This project intends to create a better object identification system by combining YOLO (You Only Look Once) with simulated LiDAR data to improve real-time perception in sectors such as autonomous driving, surveillance, and robotics. By combining YOLO’s quick picture recognition with LiDAR’s depth-sensing capabilities, the system aims to overcome the limitations of solely visual techniques, particularly in low-visibility or complicated environments. This integration improves the system’s ability to identify, locate, and track objects in tough situations like fog, darkness, or clutter. The project entails creating synthetic LiDAR data, integrating it with the YOLO framework, and evaluating the model in various circumstances. The predicted outcome is a dependable detection system with better accuracy and flexibility when compared to traditional approaches.