MICRO-515 / 4 crédits

Enseignant: Floreano Dario

Langue: Anglais


Summary

The course covers theories, methods, and technologies for designing robots and artificial systems inspired by evolution, development, and learning. It shows how robotic models help understand biological systems and includes programming exercises using MuJoCo and gym.

Content

  • Natural and Artificial Evolution
  • Principles of Evolutionary Computation
  • Algorithms: Genetic Algorithms and Evolutionary Strategies
  • Algorithms: Multi-objective optimization (various algorithms, including NSGA-II)
  • Intorduction to neural netwok architectures and learning methods, including reinforcement learning
  • Evolution of Artificial Neural Networks and comparison to Reinforcement Leanring
  • Evolution of Neurocontrollers for mobile robots
  • Morphological Growth and Evolution
  • Evolution of Collective Systems: Competitive and Cooperative Evolution
  • Evolution of bio-hybrid robots

Learning Prerequisites

Important concepts to start the course

Python

Learning Outcomes

By the end of the course, the student must be able to:

  • Apply tate-of-the-art software tools for robot simulation
  • Translate acquired theoretical knowledge in practical implementations during exercise sessions

Teaching methods

Lectures, software exercises, and final report on an evolutionary robotics experiment in simulation.

Expected student activities

Attending lectures, asking critical questions, taking all exercises and completing assignments for the following week, forming groups and performing collaboratively project with evolutionary robotics software, writing report on project results.

Assessment methods

Mini-project report in powerpoint + presentation + written exam

Supervision

Office hours No
Assistants Yes
Forum Yes

Resources

Bibliography

Floreano, D. & Mattiussi, C. (2008) Bioinspired Artificial Intelligence. MIT Press (selected chapters)

Ressources en bibliothèque

Moodle Link

Dans les plans d'études

  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Evolutionary robotics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Evolutionary robotics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Evolutionary robotics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Evolutionary robotics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Evolutionary robotics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel

Semaine de référence

Jeudi, 9h - 11h: Cours BS160

Jeudi, 11h - 13h: Projet, labo, autre BS160

Cours connexes

Résultats de graphsearch.epfl.ch.