This study addresses the limitations of existing autonomous vehicle datasets, particularly the need for greater specificity of weather conditions and road types. We utilized X-CAR to highlight the challenges of extreme weather and non-urban road conditions on autonomous driving systems. Our dataset comprises recordings under seven distinct weather and lighting conditions across four road types. Notably, our research focuses on differentiating between various lighting and weather conditions and road types, which often need improvement in many existing datasets. We used the X-CAR platform to collect 360-degree image information and LiDAR point clouds at 10Hz. Due to the constraints of time and resources, we used algorithmic prediction to generate ground truth data via the Co-DETR 2D prediction algorithm. We validated the accuracy of the Co-DETR algorithm through partial manual annotation. However, it is undeniable that in some extreme conditions, the algorithm-generated ground truth can lead to results deviating from expectations and real-world situations. Therefore, we conducted a scaled manual annotation and controlled experiments, ensuring the highest level of accuracy. After the manual annotation, we validated our initial conclusions and trained a model based on YOLOv8x, focusing on weak environmental conditions. The final model underwent multiple iterations and achieved satisfactory accuracy. The enhanced model demonstrated a significant increase in detection accuracy compared to the original YOLOv8x model. At the same time, our analysis identifies weather conditions that markedly reduce detection accuracy, providing focal points for future dataset enhancements. / Master of Science / This study explores the limitations of current autonomous vehicle datasets, particularly their lack of detail regarding weather conditions and road types. We used X-CAR to examine how extreme weather and light conditions affect autonomous driving systems. Our dataset includes recordings from seven different weather and lighting conditions across four types of roads. Due to time and resource constraints, we used an algorithm to predict ground truth data with the help of Co-DETR. While not all data was fully annotated, we manually labeled part of the data to create an actual ground truth. This allowed us to verify our previous findings and train a model based on YOLOv8x, focusing on challenging conditions. The improved model showed much higher accuracy in detecting objects than the original YOLOv8x model. This study highlights the significant impact of weather conditions on detection accuracy and suggests areas for future improvements in datasets.

Ett produktutvecklingsprojekt som behandlar hur problemen kring en förarmiljös formspråk, reglage och kombinationen av dessa i högre grad kan utformas på ett kognitivtergonomiskt och estetiskt vis med anknytning till varumärke. I projektet utfördes en omfattande studie över nutidens förarmiljöer där flera tydliga trender upptäcktes.  I parallellkurs utfördes ett kognitiv ergonomiskt praktikfall tillsammans med litteratur som förankrat arbetet i att forma tekniken efter människan.  Sedan har projektet fördjupat i estetiska principer och olika studier kring förarmiljöer behandlas.  Konceptframtagningen bestod av tre faser. Där det initialt togs fram en mängd övergripande formspråk. Sedan lades de åt sidan för att utforma manöverdon. Slutligen kombinerades resulterande formspråk med manöverdon till en helhet och ett slutkoncept valdes ur dem. Projektet leder fram till ett konceptförslag genom formspråk, ratt och mittreglage till förarmiljön. Konceptförslag med återkoppling till varumärket, målgrupp, kognitiv ergonomi och estetik. / A product development project that deal with the problem of how a driver environment's design language, controls, and the combination of these to a greater extent can be designed in a cognitive ergonomic and aesthetic way related to the brand. The project was carried out a comprehensive study of contemporary operator environments where several clear trends were detected. In parallel course was conducted a cognitive ergonomic case study together with literature that secured the work in shaping technology for humans. The project has immersed in the aesthetic principles and various studies on driver environments have been treated. The development concept consisted of three phases. Initially a wide range of comprehensive design language was developed. Then they were put aside to design the actuators. Finally the resulting design with actuators combined into a whole which an end concept was chosen from. The project leads to design documentation through form-language, steering wheel and center controls for a driving environment. Design documentation with feedback to the brand, audience, cognitive ergonomics and aesthetics.

Indianapolis / E-scooters are ubiquitous and their number keeps escalating, increasing their interactions with other vehicles on the road. E-scooter riders have an atypical behavior that varies enormously from other vulnerable road users, creating new challenges for vehicle active safety systems and automated driving functionalities. The detection of e-scooter riders by other vehicles is the first step in taking care of the risks. This research presents a novel vision-based system to differentiate between e-scooter riders and regular pedestrians and a benchmark dataset for e-scooter riders in natural environments. An efficient system pipeline built using two existing state-of-the-art convolutional neural networks (CNN), You Only Look Once (YOLOv3) and MobileNetV2, performs detection of these vulnerable e-scooter riders.

E-scooters are ubiquitous and their number keeps escalating, increasing their interactions with other vehicles on the road. E-scooter riders have an atypical behavior that varies enormously from other vulnerable road users, creating new challenges for vehicle active safety systems and automated driving functionalities. The detection of e-scooter riders by other vehicles is the first step in taking care of the risks. This research presents a novel vision-based system to differentiate between e-scooter riders and regular pedestrians and a benchmark dataset for e-scooter riders in natural environments. An efficient system pipeline built using two existing state-of-the-art convolutional neural networks (CNN), You Only Look Once (YOLOv3) and MobileNetV2, performs detection of these vulnerable e-scooter riders.<br>