This section will focus on a very useful technique called behavioral cloning. This chapter is relatively intense and will combine all the previous techniques we have dealt with in this book, such as deep learning, feature extraction from images, CNNs, and continuous regression.
We are going to follow these steps:
- Download an open source SDC simulator by Udacity.
- Collect the training data by driving the car in manual mode in the simulator. The training data consists of images from the surrounding environment of the car and the steering angles.
- Clean the collected dataset using various OpenCV techniques.
- Train a convolution neural network model.
- Evaluate the model in Autonomous mode of the Udacity simulator.
This project isn't easy as it requires complex deep learning techniques and image preprocessing techniques. For this reason, I have structured this book so that you have all the necessary skills to complete...
