• Publications
  • Influence
Evolutionary fuzzy system for architecture control in a constructive neural network
TLDR
A classifier system generates Takagi-Sugeno fuzzy rules and controls the architecture of a constructive neural network for autonomous navigation. Expand
  • 6
  • 3
Generative Modeling of Autonomous Robots and their Environments using Reservoir Computing
TLDR
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
  • 41
  • 1
  • PDF
Event detection and localization for small mobile robots using reservoir computing
TLDR
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
  • 78
  • PDF
On Learning Navigation Behaviors for Small Mobile Robots With Reservoir Computing Architectures
TLDR
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
  • 42
  • PDF
Echo State Networks for data-driven downhole pressure estimation in gas-lift oil wells
TLDR
This paper aims at designing data-driven soft-sensors for downhole pressure estimation in gas-lift oil wells. Expand
  • 27
  • PDF
Event Detection and Localization in Mobile Robot Navigation Using Reservoir Computing
TLDR
Reservoir Computing (RC) uses a randomly created recurrent neural network where only a linear readout layer is trained. Expand
  • 25
  • PDF
Mobile robot control in the road sign problem using Reservoir Computing networks
TLDR
We tackle the road sign problem with reservoir computing (RC) networks. Expand
  • 24
  • PDF
Modular reservoir computing networks for imitation learning of multiple robot behaviors
TLDR
In this work, we use Reservoir Computing (RC) for learning robot behaviors by demonstration. Expand
  • 13
  • PDF
Modular Neural Network and Classical Reinforcement Learning for Autonomous Robot Navigation: Inhibiting Undesirable Behaviors
TLDR
An autonomous navigation system for mobile robot navigation is proposed based on two intelligent computation techniques: neural networks and classical reinforcement learning. Expand
  • 15
  • PDF