Welcome to Genetic Navigation’s documentation!

The Genetic Navigation uses a Genetic Algorithm (GA) to learn a controller for a wheeled mobile robot in order to successfully navigate in an environment. The objective is for the robot to reach a goal location while avoiding collisions with obstacles.

For more information on Genetic Algorithms, please visit the Genetic Algorithms (GA) section.

This algorithm utilizes four custom environments, where each environment consists of a goal position (indicated by the green circle), a set of obstacles, and the list of robots that are candidate solutions.

environments

The custom environments

These are the results for each environment after a few generations:

Environment 1

Environment 1

Environment 2

Environment 2

Environment 3

Environment 3

A solution that enables the robot to navigate to the goal while avoiding collisions is always found.

Check out the Implementation Details section for further information and the Installation section for instructions on how to use Genetic Navigation.