Learning robot-environment interaction using echo state networks

Authors:
Mohamed Oubbati;Bahram Kord;Günther Palm
Affiliations:
Institute of Neural Information Processing, University of Ulm, Ulm, Germany;Institute of Neural Information Processing, University of Ulm, Ulm, Germany;Institute of Neural Information Processing, University of Ulm, Ulm, Germany
Venue:
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Year:
2010

Citing 6
Cited 0

Original Contribution: Approximation of dynamical systems by continuous time recurrent neural networks

Neural Networks
How the Body Shapes the Way We Think: A New View of Intelligence (Bradford Books)

How the Body Shapes the Way We Think: A New View of Intelligence (Bradford Books)
A dynamical systems perspective on agent-environment interaction

Artificial Intelligence
A neural framework for adaptive robot control

Neural Computing and Applications
Velocity control of an omnidirectional robocup player with recurrent neural networks

RoboCup 2005
On the dynamics of robot exploration learning

Cognitive Systems Research

Quantified Score

Hi-index	0.01

Visualization

Abstract

Learning robot-environment interaction with echo state networks (ESNs) is presented in this paper. ESNs are asked to bootstrap a robot's control policy from human teacher's demonstrations on the robot learner, and to generalize beyond the demonstration dataset. Benefits and problems involved in some navigation tasks are discussed, supported by real-world experiments with a small mobile robot.