<![CDATA[The advancement of automation technology, particularly in autonomous vehicles, has rapidly progressed with the integration of machine learning. However, these systems still face challenges in environments with dense traffic and dynamic conditions, making safety a primary concern. Traffic accident data indicate that the implementation of autonomous vehicles remains far from optimal, especially under extreme conditions such as severe weather and unpredictable traffic congestion. This study aims to develop an autonomous vehicle system model that can operate not only under normal conditions but also adapt to extreme situations. The model is developed using the CARLA Simulator, which enables testing in various realistic environmental scenarios. Simulations involving severe weather and high traffic density are conducted to evaluate the model’s resilience and responsiveness across different scenarios. The results show that the developed model enhances driving safety under extreme conditions with high effectiveness in obstacle avoidance and dynamic decision-making. Thus, this approach is expected to contribute to the development of more adaptive and safer autonomous vehicles for real-world applications]]>
Copyrights © 2025
