Evolutionary Computing Research Project

Evolutionary Robotics

A topology and parameter evolving universal learning network.

Python API with evolutionary computation and reinforcement learning algorithms for Khepera simulation engine

A universal supervisor controller and ER suite for Webots that can be adapted to any wheeled robot morphology with ease. The project is also setup to allow for easy Reinforcement Learning experimentation with some select algorithms (CMA-ES, Novlty Search, MAP-Elites) and neural networks (fixed and recurrent).

This repository hosts the code used in the paper "On the Impact of Body Material Properties on Neuroevolution for Embodied Agents: the Case of Voxel-based Soft Robots"

This repository hosts the code used in the paper "Collective control of modular soft robots via embodied Spiking Neural Cellular Automata"

This repository hosts the code used in the paper "On the Schedule for Morphological Development of Evolved Modular Soft Robots"

A lightweight, generic C++11 framework for evolutionary computation

Repository replicating the design- and behaviour-adaptation algorithm using reinforcement learning algorithm presented in the paper " Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning"

Lightweight simulator of a roomba-like robot

This is the official repository for the GECCO (Genetic and Evolutionary Computation Conference, 2022) paper "A Comparative Analysis on Genome Pleiotropy for Evolved Soft Robots". This repository hosts all the code necessary to replicate the experiments. This work was carried out at Ghent University IDLab-AIRO.

This repository hosts the code used in the paper "An Experimental Comparison of Evolved Neural Network Models for Controlling Simulated Modular Soft Robots".

This is the official repository for the ACM TELO paper "Factors impacting diversity and effectiveness of evolved modular robots"

Repository containing the projects of the EPFL course "Evolutionary robotics".

A modified benchmark for designing and controlling 2D Voxel-based Soft Robots

This study uses evolutionary collective robotics as an experimental platform to investigate the impact of increasing task environment complexity (collective behavior task difficulty) on the evolution and benefits of morphological and behavioral diversity in robotic swarms.

Repository containing results and the algorithms described in the article: https://periodicos.ufsm.br/coming/article/view/85256