A Recurrent Neural Network for Robotic Sensory-based Search

Authors:
Darlo Maravall;Javier Lope;Miguel Ángel Patricio
Affiliations:
Department of Artificial Intelligence Faculty of Computer Science, Universidad Politëcnica de Madrid, Madrid, Spain 28660;Department of Artificial Intelligence Faculty of Computer Science, Universidad Politëcnica de Madrid, Madrid, Spain 28660;Departamento de Informatica, Universidad Carlos III de Madrid, Spain
Venue:
IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
Year:
2009

Citing 4
Cited 0

Situated Cognition: On Human Knowledge and Computer Representations

Situated Cognition: On Human Knowledge and Computer Representations
Where is knowledge in robotics? some methodological issues on symbolic and connectionist perspectives of AI

Autonomous robotic systems
Integration of reactive utilitarian navigation and topological modeling

Autonomous robotic systems
Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems

Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Based on the utilitarian navigation concept, the paper introduces a recurrent neural network for the search of sensory sources by a mobile robot. First, a utility function for sensory-based search is defined and a dynamic optimization process is obtained. Next, a bio-inspired neural model of sensory-motor coordination is proposed. The paper analyzes the proposed motor neural circuit in more detail, using a dynamic model of the respective motor neurons. Experimental results confirm the viability of the recurrent neural model for implementing sensory-based search by a mobile robot.