Prerequisites

• Lecture: "Natural and Artificial Evolution"
• Lecture: "Biological and Artificial Neural Networks"
• Lecture: "Evolution of Artificial Neural Networks"
• Lecture: "Evolutionary Robotics"
• C-programming

Overview

The goal of this laboratory is to evolve a neural controller for an e-puck robot which has to navigate in an environment as fast as possible while avoiding obstacles (for example, walls). Evolution is done in the Webots™ simulator from Cyberbotics and tests of the best evolved controller can be done in simulation or on the real e-puck.

Webots can be downloaded here.

The source code for the exercise can be downloaded here.

A detailed description of the exercise can downloaded here.