Skip to Main content Skip to Navigation
Journal articles

Neural Nets trained by genetic algorithms for collision avoidance

Abstract : 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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal-enac.archives-ouvertes.fr/hal-00934535
Contributor : Laurence Porte <>
Submitted on : Tuesday, April 29, 2014 - 5:12:39 PM
Last modification on : Tuesday, June 2, 2020 - 12:10:09 PM
Long-term archiving on: : Tuesday, July 29, 2014 - 10:45:20 AM

File

Durand_AI2000.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Nicolas Durand, Jean-Marc Alliot, Frédéric Medioni. Neural Nets trained by genetic algorithms for collision avoidance. Applied Intelligence, Springer Verlag (Germany), 2000, 13 (3), pp 205-213. ⟨10.1023/A:1026507809196⟩. ⟨hal-00934535⟩

Share

Metrics

Record views

472

Files downloads

429