Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
4 results
Search Results
Item Restricted Employing communication for building learned trust in autonomous vehicles, A qualitative pilot study.(Politecnico Di Milano, 2024) Alharbi, Eilaf; Borghetti, Fabio; Bianchini, BeatriceAs autonomous vehicles (AVs) advance towards full automation, trust between passengers and the automated systems becomes a critical factor to their existence. This research presents a pilot study on developing a design framework to help build and maintain a dynamic learned trust during interactions with fully autonomous vehicles by exploring various information types, structures, and communication modalities. The study draws on insights from previous research, semi-structured interviews with 6 users and 3 experts to identify key design elements that influence trust. Key findings suggest that minimizing driving-related information and instead focusing on journey-related details can prevent passengers from feeling the need to monitor the vehicle’s decisions, thereby fostering trust. The concept of "Information on Demand" emerged as a valuable approach to balance transparency and personalization, allowing passengers to request specific information whenever is needed. Additionally, "technical explanations" were identified as effective in restoring trust when errors occur, emphasizing the importance of timely and clear communication. The research also highlighted the limited impact of non-driving tasks, such as entertainment on trust. Furthermore, communication modalities should be tailored to the type of information being conveyed, taking into account various risks and the passengers’ ability to process different communication methods. This pilot study’s results lay the foundations for a larger scale study aiming to examine various factors that influence the dynamic learned trust during the interaction with the automated system in the vehicles.5 0Item Restricted Advanced Autonomous Vehicles Analytics for Predicting Navigation Performance(University of Pittsburgh, 2024) Alharbi, Mohammed Abdullah H; Karimi, Hassan AliAutonomous Vehicles (AVs) stand as a monumental leap in modern transportation technology, offering the potential to enhance road safety and optimize transportation efficiency. However, their broad adoption is hindered by uncertainties associated with their sensors that allow for perceiving, interpreting, and interacting with their surroundings. Sensor uncertainties (SUs) arise from various sources, including sensor noise, varying environmental conditions, and inherent limitations in sensor design. SUs undermine the accuracy and reliability of AV navigation, posing substantial risks to AV performance and, by extension, to passenger safety. Considering the high stakes involved, including human lives, traffic flow optimization, and the structural integrity of transportation infrastructures, it is crucial for AVs to operate with minimal SUs. As driving on roads is dynamic with unpredictable elements, like sudden weather changes, AVs must be designed to handle both planned and unforeseen changes with unwavering precision. Failure to account for such uncertainties can cause unsafe driving and culminate in catastrophic outcomes, thereby deteriorating public confidence in autonomous driving technologies. Common approaches to identifying and handling SUs in AVs involve data fusion and machine learning techniques. Despite their acceptable performance, these techniques are constrained by several critical limitations that hinder their applicability in complex real-world scenarios. For instance, conventional sensor fusion techniques often make overly simplistic assumptions, such as treating uncertainties as independent and normally distributed, which fail to capture the complex interdependencies and nonlinearities present in real sensor data. This simplification leads to suboptimal solutions, especially in challenging environments. Additionally, these techniques lack adaptive mechanisms to respond to changing environmental conditions, limiting their robustness. On the other hand, machine learning techniques, though capable of processing large volumes of data and uncovering hidden patterns, typically suffer from a lack of interpretability, often referred to as the “black-box” problem. This opacity inhibits a comprehensive understanding of the decision-making processes, complicating efforts to ensure transparency and accountability in AV operations. Furthermore, the extant literature is void in furnishing robust evaluative metrics and tools that could facilitate the systematic analysis of AV sensor performance, both before and after occurrence of incidents. This thesis addresses these critical gaps by introducing an advanced AV analytics (AVA) framework and making the following contributions. Firstly, it introduces a novel ontology that represents and formalizes major concepts related to SUs in AV navigation. This ontology serves as a conceptual foundation for automated reasoning about navigation safety. Secondly, the thesis formulates a set of tailored performance metrics that provides a more nuanced evaluation of sensor reliability and accuracy under varying operational conditions. Thirdly, the AVA framework incorporates predictive models that not only quantify AV navigation sensor performance but also identify factors contributing to SUs. These models are unique in their multidimensional scope, encompassing environmental variables, and sensor specifications, and are of two types: online and offline. Online models focus on real-time evaluation of uncertainties for immediate decision-making, while offline models, also called forensic models, allow to analyze factors behind any unexpected behaviors. Finally, the thesis introduces a global path planner that integrates AVA’s analytical outputs to optimize AV route planning. Unlike commonly used route optimization criteria, such as shortest or fastest routes, this path planner incorporates sensor performance to identify safest routes by avoiding high-risk areas or conditions that could exacerbate SUs. These contributions are thoroughly validated using simulated and real data. The outcomes of the proposed research will help develop AV navigation solutions that are reliable and safe.19 0Item Restricted Predicting Pedestrian Crossing Intention(Saudi Digital Library, 2024) Alofi, Afnan; Trivedi, MohanAutonomous vehicles face significant challenges in understanding pedestrian behavior, particularly in urban environments. The system must recognize pedestrians’ intentions and anticipate their actions to achieve intelligent driving. This paper focuses on predicting pedestrian crossings, aiming to enable oncoming vehicles to react in a timely manner. We investigate the effectiveness of various input modalities for pedestrian crossing prediction, including human poses, bounding boxes and ego vehicle speed features. We propose a novel lightweight architec- ture based on LSTM and attention to accurately identifying crossing pedestrians. Our methods evaluated on two widely used public datasets for pedestrian behavior, PIE and JAAD datasets, and our algorithm achieved a state-of-the-art performance in both datasets34 0Item Restricted ENHANCED NET VALENCE MODEL FOR ADOPTION OF AUTONOMOUS VEHICLES AMONG FEMALE NOVICE DRIVERS IN SAUDI ARABIA(Saudi Digital Library., 2023-04-01) Alshaafee, Areej Ahmad Ayed; IAHAD, NOORMINSHAH A.Autonomous Vehicles-Level4 (AVs) are vehicles which can drive themselves from point A to point B, without the need of any interaction from the driver because of the ability to sense the surroundings and to detect the objects and environment around. In 2018, Saudi females can finally drive by themselves after the ban was lifted. Since then, the kingdom is facing a big problem of female novice drivers from different ages which might make the kingdom such a risky place to drive. Therefore, AVs-Level4 would help novice drivers to overcome their fear of driving, decrease accidents and increase drive safety. Based on the literature, previous studies in pre-adoption of AVs focused narrowly on those who already have enough driving experience and already holding a valid driving license. Research on the pre-adoption of AVs-Level4 by novice drivers was still not well explored. Moreover, none of the previous studies had used Net Valence Model (NVM) for AVs pre-adoption to understand the benefits/risks surrounding the pre-adoption. Realizing this gap, this study aimed to propose an enhanced pre-adoption model for AVs by using NVM to identify the benefits/risks factors that influence the pre-adoption of AVs by novice drivers. This study extended NVM by adding three factors which are social influence, personal innovativeness, and alternatives attractiveness. The theoretical contribution of this study offered a theoretical model for measuring the intention to adopt AVs-Level4 by novice drivers. A survey method was applied using the purposive sampling technique. Data were collected from 1400 participants Saudi women novice drivers who had prior experience in driving AVs-Level4 at least once. Data analysis was performed using SmartPLS Version 3. The results show that individuals tend to ignore the potential risks and focus more on potential benefits. Performance expectancy, enjoyment, and effort expectancy were found to be positively related to perceived benefits. On the other side, financial and time risks were found to be positively related to perceived risks. Perceived risks as a construct did not directly influence the intention to adopt AVs-Level4 which means none of the five types of risks was directly influencing the pre-adoption. Among the additional factors for NVM, which were social influence, personal innovativeness, and alternatives attractiveness, this study found all three factors significantly influenced the pre-adoption. In addition, according to the results of Importance-Performance Matrix Analysis, social influence was found as the second most important factor toward the pre-adoption of AVs. Personal innovativeness and alternatives are the third and the fifth most important factor respectively toward the pre-adoption of AVs. Finally, the enhanced NVM model would help AVs-Level4 developers to identify the most critical factor influencing novice drivers’ behavioral intention to adopt AVs-Level4 from the novice drivers’ perspectives.56 0