Self-Driving Cars Using Nvidia PilotNet
Last updated
Was this helpful?
Last updated
Was this helpful?
Computer Vision is a key technology for building algorithms to enable self-driving cars. We've used PerceptiLabs to recreate Nvidia's end-to-end deep learning approach for mapping raw pixels using images captured from front-facing cameras mounted on a car. Each image has a corresponding steering angle associated with it that tells the position of the car's steering for that frame. For this model, we have used to collect the dataset:
The car captures three pictures – left, center, right – for every single frame using the cameras that are fitted on the front of the car: ​
Each frame has its own steering angle value that will be used as labels.
The model is based around the PilotNet model which is composed of nine layers:
Three Dense layers.
You can also watch how to build and train this model in the following video:
Five Convolutional Layers. These layers, which form a (CNN), play a big part in computer vision, namely in the training of features using images as input.
An output layer (implemented as a fully-connected component in PerceptiLabs).
The PilotNet model that we recreated in PerceptiLabs, along with sample data, is available for you to try on . The final model looks as follows:
The data was preprocessed by normalizing it with Google which involved dividing the entire image matrix by 255 to bring all the values on the same scale (i.e., 0 to 1). We've also made some code modifications in our model's components as described in the README.md file on . ​