Márcio Lobo Netto

Learn More
This paper addresses the problem of cognitive character animation. We propose the use of finite state machines for the behavioral control of characters. Our approach lays on the idea that the cognitive character arises from the evolutionary computation embedded in the artificial life simulation, which in our case is implemented by the finite state machine.(More)
Neuroevolution comprehends the class of methods responsible for evolving neural network topologies and weights by means of evolutionary algorithms. Despite their good performance in several control tasks, most of these methods use variations of simple sigmoidal neurons. Recent investigations have shown the potential applicability of more realistic neuron(More)
Information can be encoded in spiking neural network (SNN) by precise spike-time relations. This hypothesis can explain cell assembly formation, such as polychronous group (PNG), a notion created to explain how groups of neurons fire time-locked to each other, not necessarily synchronously. In this paper we present a set of PNGs capable of retaining(More)
This paper reports some of the results of the WOXBOT / ARENA project on artificial life. This project to build virtual worlds was set initially aimed at the graphic simulation of an arena where WoxBots, small mobile robots, can perform requested tasks while behaving according to their own motivation and reasoning. Each robot is an intelligent agent that(More)
—Agent concepts are natural to describe intelligent and adaptive systems in a distributed and collaborative scenario. In this paper we outline the different aspects we have considered in order to build a tool for supporting developers to handle the complexity they are faced to when designing smart environments. Such tool uses agent-based technologies, and(More)