Eric A. Antonelo

A classifier system generates Takagi-Sugeno fuzzy rules and controls the architecture of a constructive neural network for autonomous navigation. Expand

We propose the use of Recurrent Neural Networks (RNN) networks for learning robot controllers by example, performing efficient and robust robot localization, and constructing implicit environment maps. Expand

Reservoir Computing (RC) techniques use a fixed (usually randomly created) recurrent neural network, or more generally any dynamic system, which operates at the edge of stability, where only a linear static readout output layer is trained by standard linear regression methods. Expand

This paper proposes a general reservoir computing (RC) learning framework that can be used to learn navigation behaviors for mobile robots in simple and complex unknown partially observable environments. Expand

This paper aims at designing data-driven soft-sensors for downhole pressure estimation in gas-lift oil wells. Expand

Reservoir Computing (RC) uses a randomly created recurrent neural network where only a linear readout layer is trained. Expand

We tackle the road sign problem with reservoir computing (RC) networks. Expand

In this work, we use Reservoir Computing (RC) for learning robot behaviors by demonstration. Expand

An autonomous navigation system for mobile robot navigation is proposed based on two intelligent computation techniques: neural networks and classical reinforcement learning. Expand