Simulating Surrounding Human Drivers With Cognitive Models in Autonomous Vehicles Testing Scenarios
שמור ב:
| הוצא לאור ב: | ProQuest Dissertations and Theses (2025) |
|---|---|
| מחבר ראשי: | |
| יצא לאור: |
ProQuest Dissertations & Theses
|
| נושאים: | |
| גישה מקוונת: | Citation/Abstract Full Text - PDF |
| תגים: |
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3184230495 | ||
| 003 | UK-CbPIL | ||
| 020 | |a 9798310159792 | ||
| 035 | |a 3184230495 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 66569 |2 nlm | ||
| 100 | 1 | |a Jawad, Abdul | |
| 245 | 1 | |a Simulating Surrounding Human Drivers With Cognitive Models in Autonomous Vehicles Testing Scenarios | |
| 260 | |b ProQuest Dissertations & Theses |c 2025 | ||
| 513 | |a Dissertation/Thesis | ||
| 520 | 3 | |a Simulation-based testing has become essential for validating autonomous vehicles (AVs) due to the impracticality of real-world testing at scale. However, current simulations often lack the complexity and diversity of real-world human driving behaviors needed to sufficiently mimic reality. In particular, the current modeling approach fails to account for cognitive and perceptual limitations that contribute to accidents. This limitation hinders the effectiveness of simulations in preparing AVs for real-world interactions with human drivers. This dissertation addresses these gaps by integrating insights from cognitive science, psychology, and computer science to develop driver behavior models that simulate human cognitive and perceptual constraints. We identify critical human factors, such as information processing delays and limited fields of vision, which significantly impact accident-related driving behavior. To replicate behavioral stochasticity and diversity, we propose three driver models: a behavior tree-based model for integrating multiple driving tasks within a consistent framework, a cognitive architecture-based model that incorporates human limitations leading to critical scenarios, and a hybrid model that combines reinforcement learning with cognitive modeling to generate rare and critical accident scenarios. By leveraging these models, we enhance the realism and variability of simulated traffic scenarios, creating rare and critical events that better challenge AV systems. This work aims to improve simulation-based testing frameworks for AVs and advances the field of simulation-based testing by enabling the generation of diverse and critical scenarios, ultimately supporting the safer deployment of autonomous vehicles. | |
| 653 | |a Computer science | ||
| 653 | |a Cognitive psychology | ||
| 653 | |a Computer engineering | ||
| 653 | |a Artificial intelligence | ||
| 773 | 0 | |t ProQuest Dissertations and Theses |g (2025) | |
| 786 | 0 | |d ProQuest |t ProQuest Dissertations & Theses Global | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3184230495/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3184230495/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |