Neural Nets trained by genetic algorithms for collision avoidance

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.

Data and Resources

Additional Info

Field Value
Source ISSN: 0924-669X
Author Durand, Nicolas, Alliot, Jean-Marc, Medioni, Frédéric
Maintainer CCSD
Last Updated May 7, 2026, 07:07 (UTC)
Created May 7, 2026, 07:07 (UTC)
Identifier hal-00934535
Language en
Rights https://about.hal.science/hal-authorisation-v1/
contributor Ecole Nationale de l'Aviation Civile (ENAC)
creator Durand, Nicolas
date 2000-11-07T00:00:00
harvest_object_id 5c6363e6-61cd-4c79-9ed5-c1bae64681cd
harvest_source_id 3374d638-d20b-4672-ba96-a23232d55657
harvest_source_title test moissonnage SELUNE
metadata_modified 2025-02-20T00:00:00
relation info:eu-repo/semantics/altIdentifier/doi/10.1023/A:1026507809196
set_spec type:ART