Autonomous Driving and Advance Driver Assistance Systems (ADAS) are revolutionizing the way we drive and the future of mobility. Among ADAS, Traffic Sign Classification is an important technique which assists the driver to easily interpret traffic signs on the road. In this thesis, we used the powerful combination of Image Processing and Deep Learning to pre-process and classify the traffic signs. Recent studies in Deep Learning show us how good a Convolutional Neural Network (CNN) is for image classification and there are several state-of-the-art models with classification accuracies over 99 % existing out there. This shaped our thesis to focus more on tackling the current challenges and some open-research cases. We focussed more on performance tuning by modifying the existing architectures with a trade-off between computations and accuracies. Our research areas include enhancement in low light/noisy conditions by adding Recurrent Neural Network (RNN) connections, and contribution to a universal-regional dataset with Generative Adversarial Networks (GANs). The results obtained on the test data are comparable to the state-of-the-art models and we reached accuracies above 98% after performance evaluation in different frameworks

To achieve the widespread diffusion of autonomous electric buses (AEBs) and thus harness their environmental potential, a broad acceptance of new technology-based mobility concepts must be fostered. Still, there remains little known about the factors determining their acceptance, especially in the combination of vehicles with alternative fuels and autonomous driving modes, as is the case with AEBs. In this study, we first conducted qualitative research to identify relevant factors influencing individual acceptance of autonomously driven electric buses. We then developed a comprehensive research model that was validated through a survey of 268 passengers of an AEB, operated in regular road traffic in Germany. The results indicate that a mix of individual factors, social impacts, and system characteristics determine an individual’s acceptance of AEBs. Notably, it is important that users perceive AEBs, not only as advantageous, but also trustworthy, enjoyable, and in a positive social light. Our research supplements the existing corpora by demonstrating the importance of individual acceptance and incorporating it to derive policy implications.

No description available.

Sensors, as a crucial part of autonomous driving, are primarily used for perceiving the environment. The recent deep learning development of different sensors has demonstrated the ability of machines recognizing and understanding their surroundings. Automotive radar, as a primary sensor for self-driving vehicles, is well-known for its robustness against variable lighting and weather conditions. Compared with camera-based deep learning development, Object detection using automotive radars has not been explored to its full extent. This can be attributed to the lack of public radar datasets. In this thesis, we collect a novel radar dataset that contains radar data in the form of Range-Azimuth-Doppler tensors along with the bounding boxes on the tensor for dynamic road users, category labels, and 2D bounding boxes on the Cartesian Bird-EyeView range map. To build the dataset, we propose an instance-wise auto-annotation algorithm. Furthermore, a novel Range-Azimuth-Doppler based multi-class object detection deep learning model is proposed. The algorithm is a one-stage anchor-based detector that generates both 3D bounding boxes and 2D bounding boxes on Range-AzimuthDoppler and Cartesian domains, respectively. Our proposed algorithm achieves 56.3% AP with IOU of 0.3 on 3D bounding box predictions, and 51.6% with IOU of 0.5 on 2D bounding box predictions. Our dataset and the code can be found at https://github.com/ZhangAoCanada/RADDet.git.

This thesis is concerned with model predictive control (MPC) within the field of autonomous driving. MPC requires a model of the system to be controlled. Since a vehicle is expected to handle a wide range of driving conditions, it is crucial that the model of the vehicle dynamics is able to account for this. Differences in road grip caused by snowy, icy or muddy roads change the driving dynamics and relying on a single model, based on ideal conditions, could possibly lead to dangerous behaviour. This work investigates the use of Gaussian processes for learning a model that can account for varying road friction coefficients. This model is incorporated as an extension to a nominal vehicle model. A double lane change scenario is considered and the aim is to learn a GP model of the disturbance based on previous driving experiences with a road friction coefficient of 0.4 and 0.6 performed with a regular MPC controller. The data is then used to train a GP model. The GPMPC controller is then compared with the regular MPC controller in the case of trajectory tracking. The results show that the obtained GP models in most cases correctly predict the model error in one prediction step. For multi-step predictions, the results vary more with some cases showing an improved prediction with a GP model compared to the nominal model. In all cases, the GPMPC controller gives a better trajectory tracking than the MPC controller while using less control input.

Semi-autonomous driving is an emerging – though not unprecedented – technology which cannot necessarily be seen as safe and reliably accident-free. Insurance companies thus play an important role as influential stakeholders in the negotiation and implementation processes around this new technology. They can either push the technology (e.g. by offering beneficial, promotional insurance models for semi-autonomous car owners) or constrain it (e.g. by providing restrictive insurance models or no insurance cover at all). Insurers face questions concerning ethical or societal consequences on various levels: not only when it comes to promoting the technology – whose impact is not yet certain and may range from saving to endangering lives – but also with respect to insurance models such as “pay as you drive”, which may involve discriminatory elements. The concept of responsible research and innovation (RRI) is well suited to accompanying and guiding insurers, policy makers and other stakeholders in this field through a responsible negotiation process that may prove beneficial for everyone. Part of the RRI approach is to make stakeholders aware of “soft” factors such as the ethical, societal or historical factors which influence innovation and of the need to include these aspects in their activities responsibly.

The aim of the thesis is to develop a method to identify driving lanes based on aerial images and existing spatial data. The proposed method uses up to date available data in which it identifies road surface marking (RSM). Polygons classified as RSM are further processed to obtain their vector line representation as the first partial result. While processing RSM vectors further, borders of driving lanes are modelled as the second partial result. Furthermore, attempts were done to be able to automatically distinguish between solid and broken lines for a higher amount of information contained in the resulting dataset. Proposed algorithms were tested in 20 case study areas and results are presented further in this thesis. The overall correctness as well as the positional accuracy proves effectivity of the method. However, several shortcomings were identified and are discussed as well as possible solutions for them are suggested. The text is accompanied by more than 70 figures to offer a clear perspective on the topic. The thesis is organised as follows: First, Introduction and Literature review are presented including the problem background, author's motivation, state of the art and contribution of the thesis. Secondly, technical and legal requirements of RSM are presented as well as theoretical concepts and...

Recent studies on robustness of machine learning systems shows that today’s autonomous vehicles struggle with very basic visual disturbances such as rain or snow. There is also a lack of training data that includes off road scenes or scenes with different forms of deformation to the road surface. The purpose of this thesis is to address the lack of off-road scenes in current dataset for training of autonomous vehicles and the issue of visual disturbances by building a simulated 3D environment for generating training scenarios and training data for specific environments. The synthesised scenes is implemented using modern OpenGL, and we propose methods to synthesis rutting and the formation of potholes on road surfaces as well as rain and fog with a parameterized approach. \\ The generated datasets are tested through semantic segmentation using state of the art pretrained neural networks. The results show that the neural networks accurately identifies the road surface in in clear weather as long as the road surface is mostly coherent. The synthesised rain and fog decrease performance of the neural networks significantly. \\ Generating training data with the method presented in this thesis and incorporating it as part of the training data used in training neural networks for autonomous driving systems could be used to improve performance in certain scenarios. Specifically, it could improve performance in driving scenes with heavy road deformations, and in scenes with low visibility. Further research is needed to conclude that the data is useful, but the results generated in this thesis is promising.

The latest trends in autonomous vehicles research gave rise to the needs for specific tools to validate and test such systems. The estimations state that to consider an autonomous vehicle statistically safe, it should drive for thousands of kilometres using traditional validation methods. This process would take a long time. Furthermore, an update in the software, would require to re-run those kilometres. Therefore, the testing must be performed exploiting virtual simulations that should realistically reflect the real world. One way to perfor msuch simulations is to let the vehicle model drive down a road map and control the surrounding traffic. To be effective, spawned traffic should not be generated too far from the target vehicle. The OpenSCENARIO standard offers a feature restricting such traffic within an ellipse centred in the central object (target vehicle). This thesis investigated what technique was more efficient and scalable to detect viable roads within the ellipse to spawn stochastic traffic on. The explored solutions are two: an analytical approach and an adaptation of the AABB tree algorithm. The research started with simple cases and incremented the scenario’s complexity during the development. Through this methodology, each technique’s positive aspects and limits have been highlighted, allowing a comparison to be made. / De senaste trenderna i autonoma fordon har ökat behovet av specifika verktyg för att validera och testa sådana system. För att kunna betrakta ett autonomt fordon som statistiskt säkert, ska enligt uppskattningar autonoma fordon köra tusentals kilometer med traditionella valideringsmetoder. Denna process skulle ta mycket lång tid. Dessutom skulle en uppdatering i mjukvaran kräva att alla dessa tusentals kilometer att körs igen. Därför måste testningen utföras med hjälp av virtuella simuleringar som bör efterlikna den reella världen realistiskt. Ett sätt att genomföra dessa simuleringar är att låta en autonom fordonsmodell köra genom ett vägnät och kontrollera kringliggande trafik. För att vara effektiv, bör kringliggande trafik inte genereras för långt bort från autonoma fordonsmodellen. OpenSCENARIO-standarden innehåller en funktion som begränsar genererad trafik inom en ellips centrerad kring fordonsmodellen. Detta examensarbete undersökte vilka tekniker som är mest effektiva och skalbara för att detektera relevanta vägar inom ellipsen att generera stokastisk trafik på. De två lösningar som studerades var: en analytisk och en numerisk som använde sig av AABB-träd-algoritmen. Utförandet började med simpla fall som successivt ökade till mer avancerade scenarion. Genom denna metodik blev varje tekniks positiva aspekter samt begränsningar belysta och jämförbara.

This document is intended to give an overview of the validation of the human subject study, conducted in the driving simulator of the Chair of Traffic and Transportation Psychology (Verkehrspsychologie – VPSY) of the Technische Universität Dresden (TUD), as well of the validation of the stochastic traffic simulation developed in the AutoDrive project by the Chair of Automotive Engineering (Lehrstuhl Kraftfahrzeugtechnik – LKT) of TUD. Furthermore, the evaluation process of a C-AEB (Cooperative-Automatic Emergency Brake) system is demonstrated. The main purpose was to compare the driving behaviour of the study participants and the driving behaviour of the agents in the traffic simulation with real world data. Based on relevant literature, a validation concept was designed and real world data was collected using drones and stationary cameras. By means of qualitative and quantitative analysis it could be shown, that the driving simulator study shows realistic driving behaviour in terms of mean speed. Moreover, the stochastic traffic simulation already reflects reality in terms of mean and maximum speed of the agents. Finally, the performed evaluation proofed the suitability of the developed stochastic simulation for the assessment process. Furthermore, it could be shown, that a C-AEB system improves the traffic safety for the chosen test-scenarios.