Notice: Sunsetting SVL Simulator. Read more.

David Uhm

Use Case: Deep Learning Model Training with SVL Simulator

We are announcing a new project to show a use case for SVL Simulator with applying a deep learning neural network. The goal of this project is to demonstrate how to collect sensor data using SVL Simulator and train an end-to-end deep learning model that would let a car drive autonomously, following lanes. The network is trained to replicate the human steering behavior while driving and collecting data. During the inference phase, it takes camera images from a frontal camera as input and predicts steering angle commands. This project was inspired by NVIDIA's End-to-End Deep Learning Model for Self-Driving Cars.

Full source code, documentation, and a pre-trained model can be found here: