YOLOP is a real-time multi-task neural network published in Machine Intelligence Research (2022) that jointly handles three perception tasks for autonomous vehicles: object detection, drivable area segmentation, and lane detection. Built on the YOLO architecture, it is designed to run efficiently on embedded devices like Jetson TX2 while achieving state-of-the-art performance on the BDD100K dataset. The work demonstrates that multi-task learning can reduce inference time and computational costs compared to separate models for each task.