technology, but the models in their current form cannot consider, for example, vehicle sharing. It is important to point out that bus and train drivers currently perform many tasks that are not directly related to the driving of the vehicle, such as answering questions, maintaining social order among passengers and taking care of faults that occur during the trip. Today, self-driving technology cannot fulfil these roles. Self-driving technology for public transport would affect people's accessibility, driving style for vehicles, safety on board, how we plan traffic and the people who currently work as drivers. In fact, a multitude of societal effects have been identified, affecting all areas of transport. In addition, the effects are generally not similar across geographies, time units or for different actors, which further emphasizes that the total effect is not easy to summarize. / Självkörande teknik har under det senast decenniet synts allt mer i media, med målet att människor ska slippa köra själv på väg till jobbet, och istället kunna vila, läsa tidningen eller hålla ett möte. Dessa visioner har dock i huvudsak fokuserat på just bilen, trots att kollektivtrafiken skulle kunna dra stor nytta av självkörande teknik. För busstrafik står bussföraren för hälften av kostnaden för att köra trafiken, och besparingar på personalkostnader skulle t ex kunna återinvesteras i mer utökad kollektivtrafik, lägre skatter eller utökad välfärd inom andra områden. Samtidigt så har alltmer forskning visat på potentiella problem kopplat till självkörande teknik, exempelvis att den mer bekväma körningen skulle leda till mer trafik som i sin tur leder till mer utsläpp, höjda bullernivåer i städer eller ytterligare fokus på bilcentrerad infrastruktur. För kollektivtrafiken har även förarens roll som trygghetsskapande och som problemlösare lyfts fram – vem ska jag fråga om vägen om det inte finns en kunnig förare ombord?  Olika metoder har tidigare använts för att utforska samhällseffekterna av självkörande teknik, i den här avhandlingen har jag använt mig av så kallade ”fyrstegsmodeller”, mer specifikt den svenska transportmodellen Sampers. Fyrstegsmodeller har använts i uppemot 50 år för att utvärdera effekter på transportsystemet, men har ställts inför nya krav på att hantera fordon som körs av sig själva. Inom min forskning har jag gjort anpassningar av modellen för att simulera självkörande teknik och undersökt vilka effekter detta får på t ex trafikvolymer och utsläpp. I de tre vetenskapliga artiklarna som är del av avhandlingen har jag kommit fram till fyra huvudsakliga slutsatser: Självkörande teknik kan innebära stora besparingar i kostnader för kollektivtrafiken, i första hand för busstrafik men även i viss mån för spårtrafik. Därutöver skulle en mer jämn körstil innebära bekvämare resor, vilket skulle öka kollektivtrafikens attraktionskraft. Därutöver kan kollektivtrafik som inte begränsas av t ex förarscheman eller nuvarande kommersiella villkor kunna innebära nya tjänster, såsom efterfrågestyrd (”on-demand”) kollektivtrafik.  Fyrstegsmodeller har tidigare använts för att modellera transportsystemet och visat sig ha god överenstämmelse med verkligheten, åtminstone på övergripande nivå. Inom ramen för min forskning har jag gjort anpassningar av Sampers för att efterlikna självkörande teknik, men modellerna kan i sin nuvarande form inte ta hänsyn till t ex delande av fordon.  Det är viktigt att påpeka att förare idag utför många uppgifter som inte direkt är kopplade till framförandet av fordonet, såsom att svara på frågor, upprätthålla ordning bland resenärer och att ta hand om fel som uppstår på fordonet. Dessa roller kan självkörande teknik idag inte uppfylla.  De samhällseffekter som identifierats är överlag varierande och mångfaldiga. Självkörande teknik för kollektivtrafik skulle påverka människors tillgänglighet, körstilen för fordonen, tryggheten ombord, hur vi planerar trafiken och de personer som idag arbetar som förare. Dessutom är effekterna generellt sett inte likartade över geografi, tidsenhet eller för olika aktörer, vilket ytterligare understryker att effekten inte är enkel att sammanfatta.

Målet med examensarbetet har varit att samla information åt ett tekniskt konsultföretag för att öka deras kunskap om autonoma system och fordonskommunikation. Statusen på arbetet kring dessa aktiva säkerhetssystem hos olika aktörer och hur systemen implementeras i dagens och framtidens fordon har undersökts genom omfattande litteraturstudier, intervjuer och marknadsanalyser. De autonoma systemen kan samla information från omgivningen genom sensorer och bidra till ett jämnare trafikflöde, ökad säkerhet, lättare bilar och bättre miljö. Genom fordonskommunikationen kan fordon kommunicera med varandra samt infrastrukturen och garantera en säker bilfärd. År 2030 utgörs innerstaden av autonom, elektrifierad kollektivtrafik för att transportera människor på begäran, samtidigt som personbilar till viss del förbjuds. Potentiella behov för människan i en fullt autonom bil har identifierats och diverse produktutvecklingsmetoder har tillämpats för att utforma två konceptuella lösningar för en framtida bilinteriör. Lösningarna visar interaktionen mellan människa och system eftersom underhållning och bekvämlighet blir viktigt i en fullt autonom bil. Respektive lösning är statsägd och rymmer fyra passagerare. I lösningarna är sittplatserna placerade på ett sätt som underlättar kommunikation mellan passagerarna. Passagerarna kan underhållas eller informeras individuellt eller gemensamt via text, ljud och bild. / The goal with this thesis project has been to collect information for a technical consulting company in order to increase their knowledge about autonomous systems and vehicular communication. The status of how various operators work with active safety systems and how the systems are implemented in current and future vehicles has been investigated through extensive literature studies, interviews and market research. The autonomous systems can collect information from the surrounding through sensors and contribute to better traffic efficiency, increased safety, lighter cars and a better environment. Through vehicle communication, the vehicle can communicate with each other in order to guarantee a safe ride. In 2030 the inner city constitutes of autonomous, electrified public transport to transport people on demand, meanwhile private cars are prohibited. Potential needs for the human in a fully, autonomous car has been identified and various product development methods has been applied in order to develop two conceptual solutions for a future car interior. The solutions show the interaction between human and system since entertainment and comfort becomes important in a fully, autonomous car. Each solution is state-owned and holds four passengers. In the solutions, the seats are placed in regard to facilitate communication between the passengers. The passengers can be entertained or informed individually or collectively by text, sound and images.

The aim of this report is to evaluate how a future commercially owned fleet of self-driving electric vehicles (EV:s) would be able to provide power in order to avoid power exceedances in the power grid. Exceedances occur when network agreements between grid operating companies are exceeded. Exceedances are problematic, since they infer penalty fees for the paying company and make dimensioning the grid capacity more difficult for the supplying company. Capacity deficiency regarding the infrastructure of the grid is expected to increase, likely resulting in higher penalty fees. Integrating transport and power systems by using self-driving EV:s as Mobility as a Service combined with Vehicle-to-Grid (V2G) technology is a potential solution for this problem. By modeling the EV-fleet as the New York City taxi fleet, a usage pattern deemed to resemble Mobility as a Service is created. An economic value for the V2G service is estimated by comparing the availability of the EV-fleet with local exceedances from Uppsala as well as regional occurring exceedances. The highest income during the first quarter of 2019 is 96 000 SEK for the whole fleet, or 1100 SEK per EV and hour-long exceedance. The time of exceedance and the power magnitude have to interplay with the availability of the EV-fleet in order to enable the system. The EV battery capacity highly impacts the system, but is concluded to not be a limiting factor due to market logic. Lastly, key features such as market formation as well as geographical and technical aspects are presented and discussed.

Autonomous, otherwise known as self-driving, vehicles represent the future of transportation. Vehicles that drive themselves offer far reaching benefits from increased leisure and productivity for individuals to significant improvements in congestion and infrastructure for governments. The autonomous car will radically change the way we look at transportation, and they are right around the corner. However, the question remains: are we ready? Are we, as a society, ready to hand over the steering the wheel and trust autonomous vehicles with our safety? This paper predicts how the autonomous car will spread through society by analyzing and applying the product qualities and consumer types described in Everett Rogers’ Diffusion of Innovations Theory. Corporations, specifically Uber and Amazon, as opposed to individual consumers, will be the first to adapt, purchase and implement autonomous vehicles. Contrary to popular belief, these vehicles will not be successfully introduced as privately owned vehicles, and therefore, must be marketed towards corporations and organizations.

With self-driving cars on the horizon, vehicle autonomy and its problems is a hot topic. In this study we are using convolutional neural networks to make a robot car avoid obstacles. The robot car has a monocular camera, and our approach is to use the images taken by the camera as input, and then output a steering command. Using this method the car is to avoid any object in front of it. In order to lower the amount of training data we use models that are pretrained on ImageNet, a large image database containing millions of images. The model are then trained on our own dataset, which contains of images taken directly by the robot car while driving around. The images are then labeled with the steering command used while taking the image. While training we experiment with using different amounts of frozen layers. A frozen layer is a layer that has been pretrained on ImageNet, but are not trained on our dataset. The Xception, MobileNet and VGG16 architectures are tested and compared to each other. We find that a lower amount of frozen layer produces better results, and our best model, which used the Xception architecture, achieved 81.19% accuracy on our test set. During a qualitative test the car avoid collisions 78.57% of the time.

The self-driving public bus (SDPB) holds the potential to replace human-operated driving with more eco-friendly means and is therefore a valuable mobility solution for our future. The SDPB is based on the innovative technology of autonomous driving, which can only be guaranteed future market success with broad enough user acceptance. This acceptance is thus an essential factor for the growth of SDPB services. In this context, the travel behavior of young people is particularly interesting, as its development will continually demonstrate future mobility behavior trends. However, little research has been conducted regarding the best methods for motivating young people to accept SDPBs as a viable mode of travel. To address this topic, we first conducted a literature review, identifying factors that potentially influence SDPB acceptance. Subsequently, we developed a comprehensive research model based on the life-oriented approach and the technology acceptance model. This conceptualization was validated by a survey of 268 SDPB riders in real-world traffic. The results reveal several novel factors influencing the acceptance of SDPBs, in particular regarding differences in age. Our research contributes to existing research on both the life-oriented and travel behavior approaches by highlighting age differences and their importance in the field. For instance, our findings demonstrate a vital need to account for age differences when deriving policy implications for future mobility solutions.

Barns mobilitet och möjlighet att på egen hand ta sig runt i staden har minskat och begränsas idag i stor utsträckning av otrygga trafiksituationer. I och med sin begränsade oberoende mobilitet exkluderas barn från stadsrummet och dess faciliteter. Oberoende mobilitet kan relateras till flera dimensioner av barns sociala, fysiska, psykiska och kognitiva välmående. Syftet med studien är att undersöka om och på vilket sätt autonoma bussar kan bidra till barns oberoende mobilitet och med hjälp av barns upplevelser och erfarenheter bidra med insikter i detta inför införandet av autonoma bussar i städer och kollektivtrafiksystem. För att göra det besvaras frågeställningarna “Hur kan autonoma bussar i transportsystemet bidra till barns oberoende mobilitet?” och “Vilka förutsättningar är nödvändiga för att autonoma bussar ska bidra till barns oberoende mobilitet?”. Undersökningen utgår från ett fall av införande av autonoma bussar i stadsmiljö och för att besvara frågeställningarna genomfördes med elever på en grundskola fokusgrupper med syfte att inhämta deltagarnas upplevelser och erfarenheter. Resultatet tyder på att införandet av autonoma bussar i ett urbant område kan bidra till barns oberoende mobilitet på flera sätt och att bussarna har vissa egenskaper som gör att de kan anpassas till barns förutsättningar. Insikter från studien kan bidra till en förståelse för hur, från barns eget perspektiv, oberoende mobilitet kan gynnas av autonoma bussar i kollektivtrafiken, samt hur tjänsten behöver utvecklas för att anpassas till denna användargrupp när autonoma bussar i större utsträckning ska implementeras i staden. / Children's mobility and the opportunity to get around the city on their own has decreased and is today limited to a large extent by unsafe traffic situations. Due to their limited independent mobility, children are excluded from the urban space and its facilities. Independent mobility can be related to several dimensions of children's social, physical, mental and cognitive wellbeing. The purpose of the study is to investigate if and in what way autonomous buses can contribute to children's independent mobility and, using children's experiences, provide insights into this before the introduction of autonomous buses in cities and public transport systems. To do so, the two research questions "How can autonomous buses in the transport system contribute to children's independent mobility?"and "What prerequisites are necessary for autonomous buses to contribute to children's independent mobility?" are answered. The survey is based on a case of introduction of autonomous buses in urban environments and to answer the questions three focus groups with students in a primary school were conducted with the aim of gaining the participants' experiences. The results indicate that the introduction of autonomous buses in an urban area can contribute to children's independent mobility in several ways and that the buses have certain characteristics that enable them to be adapted to children's conditions. Insights from the study can contribute to an understanding of in what way, from children's own perspective, independent mobility can benefit from autonomous buses in public transport, and how the service needs to be developed to adapt to this user group when autonomous buses are to be implemented to a greater extent in the city.

Helt självkörande fordon är inte längre en utopi eller något som man ser på film. Redan idag finns fullt fungerande prototyper och flera tillverkare påstår sig ha fullt självkörande fordon redan on några år. Autonomi bedöms civilt kunna ge upphov till flera resurseffektiviseringar inom vägtransportområdet. En kapacitetsökning av förmågan till förbandstransporter av stridsfordonsförband, samt en ökning av uthållighet, transportförmåga och tillgänglighet är faktorer som Försvarsmaktens perspektivstudie (2018) och Försvarsberedningens rapport, Värnkraft (2019) anser borde prioriteras fram till 2025.  I denna komparativa prediktionsstudie har tre olika alternativ av autonomi jämförts med hjälp av Analytic hierarchy process (AHP), för att analysera vilken grad av autonomi som har störst militär nytta för stridsfordonstransporter. Utgångspunkt för studien har varit utifrån ett scenario där förbandstransport av en mekaniserad bataljon genomförts. Som ingångsvärden för studien har litteraturstudier och intervjuer utifrån tekniken, autonominoch militära kontexten nyttjats. Resultatet indikerar att autonomi har militär nytta vid operativa stridsfordonstransporter genom att den taktiska tillgängligheten, operativa rörligheten och transportkapaciteten ökas. Möjlighet till autonomi minskar transporttiden vilket medger längre tid till förberedelser i insatsområdet för förbandet som transporterades. / Self-driving vehicles are no longer a utopian idea or something that you see in the movies. Today there are already fully functioning prototypes and several manufacturers claim they will have fully self-driving vehicles in just a few years’ time. In the civilian world, this new technology is expected to be capable of generating several resource efficiencies in road transportation. Increased capacity in unit combat vehicle transport capability and an increase in endurance, transportability and availability are factors that the Armed Forces' Perspective Study, as well as the Swedish Ministry of Defence´s study report Värnkraft, considers should be prioritized by 2025. In this comparative study, three different autonomy options have been compared, using the Analytic Hierarchy Process (AHP), to analyse what degree of autonomy has the greatest military utility for combat vehicle transport. The starting point of the study was based on a scenario where the transportation of a mechanized battalion had been carried out. The sources of information ​​for the study were literature studies and interviews based on technology, autonomy and the military context. The results indicate some degree of autonomy has military utility in the long-distance transportation of combat vehicles, by increasing tactical availability, operational mobility and transport capacity. Autonomy reduces transport time, allowing longer preparation time for the transported unit in the combat zone.