​This work involved four capstone projects in the area of self-driving cars. Topics such as 
 wheeled-robot mathematical modelling through dynamical modelling (tire model), lateral and 
 longitudinal control, state estimation with Kalman filters, visual perception and motion planning 
 were addressed. Most of the projects were tested in the Carla Simulator to assess performance. A 
 description of the projects developed are presented below.

    * Control of a car-like robot through a longitudinal and lateral controller. The longitudinal 
    controller was implemented with a PID and the lateral controller was a cross-track error 
    controller. 
    
    * Implementation of an error state extended Kalman Filter for the estimation of the trajectory 
    of a vehicle. The filter fused information from a GNSS and IMU alongside the dynamic model of 
    the vehicle to produce an accurate estimation of its trajectory on the space.
    
    * Robotics perception stack which detected the drivable space of the vehicle through image 
    segmentation. Canny edge detector was used to detect the lines of the road and a depth 
    representation of the scene was employed to estimate the distance-to-objects in the road and 
    avoid collision using only image-based methods.
    
    * Implemented a navigation stack in the Carla simulator with the use of grid world 
    representations  and state machines for a simple navigation strategy.