Applied Intelligence

, Volume 13, Issue 3, pp 205–213

Neural Nets Trained by Genetic Algorithms for Collision Avoidance

  • Nicolas Durand
  • Jean-Marc Alliot
  • Frédéric Médioni

DOI: 10.1023/A:1026507809196

Cite this article as:
Durand, N., Alliot, J. & Médioni, F. Applied Intelligence (2000) 13: 205. doi:10.1023/A:1026507809196


As air traffic keeps increasing, many research programs focus on collision avoidance techniques. For short or medium term avoidance, new headings have to be computed almost on the spot, and feed forward neural nets are susceptible to find solutions in a much shorter amount of time than classical avoidance algorithms (A*, stochastic optimization, etc.) In this article, we show that a neural network can be built with unsupervised learning to compute nearly optimal trajectories to solve two aircraft conflicts with the highest reliability, while computing headings in a few milliseconds.

air traffic controlcollision avoidanceneural networksgenetic algorithms

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Nicolas Durand
    • 1
  • Jean-Marc Alliot
    • 2
  • Frédéric Médioni
    • 3
  1. 1.Centre d'Etudes de la Navigation ArienneFrance
  2. 2.Centre d'Etudes de la Navigation ArienneFrance
  3. 3.Centre de Mathématiques Appliquées de l'Ecole PolytechniqueFrance