An Immune-based Multilayered Cognitive Model for Autonomous Navigation

Author

Romero, D.A. ; Nino, F.

Author_Institution

Electrical and Electronics Engineering Department at the National University of Colombia, Bogota, Colombia (Phone: +57-1-251-7574; fax: +57-1-234-3291; e-mail: daromerolo@unal.edu.co).

fYear

0

fDate

0-0 0

Firstpage

391

Lastpage

398

Abstract

In this work, an immune-based multilayer cognitive model for autonomous navigation is proposed. Each layer is modeled by a bioinspired technique, namely, neural networks and artificial immune systems. In this research, a new immune based algorithm is proposed, which is a combination of an algorithm based on immune network theory and a reinforcement learning technique. The proposed approach was tested on several environments and it exhibited interesting learning capabilities in solving an autonomous navigation problem.

Keywords

artificial immune systems; cognitive systems; learning (artificial intelligence); mobile robots; navigation; path planning; artificial immune systems; autonomous navigation; bioinspired technique; immune network theory; immune-based multilayered cognitive model; reinforcement learning technique; Artificial neural networks; Computational modeling; Data processing; Immune system; Mobile agents; Mobile robots; Multi-layer neural network; Navigation; Robot sensing systems; Sensor fusion;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 2006. CEC 2006. IEEE Congress on

Conference_Location

Vancouver, BC

Print_ISBN

0-7803-9487-9

Type

conf

DOI

10.1109/CEC.2006.1688335

Filename

1688335