<div>From prehistoric man who needs to be aware of the surrounding situations and hunt for food, to modern industry where machines and robots are programmed to explore the environment and accomplish assignments, situation awareness has always been an essential topic to everyone.</div><div><br></div><div>Advanced Driver-Assistance Systems (ADAS) is one of the modern technologies seeking effective solutions for driving safety. It also utilizes situation awareness model to interpret the driver's state in the environment and provide safe driving advice, with the potential to significantly reduce the traffic accident fatalities.</div><div><br></div><div>To enable situation awareness, an intelligent driving system needs to fulfill the following: (1) perceives the traffic elements in the environment, (2) comprehends the spatial-temporal interactions between a driver and other objects, and (3) projects the states of traffic elements to forecast future actions.</div><div><br></div><div>However, each level of situation awareness encounters its unique challenges in driving scenarios, for example, how to perceive vehicles in low-illuminated conditions? How to represent the complicated interactive relations in complicated driving situations? And how to anticipate the temporal dynamics of traffic elements and identify the where the potential risk comes from? To answer these questions, we explore situation awareness model for Advanced Driver-Assistance Systems at 3 levels: Perception, Comprehension and Projection. We discuss how to realize situation awareness based on three different computer vision tasks. We demonstrate that our proposed system is able to forecast the driver's operational intentions and identify risk objects to avoid hazards.</div>

Semantic segmentation is the task of predicting predefined class labels for each pixel in a given image. It is essential in autonomous driving, but also challenging because training accurate models requires large and diverse datasets, which are difficult to collect due to the high cost of annotating images at pixel-level. This raises interest in using synthetic images from simulators, which can be labelled automatically. However, models trained directly on synthetic data perform poorly in real-world scenarios due to the distributional misalignment between synthetic and real images (domain shift). This thesis explores the effectiveness of several techniques for alleviating this issue, employing Synscapes and Cityscapes as the synthetic and real datasets, respectively. Some of the tested methods exploit a few additional labelled real images (few-shot supervised domain adaptation), some have access to plentiful real images but not their associated labels (unsupervised domain adaptation), and others do not take advantage of any image or annotation from the real domain (domain generalisation). After extensive experiments and a thorough comparative study, this work shows the severity of the domain shift problem by revealing that a semantic segmentation model trained directly on the synthetic dataset scores a poor mean Intersection over Union (mIoU) of 33:5% when tested on the real dataset. This thesis also demonstrates that such performance can be boosted by 25:7% without accessing any annotations from the real domain and 17:3% without leveraging any information from the real domain. Nevertheless, these gains are still inferior to the 31:0% relative improvement achieved with as little as 25 supplementary labelled real images, which suggests that there is still room for improvement in the fields of unsupervised domain adaptation and domain generalisation. Future work efforts should focus on developing better algorithms and creating synthetic datasets with a greater diversity of shapes and textures in order to reduce the domain shift. / Semantisk segmentering är uppgiften att förutsäga fördefinierade klassetiketter för varje pixel i en given bild. Det är viktigt för autonom körning, men också utmanande eftersom utveckling av noggranna modeller kräver stora och varierade datamängder, som är svåra att samla in på grund av de höga kostnaderna för att märka bilder på pixelnivå. Detta väcker intresset att använda syntetiska bilder från simulatorer, som kan märkas automatiskt. Problemet är emellertid att modeller som tränats direkt på syntetiska data presterar dåligt i verkliga scenarier på grund av fördelningsfel mellan syntetiska och verkliga bilder (domänskift). Denna avhandling undersöker effektiviteten hos flera tekniker för att lindra detta problem, med Synscapes och Cityscapes som syntetiska respektive verkliga datamängder. Några av de testade metoderna utnyttjar några ytterligare märkta riktiga bilder (few-shot övervakad domänanpassning), vissa har tillgång till många riktiga bilder men inte deras associerade etiketter (oövervakad domänanpassning), och andra drar inte nytta av någon bild eller annotering från den verkliga domänen (domängeneralisering). Efter omfattande experiment och en grundlig jämförande studie visar detta arbete svårighetsgraden av domänskiftproblemet genom att avslöja att en semantisk segmenteringsmodell som upplärts direkt på den syntetiska datauppsättningen ger en dålig mean Intersection over Union (mIoU) på 33; 5% när den testas på den verkliga datamängden. Denna avhandling visar också att sådan prestanda kan ökas med 25; 7% utan att komma åt några annoteringar från den verkliga domänen och 17; 3% utan att utnyttja någon information från den verkliga domänen. Ändå är dessa vinster fortfarande sämre än den 31; 0% relativa förbättringen som uppnåtts med så lite som 25 kompletterande annoterade riktiga bilder, vilket tyder på att det fortfarande finns utrymme för förbättringar inom områdena oövervakad domänanpassning och domängeneralisering. Framtida arbetsinsatser bör fokusera på att utveckla bättre algoritmer och på att skapa syntetiska datamängder med en större mångfald av former och texturer för att minska domänskiftet.

The objective of this project is to develop a driving test using a Digital Human Modeling tool (DHM), specifically IPS IMMA, which will allow the evaluation of the ergonomics of the interior of vehicles as currently demanded by the automotive companies. Thus, improving both the design and the design process. This will involve a study of the driving and the tasks carried out by a real person to end up programming them in the DHM software. Based on this study an interface is suggested that guides engineers or ergonomists to design their own driving tests and enable them to evaluate their own designs without a high specialization in DHM tools and software. Taking into account the already present autonomous cars and their future development, the conceptual design of a two positions steering wheel (autonomous/manual driving) will be introduced as an example to be added in the driving test. This example is intended to show how DHM tools can be used to evaluate different designs solutions in early stages of the product development process. This project will be a contribution to one of the sections of the ADOPTIVE project carried out at the University of Skövde and in collaboration with Swedish automotive companies.

Le déploiement des futurs véhicules autonomes promet d'avoir un impact socio-économique majeur, en raison de leur promesse d'être à la fois plus sûrs et plus efficaces que ceux conduits par des humains. Afin de satisfaire à ces attentes, la capacité des véhicules autonomes à planifier des trajectoires sûres et à manœuvrer efficacement dans le trafic sera capitale. Cependant, le problème de planification de trajectoire au milieu d'obstacles statiques ou mobiles a une combinatoire forte qui est encore aujourd'hui problématique pour les meilleurs algorithmes.Cette thèse explore une nouvelle approche de la planification de mouvement, basée sur l'utilisation de la notion de décision de conduite comme guide pour structurer le problème de planification en vue de faciliter sa résolution. Cette approche peut trouver des applications pour la conduite coopérative, par exemple pour coordonner plusieurs véhicules dans une intersection non signalisée, ainsi que pour la conduite autonome où chaque véhicule planifie sa trajectoire. Dans le cas de la conduite coopérative, les décisions correspondent au choix d'un ordonnancement des véhicules qui peut être avantageusement encodé comme un graphe. Cette thèse propose une représentation similaire pour la conduite autonome, où les décisions telles que dépasser ou non un véhicule sont nettement plus complexes. Une fois la décision prise, il devient aisé de déterminer la meilleure trajectoire y correspondant, en conduite coopérative comme autonome. Cette approche basée sur la prise de décision peut permettre d'améliorer la robustesse et l'efficacité de la planification de trajectoire, et ouvre d'intéressantes perspectives en permettant de combiner des approches mathématiques classiques avec des techniques plus modernes d'apprentissage automatisé. / The deployment of future self-driving vehicles is expected to have a major socioeconomic impact due to their promise to be both safer and more traffic-efficient than human-driven vehicles. In order to live up to these expectations, the ability of autonomous vehicles to plan safe trajectories and maneuver efficiently around obstacles will be paramount. However, motion planning among static or moving objects such as other vehicles is known to be a highly combinatorial problem, that remains challenging even for state-of-the-art algorithms. Indeed, the presence of obstacles creates exponentially many discrete maneuver choices, which are difficult even to characterize in the context of autonomous driving. This thesis explores a new approach to motion planning, based on using this notion of driving decisions as a guide to give structure to the planning problem, ultimately allowing easier resolution. This decision-based motion planning approach can find applications in cooperative driving, for instance to coordinate multiple vehicles through an unsignalized intersection, as well as in autonomous driving where a single vehicle plans its own trajectory. In the case of cooperative driving, decisions are known to correspond to the choice of a relative ordering for conflicting vehicles, which can be conveniently encoded as a graph. This thesis introduces a similar graph representation in the case of autonomous driving, where possible decisions -- such as overtaking the vehicle at a specific time -- are much more complex. Once a decision is made, planning the best possible trajectory corresponding to this decision is a much simpler problem, both in cooperative and autonomous driving. This decision-aware approach may lead to more robust and efficient motion planning, and opens exciting perspectives for combining classical mathematic programming algorithms with more modern machine learning techniques.

No description available.

The presence of electrical and electronic circuits in commercial trucks has increased at a very fast rate during recent decades. With advancements in embedded systems and the introduction of electric controls in the automotive industry, the design of complex electric systems for the vehicles has become one of the major design challenges. In the commercial truck industry, the development cycles are almost a decade long. Therefore, it is a big challenge to introduce a new architecture to accommodate the modern automotive technologies in the upcoming generation of trucks. Currently, the commercial truck industry relies highly on a federated electrical/electronic (E/E) architecture. In this architecture, Electronic Control Units (ECU) are responsible for computation and Input/Output operations. These ECUs are clustered into different domains based on their respective functions. However, these domains are not isolated from each other. These modules communicate with each other using a vehicular network, which is typically a controller area network in the current trucks. In the automotive industry, automation is increasing at a fast pace. As the level of automation increases, the need for high computation also increases, which increases the overall costs. This study aims to address this problem by introducing an integrated E/E architecture where all the computational power is concentrated at one place (or perhaps two or three places to allow for redundancy). This study proposes to introduce a lowcost replacement for the current ECUs with more limited computational power but with generic input/output interfaces. This thesis provides the reader with some background of the current E/E architecture of commercial trucks and introduces the reader to ECUs. Additionally, the relevant network architectures and protocols are explained. A potential solution, based upon the centralized computation based E/E architecture and its implementation are discussed followed by a detailed analysis of the replacements for ECUs. The result of this analysis, if adopted, should result in a reduction of manufacturing and design costs, as well as make the production and maintenance process easier. Moreover, this should also have environmental benefits by reducing fuel consumption. / Förekomsten av elektronik och elektriska kretsar I kommersiella lastbilar has ökat i en väldigt snabb takt under de senaste decennierna. Med framsteg inom inbyggda system och introduktionen av elektroniska styrsystem i fordonsindustrin så har komplexa elektroniska system blivit en av de största designutmaningarna. I den kommersiella lastbilsindustrin där utvecklingscyklerna är nästan ett decennium, är det en stor utmaning att introducera ny arkitektur som tillgodoser all den nya teknologin som införlivas i fordonet. För närvarande så förlitar sig den kommersiella lastbilsindustrin mycket på en federated elektrisk/elektronisk (E/E) arkitektur. I denna arkitektur är elektroniska styrenheter (ECU) ansvariga för beräkningar och I/O (Input/Output) operationer. Dessa ECU:er är samlade i olika domäner baserade på dess funktioner. Domänerna är dock inte isolerade från varandra. De här modulerna kommunicerar därför med varandra med hjälp av ett fordonsnätverk, typiskt en CAN (Controller Area Network) i nuvarande lastbilar. I fordonsindustrin ökar automatiseringen i en snabb fart. I takt med att automatiseringen ökar så ökar även behovet av snabba och energiintensiva beräkningar, vilket i sin tur ökar den totala kostnaden. Denna studie har som mål att adressera det här problemet genom att introducera en integrated E/E arkitektur där all beräkningskraft är koncentrerad till en plats (eller två eller tre platser för att tillåta överskott). Den här studien föreslår att introducera en ersättning av nuvarande ECU:er till en låg kostnad, med lägre beräkningskraft och generiska I/O gränssnitt. Studien föreslår också ersättningar av nuvarande fordonsnätverk. Den här uppsatsen förser läsaren med viss bakgrund till den nuvarande E/E arkitekturen för kommersiella lastbilar och introducerar läsaren till ECU:er. Dessutom förklaras de relevanta nätverksarkitekturerna och protokollen. En potentiell lösning som baseras på den integrated E/E arkitekturen och dess implementering diskuteras med fokus på en detaljerad analys av ersättningarna till ECU:er. Resultatet av den här analysen skulle, om den adopteras, medföra minskning av tillverknings- och designkostnader samt leda till en förenkling av produktion och underhåll. Utöver det så bör det även ha miljöfördelar genom minskad bränsleförbrukning.

This paper compares two different methods, reinforcement learning and genetic algorithm for designing autonomous cars’ control system in a dynamic environment. The research problem could be formulated as such: How is the learning efficiency compared between reinforcement learning and genetic algorithm on autonomous navigation through a dynamic environment? In conclusion, the genetic algorithm outperforms the reinforcement learning on mean learning time, despite the fact that the prior shows a large variance, i.e. genetic algorithm provide a better learning efficiency. / I det här papperet jämförs två olika metoder, förstärkningsinlärning och genetisk algoritm för att designa autonoma bilar styrsystem i en dynamisk miljö. Forskningsproblemet kan formuleras som: Hur är inlärningseffektiviteten jämför mellan förstärkningsinlärning och genetisk algoritm på autonom navigering i en dynamisk miljö? Sammanfattningsvis, den genetisk algoritm överträffar förstärkningsinlärning på genomsnittlig inlärningstid, trots att den tidigare visar en stor varians, dvs genetisk algoritm, ger en bättre inlärningseffektivitet.

Occlusion is a frequently occuring challenge in vision systems for autonomous driving. The density of objects in the field-of-view of the vehicle may be so high that some objects are only visible intermittently. It is therefore beneficial to investigate ways to predict the paths of objects under occlusion. In this thesis, we investigate whether trajectory prediction methods can be used to solve the occlusion prediction problem. We investigate two different types of approaches, one based on motion models, and one based on machine learning models. Furthermore, we investigate whether these two approaches can be fused to produce an even more reliable model. We evaluate our models on a pedestrian trajectory prediction dataset, an autonomous driving dataset, and a subset of the autonomous driving dataset that only includes validation examples of occlusion. The comparison of our different approaches shows that pure motion model-based methods perform the worst out of the three. On the other hand, machine learning-based models perform better, yet they require additional computing resources for training. Finally, the fused method performs the best on both the driving dataset and the occlusion data. Our results also indicate that trajectory prediction methods, both motion model-based and learning-based ones, can indeed accurately predict the path of occluded objects up to at least 3 seconds in the autonomous driving scenario.

The development of autonomous driving systems has been one of the most popular research areas in the 21st century. One key component of these kinds of systems is the ability to perceive and comprehend the physical world. Two techniques that address this are object detection and semantic segmentation. During the last decade, CNN based models have dominated these types of tasks. However, in 2021, transformer based networks were able to outperform the existing CNN approach, therefore, indicating a paradigm shift in the domain. This thesis aims to explore the use of a vision transformer, particularly a Swin Transformer, in an object detection and semantic segmentation framework, and compare it to a classical CNN on road scenes. In addition, since real-time execution is crucial for autonomous driving systems, the possibility of a parameter reduction of the transformer based network is investigated. The results appear to be advantageous for the Swin Transformer compared to the convolutional based network, considering both object detection and semantic segmentation. Furthermore, the analysis indicates that it is possible to reduce the computational complexity while retaining the performance.

Model Based Systems Engineering (MBSE) approach aims at implementing various processes of Systems Engineering (SE) through diagrams that provide different perspectives of the same underlying system. This approach provides a basis that helps develop a complex system in a systematic manner. Thus, this thesis aims at deriving a system model through this approach for the purpose of autonomous driving, specifically focusing on developing the subsystem responsible for generating a feasible trajectory for a miniature vehicle, called AutoCar, to enable it to move towards a goal. The report provides a background on MBSE and System Modeling Language (SysML) which is used for modelling the system. With this background, an MBSE framework for AutoCar is derived and the overall system design is explained. This report further explains the concepts involved in autonomous trajectory planning followed by an introduction to Robot Operating System (ROS) and its application for trajectory planning of the system. The report concludes with a detailed analysis on the benefits of using this approach for developing a system. It also identifies the shortcomings of applying MBSE to system development. The report closes with a mention on how the given project can be further carried forward to be able to realize it on a physical system. / Modellbaserade systemteknikens (MBSE) inriktning syftar till att implementera de olika processerna i systemteknik (SE) genom diagram som ger olika perspektiv på samma underliggande system. Detta tillvägagångssätt ger en grund som hjälper till att utveckla ett komplext system på ett systematiskt sätt. Sålunda syftar denna avhandling att härleda en systemmodell genom detta tillvägagångssätt för autonom körning, med särskild inriktning på att utveckla delsystemet som är ansvarigt för att generera en genomförbar ban för en miniatyrbil, som kallas AutoCar, för att göra det möjligt att nå målet. Rapporten ger en bakgrund till MBSE and Systemmodelleringsspråk (SysML) som används för modellering av systemet. Med denna bakgrund, MBSE ramverket för AutoCar är härledt och den övergripande systemdesignen förklaras. I denna rapport förklaras vidare begreppen autonom banplanering följd av en introduktion till Robot Operating System (ROS) och dess tillämpning för systemplanering av systemet. Rapporten avslutas med en detaljerad analys av fördelarna med att använda detta tillvägagångssätt för att utveckla ett system. Det identifierar också bristerna för att tillämpa MBSE på systemutveckling. Rapporten stänger med en omtale om hur det givna projektet kan vidarebefordras för att kunna realisera det på ett fysiskt system.