Teaching‎ > ‎

Evolutionary Robotics (PhD) 2020

Program

The aim of the course is to briefly explore techniques and principles of Evolutionary Computation and, by means of a few interesting and relevant examples, see how they can be applied to automatically design the body and the mind of autonomous machines.
  • Foundations of Evolutionary Computation (EC).
    • High-level working scheme of an Evolutionary Algorithm (EA); terminology.
    • Generational model; selection criteria; exploration/exploitation trade-off; genetic operators with examples; fitness function; multi-objective optimization and Pareto dominance; debugging of an evolutionary search; EA issues (diversity, variational inheritance, expressiveness); fitness landscape.
    • Examples of common EAs: GA, GP, GE.
  • Applications to robotics

Requirements

Basics of statistics: summary measures of variable distribution (mean, variance, quantiles).
Basics of linear algebra.
Basics of programming and data structures: algorithm, loops, parallel execution.

Timetable and course calendar

The course will start on June 15th, 2020.
Lectures will be held online.

Lezioni

Suggested textbooks

  • Kenneth A. De Jong. Evolutionary computation: a unified approach. MIT press, 2006.

Course material

The course material (slides) is attached at the bottom of this page.
The full pack of slides might be updated during the course.
Ċ
Eric Medvet,
Jun 14, 2020, 11:45 PM