Learn More
We propose and evaluate a novel approach called On-line Distributed NeuroEvolution of Augmenting Topologies (odNEAT). odNEAT is a completely distributed evolutionary algorithm for online learning in groups of embodied agents such as robots. While previous approaches to online distributed evolution of neural controllers have been limited to the optimisation(More)
We propose and evaluate a novel approach to the online synthesis of neural controllers for autonomous robots. We combine online evolution of weights and network topology with neuromodulated learning. We demonstrate our method through a series of simulation-based experiments in which an e-puck-like robot must perform a dynamic concurrent foraging task. In(More)
One important advantage of logic programming is that it allows the implicit exploitation of parallelism. Towards this goal, we suggest that or-parallelism can be eeciently exploited in tabling systems and propose two alternative approaches, Or-Parallelism within Tabling (OPT) and Tabling within Or-Parallelism (TOP). We then focus on OPT approach where(More)
Several solutions have been proposed to provide authentication and safe encryption for Wifi networks in order to overcome the limitation of WEP based security. This document describes a solution based on IPSec VPNs with client and server certificates. The key advantages of this solution is its ability to provide roaming between institutions without having(More)
One of the long-term goals in evolutionary robotics is to be able to automatically synthesize controllers for real autonomous robots based only on a task specification. While a number of studies have shown the applicability of evolutionary robotics techniques for the synthesis of behavioral control, researchers have consistently been faced with a number of(More)
Online evolution gives robots the capacity to learn new tasks and to adapt to changing environmental conditions during task execution. Previous approaches to online evolution of neural controllers are typically limited to the optimisation of weights in networks with a prespecified, fixed topology. In this article, we propose a novel approach to online(More)
The authors propose and evaluate a novel approach to the online synthesis of neural controllers for autonomous robots. The authors combine online evolution of weights and network topology with neuromodulated learning. The authors demonstrate our method through a series of simulation-based experiments in which an e-puck-like robot must perform a dynamic(More)
Neuroevolution, the optimisation of artificial neural networks (ANNs) through evolutionary computation, is a promising approach to the synthesis of controllers for autonomous agents. Traditional neuroevolution approaches employ direct encodings, which are limited in their ability to evolve complex or large-scale controllers because each ANN parameter is(More)
In this paper, we introduce a novel approach to the online evolution of robotic controllers. We propose accelerating and scaling on-line evolution to more complex tasks by giving the evolutionary process direct access to behavioural building blocks prespecified in the neural architecture as macro-neurons. During task execution, both the structure and the(More)