Search the digital library catalog

Abstract: This study develops and evaluates advanced predictive models for the trajectory planning of autonomous vehicles (AVs) in roundabouts, with the aim of significantly contributing to sustainable urban mobility. Starting from the “MRoundabout” speed model, several Artificial Intelligence (AI) and Machine Learning (ML) techniques, including Linear Regression (LR), Random Forest (RF), Support Vector Regression (SVR), Gradient Boosting Regression (GBR), and Neural Networks (NNs), were applied to accurately emulate human driving behavior and optimize AV trajectories. The results indicate that neural networks achieved the best predictive performance, with R2 values of up to 0.88 for speed prediction, 0.98 for acceleration, and 0.94 for differential distance, significantly outperforming traditional models. GBR and SVR provided moderate improvements over LR but encountered difficulties predicting acceleration and distance variables. AI-driven tools, such as ChatGPT-4, facilitated data pre-processing, model tuning, and interpretation, reducing computational time and enhancing workflow efficiency. A key contribution of this research lies in demonstrating the potential of AI-based trajectory planning to enhance AV navigation, fostering smoother, safer, and more sustainable mobility. The proposed approaches contribute to reduced energy consumption, lower emissions, and decreased traffic congestion, effectively addressing challenges related to urban sustainability. Future research will incorporate real traffic interactions to further refine the adaptability and robustness of the model.
Keywords: sustainable mobility, autonomous vehicles, machine learning, roundabouts, artificial intelligence, ChatGPT
Published in DKUM: 04.04.2025; Views: 0; Downloads: 1
Full text (9,00 MB)
This document has many files! More...

Abstract: Pedestrian safety is a well-known issue, such that many road safety associations emphasize measures to improve this aspect. One of the main conflict points is pedestrian crossings, where motorized and non-motorized traffic flows directly interact and where pedestrian attention and reaction are two elements that can strongly influence their safety. Nowadays, these aspects are often deviated by the use of smartphones to surf the Internet or social media. The aim of the present study is to find out (1) whether and how intersection typology affects pedestrian behavior, both in terms of attention and crossing performance, and (2) whether and how gaze and behavioral characteristics are affected by smartphone use and social media browsing. To achieve this goal, eye-tracking technology was used to obtain qualitative and quantitative information on the number of fixations, their duration, and reaction times of pedestrians. Additionally, from the eye-tracking videos, it was possible to derive pedestrian waiting times, crossing times, and speeds. Statistical tests were conducted to determine if there is a significant difference in pedestrian behavior at the three different types of intersections and in their behavior when using or not using their device. Results confirm the initial hypotheses and quantify the difference in pedestrian gaze behavior and crossing performance when walking across three different types of signalized crosswalks.
Keywords: pedestrian, eye-tracking, gaze behavior, reaction time, signalized intersection, crossing behavior
Published in DKUM: 13.03.2025; Views: 0; Downloads: 5
Full text (2,86 MB)
This document has many files! More...

Abstract: Motorcyclists remain a disproportionately large group of vulnerable road users, with fatality rates significantly higher than that in other road groups. Additionally, fatal accidents involving motorcyclists have a more slowly decreasing trend in comparison to that of other road users, while the number of this kind of users is growing fast. For all these reasons, there is a need to understand what the key factors leading to fatal accidents are in order to identify the possible measures to minimize the accidents themselves or at least their consequences. This would permit, indeed, to positively impact the road traffic system, leading to the creation of the safest road traffic system possible, as it is the goal of the Sustainable Safety approach. The aim of this study is to dive into the mentioned problem, analyzing fatal motorcycle accidents in Slovenia over a decade, highlighting the key factors contributing to these incidents. By integrating data from four databases, the study evaluated accident trends, infrastructural elements, and rider behavior through a multi-stage analysis. Firstly, data were collected from four national, up-to-date databases that contain information about road accidents themselves, the road infrastructure, additional police data, and media descriptions. After merging this information into one comprehensive database, where each row represents all the data available for one accident, a general analysis of accidents’ trends over the considered 10-year period was developed, considering at first all fatal road accidents, then deepening it to accidents caused by a motorcyclist, and finally to single-vehicle accidents. A statistical analysis followed, aimed at identifying a statistical correlation between the accidents and the factors leading to them. The results of the first accident analysis indicated that excessive speed, incorrect driving direction, and overtaking maneuvers are the primary causes of fatal accidents, especially on non-urban roads preferred by motorcyclists. Single-vehicle accidents frequently involve collisions with roadside objects, including safety barriers and poles, underscoring the need for targeted infrastructural improvements. The following correlation analysis revealed that a total of seven factors were statistically significant: three human factors (age, gender, experience)—which were the ones with the strongest correlations—one infrastructural factor (pavement width), and three factors belonging to external conditions (accident type, cause, and location). Of these, four were positively correlated to the causer, while three, i.e., pavement width, causes, and road location, were negatively correlated. This study provides a foundation for future research on less severe accidents and proactive risk behavior analysis, aiming to improve motorcyclist safety comprehensively.
Keywords: motorcycle safety, fatal accidents, road infrastructure, rider behavior
Published in DKUM: 10.03.2025; Views: 0; Downloads: 11
Full text (5,41 MB)
This document has many files! More...

Abstract: Prometna varnost otrok na prehodih za pešce je pereča tema, saj so otroci kot tudi ostali pešci pogosto ranljivi člen v prometu. Otroci se na prehodih za pešce srečujejo s številnimi tveganji, saj niso dovolj osveščeni oziroma obveščeni o pravilih in nevarnostih v prometu. Diplomsko delo obravnava vedenje in predvsem varnost osnovnošolskih otrok. Osredotočili smo se na osnovnošolske otroke, ki prečkajo nesemaforiziran prehod za pešce. Najprej smo se spoznali s pravilniki in zakoni o tem, kakšni so kriteriji za načrtovanje prehoda za pešce, kako so urejene in opremljene površine okoli šol, kakšna bi naj bila razsvetljava na prehodih za pešce, veliko pozornost pa smo namenili psihičnemu razvoju otroka med 6. in 14. letom. Obravnavani so bili prehodi za pešce v Mestni občini Maribor, ki so nameščeni v okolici osnovnih šol. S pomočjo videoposnetkov smo lažje opazovali dejansko stanje na cestah in prehodih ter analizirali otroke kot pešce ter voznike. Na koncu smo rezultate med seboj primerjali in jih analizirali. Z analizo smo ugotovili, kaj bi bilo potrebno v določenih primerih dodati ali spremeniti in mogoče s tem stanje tudi izboljšati.
Keywords: promet, otroci, prehod za pešce, varnost v prometu
Published in DKUM: 20.02.2025; Views: 0; Downloads: 24
Full text (4,01 MB)

Abstract: Diplomsko delo obravnava prometno varnost osnovnošolcev, s poudarkom na varnosti na poti do šole. V uvodnem delu so opredeljeni problem, cilji raziskave, teze, predpostavke in uporabljene metode raziskovanja. Glavni cilj raziskave je oceniti trenutne razmere prometne varnosti v okolici izbranih osnovnih šol in predlagati izboljšave za večjo varnost otrok. Raziskava se osredotoča na pomen prometne varnosti in vlogo različnih deležnikov, vključno z izobraževalnim sistemom. Obravnavan je tudi vpliv razvoja otroka na njegove varnostne potrebe in opravljena analiza varnosti otrok na poti do šole. V okviru raziskave je izvedena anketa med učenci treh osnovnih šol v Mariboru: OŠ Bojana Ilicha, OŠ Prežihovega Voranca in OŠ Toneta Čufarja. Cilj ankete je ugotoviti percepcijo varnosti med učenci in njihovimi starši ter oceniti obstoječo prometno infrastrukturo v okolici teh šol. Rezultati ankete so pokazali razlike v stopnji zaznane varnosti med različnimi šolami, kar je privedlo do primerjalne analize in oblikovanja predlogov za izboljšanje prometne varnosti. Med glavnimi ugotovitvami sta izpostavljeni potrebi po izboljšanju infrastrukture in večji ozaveščenosti učencev in staršev. Diplomsko delo zaključujemo s sklepom, kjer so povzeti glavni rezultati raziskave in podani konkretni predlogi za izboljšanje varnosti otrok na poti do šole.
Keywords: šolske poti, prometna varnost, varnostni ukrepi, otroci
Published in DKUM: 14.11.2024; Views: 0; Downloads: 24
Full text (3,32 MB)