NVIDIA provides the DRIVE platform as an in-car AI supercomputer for autonomous driving. We envision numerous deep neural networks (DNNs) to be running simultaneously, driving the vehicle autonomously. We use several types of DNNs to support autonomous driving. One is a detection and classification network used not only for object detection (pedestrians, cars, trucks, motorcycles, bicycles, signs, lampposts, and even animals), but also for lane marking detection. Another example is a segmentation network which is useful to determine the free space around the vehicle that is available for driving, driving bounds (typically bounded curbs and medians), and blocking objects such as vehicles and pedestrians. A third example is end-to-end networks that mimic learned driving behavior. This can be used as a basic path planner to drive the vehicle in normal or typical circumstances. These networks working together to enable the vehicle’s artificial intelligence to drive the vehicle, while keeping the driver, its occupants and pedestrians nearby safe.