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.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
E.M. Schuster, F.R. Petroski, R.K. Sciambi, and M. Mc Stokrp, "AERA2 functional design and performance description," Technical Report, MITRE, September 1983. MtR-83W136.
W.P. Niedringhaus, "A mathematical formulation for planning automated aircraft separation for AERA3," Technical Report, FAA, 1989. DOT/FAA/DS-89/20.
W.P. Niedringhaus, "Automated planning function for AERA3: Manoeuver Option Manager," Technical Report, FAA, 1989. DOT/FAA/DS-89/21.
F. Krella et al., "Arc 2000 scenario (version 4.3)," Technical Report, Eurocontrol, April 1989.
M. Schoenauer, E. Ronald, and S. Damour, "Evolving nets for control," Technical Report, Ecole Polytechnique, 1993.
A. Fadda, "Utilisation de techniques neuro-genetiques pour la resolution de problemes inverses," Ph.D. Thesis, Ecole Polytechnique de Paris, 1998.
TCAS-III collision avoidance algorithms, Version 3, Technical Report, The MITRE Corporation, November 1990.
H. Gruber, Comparaison de diverses m´ethodes d'Intelligence Artificielle pour la r´esolution de conflit en contrôle de trafic a´erien, Rapport de Stage, Centre d'Etudes de la Navigation A´erienne, 1992.
K. Zeghal, "Vers une th`eorie de la coordination d'actions, application `a la navigation a´erienne," Ph.D. Thesis, Universit´e Paris VI, 1994.
K. Zeghal, "A reactive approach for distributed air traffic control," in International Conference on Artificial Intelligence & Expert Systems, Mai, 1993.
K. Zeghal, "A comparison of different approaches based on force fields for coordination among multiple mobile," in IEEE International Conference on Intelligent Robotic System, IROS, Mai, 1993.
N. Durand, "Optimisation de Trajectoires pour la R´esolution de Conflits en Route," Ph.D. Thesis, ENSEEIHT, Institut National Polytechnique de Toulouse, 1996.
Bryson and Ho, Applied Optimal Control, Hemisphere Publishing Corporation: New York, 1975.
R.F. Hartl, S.P. Sethi, and R.G. Vickson, "A survey ot the maximum principles for optimal control problems with state constraints," SIAM Review, 1995.
A.R. Conn, N. Gould, and Ph.L. Toint, "A comprehensive description of LANCELOT," Technical Report, IBM T.J. Watson Research Center, 1992. Report 91/10.
N. Durand, J.M. Alliot, and J. Noailles, "Automatic aircraft con-flict resolution using genetic algorithms," in Proceedings of the Symposium on Applied Computing, Philadelphia, ACM, 1996.
N. Durand and J.M Alliot, "Optimal resolution of en route conflicts," in 1 ST U.S.A/EUROPE ATM R & D Seminar, Mai 1997.
D. Goldberg, Genetic Algorithms, Addison Wesley: Reading, MA 1989: ISBN: 0–201–15767–5.
J.M. Alliot, "A genetic algorithm to improve an othello program," in Artificial Evolution 95, Springer: Berlin, 1995.
Z. Michalewicz, Genetic algorithms C data structuresD evolution programs, Springer-Verlag: Berlin 1992, ISBN: 0–387–55387–.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Durand, N., Alliot, JM. & Médioni, F. Neural Nets Trained by Genetic Algorithms for Collision Avoidance. Applied Intelligence 13, 205–213 (2000). https://doi.org/10.1023/A:1026507809196
Issue Date:
DOI: https://doi.org/10.1023/A:1026507809196