Merging pruning and neuroevolution: towards robust and efficient controllers for modular soft robots

G Nadizar, E Medvet, HH Ramstad… - The Knowledge …, 2022‏ - cambridge.org
Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their
structure is often complex, with many neurons and connections, especially when the robots …

JGEA: a modular java framework for experimenting with evolutionary computation

E Medvet, G Nadizar, L Manzoni - Proceedings of the genetic and …, 2022‏ - dl.acm.org
We present the Java General Evolutionary Algorithm (JGEA) framework, a modular Java
framework for experimenting with Evolutionary Computation (EC). We designed JGEA to be …

Evolving Hebbian learning rules in voxel-based soft robots

A Ferigo, G Iacca, E Medvet… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
According to Hebbian theory, synaptic plasticity is the ability of neurons to strengthen or
weaken the synapses among them in response to stimuli. It plays a fundamental role in the …

Factors impacting diversity and effectiveness of evolved modular robots

F Pigozzi, E Medvet, A Bartoli, M Rochelli - ACM Transactions on …, 2023‏ - dl.acm.org
In many natural environments, different forms of living organisms successfully accomplish
the same task while being diverse in shape and behavior. This biodiversity is what made life …

Collective control of modular soft robots via embodied Spiking Neural Cellular Automata

G Nadizar, E Medvet, S Nichele… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Voxel-based Soft Robots (VSRs) are a form of modular soft robots, composed of several
deformable cubes, ie, voxels. Each VSR is thus an ensemble of simple agents, namely the …

On the schedule for morphological development of evolved modular soft robots

G Nadizar, E Medvet, K Miras - … on genetic programming (Part of EvoStar), 2022‏ - Springer
Abstract Development is fundamental for living beings. As robots are often designed to
mimic biological organisms, development is believed to be crucial for achieving successful …

On the impact of body material properties on neuroevolution for embodied agents: The case of voxel-based soft robots

E Medvet, G Nadizar, F Pigozzi - Proceedings of the genetic and …, 2022‏ - dl.acm.org
Artificial agents required to perform non-trivial tasks are commonly controlled with Artificial
Neural Networks (ANNs), which need to be carefully fine-tuned. This is where ANN …

Optimizing the sensory apparatus of voxel-based soft robots through evolution and babbling

A Ferigo, E Medvet, G Iacca - SN Computer Science, 2022‏ - Springer
The behavior of biological and artificial agents strongly depends, in general, on the data
acquired through sensors while interacting with the environment. The sensory apparatus …

Self-building neural networks

A Ferigo, G Iacca - Proceedings of the Companion Conference on …, 2023‏ - dl.acm.org
During the first part of life, the brain develops while it learns through a process called
synaptogenesis. The neurons, growing and interacting with each other, create synapses …

On the effects of collaborators selection and aggregation in cooperative coevolution: An experimental analysis

G Nadizar, E Medvet - … Conference on Genetic Programming (Part of …, 2023‏ - Springer
Cooperative Coevolution is a way to solve complex optimization problems by dividing them
in smaller, simpler sub-problems. Those sub-problems are then tackled concurrently by …