The program was developed by Udacity in partnership with Mercedes-Benz, NVIDIA, Otto, DiDi, BMW, McLaren and NextEv.
Lesson 1 - Deep Learning and Computer Vision
- Project 2: Traffic Sign Classifier (Deep Learning) - Use tensorflow to train a convolution neural network capable of detecting road side traffic signs.
- Project 3: Behavioural Cloning (Deep Learning): Train a car to drive in a 3D simulator using a deep neural network.
- Project 1: Finding Lane Lines (Intro to Computer Vision): Introductory project which used basic computer vision techniques like canny edge and hough transforms to detect lane lines
- Project 4: Advanced Lane Lines (Computer Vision): Use of image thresholding, warping and fitting lanes lines to develop a more robust method of detecting lane lines on a road
- Project 5: Vehicle Detection (Computer Vision): Use of HOG and SVM to detect vehicles on a road
Lesson 2 - Sensor Fusion, Localisation and Control
- Sensor Fusion
- Combining lidar and radar data to track objects in the environment using Kalman filters.
- Localisation
- Locate a car relative to the world (Align a car and sensors to the map).
- Use particle filters to localise the vehicle.
- Control
- Fundamental concepts of robotic control.
- Build algorithms to steer car and wheels so as to meet an objective.
Path Planning: Finding a sequence of steps in a maze (navigating cities, parking lots) Put your code in a self-driving car