A distributed behavioral model using neural fields

  • Authors:
  • Mohamed Oubbati;Josef Frick;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:
  • ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

We investigate the use of neural fields for building a distributed behavioral model enabling several agents to move in a flock. No leader is required, and each agent is implemented as an independent element that follows its own behavioral model which is composed of four steering behaviors: separation, cohesion, alignment and obstacle avoidance. The synchronized motion of the flock emerges from combination of those behaviors. The control design will be discussed in theoretical terms, supported by simulation results.