Autonomous Vehicles - Jupyter Notebooks
In the following notebooks, we learn various algorithms and tools used for autonomous driving.
Notebook 7.1 - Introduction to Trajectory Optimisation
In this notebook, we learn to use another optimisation tool GEKKO
to carry out trajectory optimisation.
Notebook 7.2 - Rapidly Exploring Random Trees
Here, we implement the rapidly exploring random trees (RRT) algorithm for search space exploration.
Notebook 7.3 - Tutorial Questions
We provide the solutions for Tutorial 7 in this notebook.
Notebook 7.4 - Segmentation for Lane Detection
Using machine learning and computer vision, we learn about image segmentation to detect lanes.
Notebook 7.5 - Feature Extraction Lane Markings
In this notebook, we use classical computer vision without relying on machine learning to detect lanes.
Notebook 7.6 - Pedestrian Detection
Not only do we learn to detect lanes but also pedestrians in this notebook.
We encourage you to have a look at the notebooks and understand the basics of algorithms used in autonomous vehicles.
You can download all notebooks for Session 7 along with the data used in the notebooks from the link below.