Within the AutoDrive project, openPASS is used to develop a cognitive stochastic traffic flow simulation for urban intersections and highway scenarios, which are described in deliverable D1.14. The deliverable D2.16 includes the customizations of the framework openPASS that are required to provide a basis for the development and implementation of the driver behavior model and the evaluated safety function. The trial design for the evaluation of the safety functions is described. Furthermore, the design of the driver behavior study is introduced to parameterize and validate the underlying driver behavior model.

As part of the AutoDrive project, OpenPASS is used to develop a cognitive-stochastic traffic flow simulation for urban intersection scenarios described in deliverable D1.14. The deliverable D4.20 is about the design of the modules for the stochastic traffic simulation. This initially includes an examination of the existing traffic simulations described in chapter 2. Subsequently, the underlying tasks of the driver when crossing an intersection are explained. The main part contains the design of the cognitive structure of the road user (chapter 4.2) and the development of the cognitive behaviour modules (chapter 4.3).

As part of the AutoDrive project, the OpenPASS framework is used to develop a cognitive-stochastic traffic flow simulation for urban intersection scenarios described in deliverable D1.14. This framework was adapted and further developed. The deliverable D5.13 deals with the construction of the stochastic traffic simulation. At this point of the process, the theoretical design aspects of D4.20 are implemented. D5.13 explains the operating principles of the different modules. This includes the foundations, boundary conditions, and mathematical theory of the traffic simulation.

Seeking a valuable and relevant topic for the future of mobility. the author came across the pain point trust in relation to artificial intelligence. Advances in the creation of artificial intelligence and deep learning ensure that our everyday lives are increasingly shaped by algorithms, sometimes consciously, sometimes unconsciously.For many people, this idea causes discomfort, and especially in situations of one‘s own vulnerability, the question of how an AI will handle more responsible tasks in the future will be essential. The automotive industry will also be shaped by this issue. In the intelligent car of the future, people will at least partially relinquish both control and privacy. Autonomous driving will be a test of trust for future users, as will the question of digital ethics and the collection of private data. In this thesis, a possible answer to the question was explored, how we can shape the approach and interaction with technology - especially artificial intelligence - in the future in order to create trustf uluser experiences. For this purpose, beyond the formal-aesthetic elaboration, the main focus was on interactive solutions and communication with AI, how an AI behaves in the vehicle and how it can contribute to making users feel comfortable in such a context. BMW Me&AI describes a scenario in which potential customers get to know an intelligent vehicle for the first time and are carefully introduced to its processes and possibilities. Inspired by soft robotics, the presented interior design is mainly defined by a holistic concept of soft interaction surfaces. Three basic scenarios are described in which passengers have the freedom to either look over AI‘s shoulder, sit back and focus on other things, or be completely on their own. This created a result that became unique in its dynamics and degree of adaptability and posed a real challenge, especially for the creative process, which in retrospect clearly paid off.

No description available.

Once automatic vehicles are available, working from self-driving car (WFC) in the AV's mobile office will be a real option. It allows firms to socialize land costs for office space from the office lot to road infrastructure used by AV. Employees, in turn, can switch wasted commuting time into working hours and reduce daily time tied to working. We develop a microeconomic model of employer's offer and employees choice of WFC contracts and hours. Using data for Germany and the U.S., we perform Monte Carlo studies to assess whether WFC may become reality. Eventually, we study the impact of transport pricing on these choices. Our findings is, that WFC contracts are likely to be a standard feature of large cities given current wages, office, and current and expected travel costs. There is a clear decline of hours spent working in office. On average, WFC hours and distance traveled slightly exceed commuting figures.

The Localization and Map building module is a core building block for designing an autonomous vehicle. It describes the vehicle ability to create an accurate model of its surroundings and maintain its position in the environment at the same time. In this thesis work, we contribute to the autonomous driving research area by providing a proof-of-concept of integrating SLAM solutions into commercial vehicles; improving the robustness of the Localization and Map building module. The proposed system applies Bayesian inference theory within the occupancy grid mapping framework and utilizes Rao-Blackwellized Particle Filter for estimating the vehicle trajectory. The work has been done at Scania CV where a heavy duty vehicle equipped with multiple-Lidar sensory architecture was used. Low level sensor fusion of the different Lidars was performed and a parallelized implementation of the algorithm was achieved using a GPU. When tested on the frequently used datasets in the community, the implemented algorithm outperformed the scan-matching technique and showed acceptable performance in comparison to another state-of-art RBPF implementation that adapts some improvements on the algorithm. The performance of the complete system was evaluated under a designed set of real scenarios. The proposed system showed a significant improvement in terms of the estimated trajectory and provided accurate occupancy representations of the vehicle surroundings. The fusion module was found to build more informative occupancy grids than the grids obtained form individual sensors. / Modulen som har hand om både lokalisering och byggandet av karta är en av huvudorganen i ett system för autonom körning. Den beskriver bilens förmåga att skapa en modell av omgivningen och att hålla en position i förhållande till omgivningen. I detta examensarbete bidrar vi till forskningen inom autonom bilkörning med ett valideringskoncept genom att integrera SLAM-lösningar i kommersiella fordon, vilket förbättrar robustheten hos lokaliserings-kartbyggarmodulen. Det föreslagna systemet använder sig utav Bayesiansk statistik applicerat i ett ramverk som har hand om att skapa en karta, som består av ett rutnät som används för att beskriva ockuperingsgraden. För att estimera den bana som fordonet kommer att färdas använder ramverket RBPF(Rao-Blackwellized particle filter). Examensarbetet har genomförts hos Scania CV, där ett tungt fordon utrustat med flera lidarsensorer har använts. En lägre nivå av sensor fusion applicerades för de olika lidarsensorerna och en parallelliserad implementation av algoritmen implementerades på GPU. När algoritmen kördes mot data som ofta används av ”allmänheten” kan vi konstatera att den implementerade algoritmen ger ett väldigt mycket bättre resultat än ”scan-matchnings”-tekniken och visar på ett acceptabelt resultat i jämförelse med en annan högpresterande RBPFimplementation, vilken tillför några förbättringar på algoritmen. Prestandan av hela systemet utvärderas med ett antal egendesignade realistiska scenarion. Det föreslagna systemet visar på en tydlig förbättring av uppskattningen av körbanan och bidrar även med en exakt representation av omgivningen. Sensor Fusionen visar på en bättre och mer informativ representation än när man endast utgår från de individuella lidarsensorerna.

A transformative revolution in transportation is coming with the advent of Au-tonomous Vehicles (AVs), which are expected to increase mobility, reduce trafficcongestion, and save fuel. Although AVs present significant advantages, they alsopose substantial challenges, particularly when it comes to security and safety. Theaim of this study is to map out the existing knowledge in order to facilitate furtherresearch and development, which will hasten the rollout of secure and reliable au-tonomous vehicles. This, in turn, will enable a sustainable and efficient future fortransportation. Research on AV safety and security is reviewed in this thesis in acomprehensive systematic literature review. The search process identified a total of283 studies published between 2019 and 2022, out of which 24 studies were selectedthrough a multi-stage process according to our predefined protocol. Based on re-search topics in selected studies, our findings have a significant impact on the fieldof Artificial Intelligence and automated vehicles. Based on our findings, we canprovide a summary of current knowledge regarding the safety, security, and stabilityimplications of autonomous vehicles. Simulations, real-life experiments, and physi-cal tests were all used in the selected articles for evaluation. Aside from the excellentresults, we identified many limitations of the articles, including the limitations of thedata sets, the analysis of unusual events, and the verification practices.

Platooning is a method where a chain of vehiclesdrive with small inter-vehicular distances. The many benefitsof autonomous platooning includes improved fuel economy,less congestion and safer transportation. To create a safe andfunctional platoon the operational software needs to be able tohandle various road surfaces without the risk of a crash. Thisreport is aiming to improve the safety of a platoon by includingcommunication of data between vehicles in the chain. Specificallythe focus has been on transferring information about the tireslip, to model a cooperative adaptive cruise control (C-ACC)and combine the two. A system was designed using the dynamicsfor a quarter-car model and then connected to a controller and aplatoon of four vehicles. Simulations of when the leading vehiclebraked hard on two different road surfaces with and withoutthe slip awareness was conducted. The tire slip awareness in thecontroller consisted of proportional control on the error and alow-pass filter. The simulations showed that the inclusion of thetire slip in the controller improved the platooning performance,in the sense that the inter-vehicle distance could be contained.It was also shown the controller could be tuned so that the slipratios were limited. / Konvojkörning är en metod där en kedjaav fordon åker med små interna distanser. De många fördelarnamed förarlösa konvojer inkluderar förbättrad bränsleförbukning, mindre trafik och säkrare transportering. För atten säker och funktionell konvoj ska kunna skapas krävs detatt mjukvaran kan handskas med varierande vägunderlag utanrisk att krocka. Den här rapporten siktar på att förbättrasäkerheten i konvojkörning genom att överföra data till andrafordon i konvojkedjan. Speciellt har fokuset legat på överförainformation om däcksliring, att modellera en kooperative adaptivfarthållare (C-ACC) och sedan kombinera de två. Ett systemdesignades genom att använda dynamiken av en fjärdedelsbil och sen ansluta modellen till en konvoj med fyra fordon.Simulationer av när det ledande fordonet tvärbromsade på olikavägunderlag med och utan däcksliringsinfromation genomfördes.Däckslirnings i regulatorn bestod av proportionerlig kontroll påfelet och ett lågpassfilter. Simulationerna visade att inkluderingenav däcksliringsinformation i regulatorn förbättrar konvojensprestanda, på så sätt att de interna distanserna kan hanteras.Det kunde också påvisas att kontrollern kunde kalibreras så attslirningen begränsades. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

Multitask Learning (MTL) was conceived as an approach to improve thegeneralization ability of machine learning models. When applied to neu-ral networks, multitask models take advantage of sharing resources forreducing the total inference time, memory footprint and model size. Wepropose MTL as a way to speed up deep learning models for applicationsin which multiple tasks need to be solved simultaneously, which is par-ticularly useful in embedded, real-time systems such as the ones foundin autonomous cars or UAVs.In order to study this approach, we apply MTL to a Computer Vi-sion problem in which both Object Detection and Semantic Segmenta-tion tasks are solved based on the Single Shot Multibox Detector andFully Convolutional Networks with skip connections respectively, usinga ResNet-50 as the base network. We train multitask models for twodifferent datasets, Pascal VOC, which is used to validate the decisionsmade, and a combination of datasets with aerial view images capturedfrom UAVs.Finally, we analyse the challenges that appear during the process of train-ing multitask networks and try to overcome them. However, these hinderthe capacity of our multitask models to reach the performance of the bestsingle-task models trained without the limitations imposed by applyingMTL. Nevertheless, multitask networks benefit from sharing resourcesand are 1.6x faster, lighter and use less memory compared to deployingthe single-task models in parallel, which turns essential when runningthem on a Jetson TX1 SoC as the parallel approach does not fit intomemory. We conclude that MTL has the potential to give superior per-formance as far as the object detection and semantic segmentation tasksare concerned in exchange of a more complex training process that re-quires overcoming challenges not present in the training of single-taskmodels.