This course introduces the technologies that make autonomous driving possible. Modern self-driving vehicles rely on multi-sensor fusion of cameras, LiDAR, radar, GPS, and IMUs to ensure robust perception and eliminate blind spots. AI and machine learning play a central role across the stack: object detection (e.g., Single-Shot Detector(SSD), YOLO, multi-object tracking (e.g., DeepSORT), semantic segmentation of drivable vs. non-drivable space, trajectory prediction, and behavior modeling of surrounding vehicles. These algorithms enable the vehicle to anticipate how other road users may respond to its maneuvers and to plan safe navigation strategies. In addition, emerging Large Language Models (LLMs) are being explored to enhance reasoning and explainability, providing natural-language feedback to passengers and interpreting traffic context in unstructured environments.

To pass the course, students are required to achieve at least 30% in course work and 30% in the examination. Also, 75% laboratory attendance rate must be obtained. 

#may include homework, tutorial exercise, project/mini-project, presentation