Evolutionary Algorithms as Creative Designers in Robotics and Engineering

Date/Time
Date(s) - 24/06/2020
4:00 pm - 5:00 pm


You are invited to join this online seminar hosted by the Nature-Inspired Intelligent Systems group  from international evolutionary robotics research Dr Jean-Baptiste Mouret.

Abstract

Evolutionary algorithms are traditionally viewed as effective gradient-free optimization algorithms. Nevertheless, this optimization-centric view “hides” one of the most fascinating aspects of natural evolution: its creativity. In this talk, I will introduce our work on niche-based “quality diversity” algorithms, which is a new family of evolutionary algorithms designed to find a large, diverse set of high-performing solutions (instead of a single, optimal solution). I will illustrate how these algorithms are more creative designers than traditional evolutionary algorithms using our experiments in robotics (legged locomotion) and in aerodynamic design (velomobiles, airfoils).

Biography:

Dr. Jean-Baptiste Mouret is a senior researcher (“Directeur de recherche”) at Inria, the French research institute dedicated to computer science and mathematics. He is currently the principal investigator of an ERC grant (ResiBots – Robots with animal-like resilience, 2015-2020). From 2009 to 2015, he was an assistant professor (“maître de conférences”) at the Pierre and Marie Curie University (Paris, France).  Overall, J.-B. Mouret conducts researches that intertwine machine learning and evolutionary computation to make robots that can adapt in a few minutes. His work was recently featured on the cover of Nature (“Robots that adapt like animals”, Cully et al., 2015) and it received several national and international scientific awards, including the “Prix La Recherche 2016” and the “Distinguished Young Investigator in Artificial Life 2017

The seminar will take place via Webex and you can register to attend here. Details of the link will be sent to registered participants on the day of the seminar.

This entry was posted in .