Simulation of self driving cars

In the context of courses at Polytech Tours and in connection with the LIFAT and RFAI researches, Romain RAVEAUX proposes to work on simulation of self driving cars, which combines algorithmic and prediction methods. Here is a video that illustrates this work.

The goal consists in making cars autonomous in a 3D simulator. The car has a constant speed and only the rotation of the steering wheels allows the car to stay on the track. The simulation of Self Driving Car is based on Thibault Neveu’s tutorial. However, the prediction model used has been adapted to fit the objective of an academic course. Especially, students have to develop from A to Z the learning algorithm (Stochastic Gradient Descent) and the prediction method (linear regression model).