Abstract :

Autonomous vehicle navigation requires accurate perception of the surrounding environment to ensure safe and efficient movement. This project presents an obstacle detection and avoidance system using the YOLO (You Only Look Once) deep learning algorithm. YOLO enables real-time object detection by identifying obstacles such as vehicles, pedestrians, traffic signs, and road barriers from live video streams. The detected objects are analyzed to estimate distance and position relative to the vehicle. Based on this information, navigation decisions are generated to avoid collisions. The proposed system enhances driving safety by reducing human intervention. Experimental results demonstrate improved detection speed and accuracy in real-time scenarios.