Chair objectives
The first objective of this chair is to develop new AI decision support tools for assisting air traffic management operators, mainly air traffic controllers and pilots, in order to enhance their efficiency and to increase the overall capacity of the air traffic system.
The chair objective is to go a step further by proposing now AI approaches to target full
automation in the framework of large scale urban mobility in a wide sense. For such system,
aerial vehicles (UAV) and ground vehicles (autonomous cars) have to self organize in order to ensure safe
and efficient operations.
For such an automatic system, there is no centralized entity which organizes
the traffic as in traditional ATM.
We propose to develop new AI algorithms for organizing traffic in such a full automatic framework for large scale air trafic management.
The main applications of the team's research are:
- Airspace design (e.g. roads, control sectors)
- Optimization of air traffic (continental and oceanic strategic, pre-tactical and tactical)
- 4D optimization of aircraft trajectories
- Optimization of airport traffic (eg landing sequencing, taxiing, allocation of runways and doors)
- Drones (ex: planning of drone trajectories, planning of missions)
Programs Certifiable & collaborative AI
Theme Automated reasoning and decision making
Chair holder: Daniel Delahaye, Professeur, HdR
Co-chairs:
- Nicolas Couellan (ENAC)
- Emmanuel Rachelson (ISAE)
Chair holder : Pr Daniel Delahaye ENAC
Co- chairs :
- Nicolas Couellan (ENAC)
- Emmanuel Rachelson (ISAE)
Senior collaborating researcher
- Stéphane Puechmorel (ENAC)
PhD students
- Sylvain Roudière,
- Dinh-Thinh Hoang,
- Yael Zorah
- Gabriel Jarry,
- Philippe Monmousseau
- Patent : Aircraft Landing Configurations Optimization (Airbus)
- Software for automatic detection of abnormal aprroaches (implemented at CDG airport), Sotware for automatic configuration of air traffic contol center ACC) implemented in the five french ACC
- Organisation de l’ Europt Conference 2021, RL summer school
- L.Ligny, A Guitart, D.Delahaye and B.Sridhar. Aircraft Emergency Trajectory Design: A Fast Marching Method on a Triangular Mesh. In procedding of the 2021 USA/Europpe ATM Seminar.
- G.Jarry, D.Delahaye, and E.F.ron. Flight safety during Covid-19: A study of Charles de Gaulle airport atypical energy approaches. Transportation Research Interdisciplinary Perspectives, 9 (100327), February 2021
- G.Jarry, D.Delahaye and E .Feron. Approach and landing aircraft onboard parameters estimation with LSTM networks. In proceeding AIDA-AT 2020.
- L.Shi-Garrier, D.Delahaye and N.Bouaynaya. Predicting Air Traffic Congested Areas with Long Short-Term Memory Networks. In procedding of the 2021 USA/Europpe ATM Seminar.
- Z.Wang, D.Delahaye, J.L. Farges and S.Alam. Complexity-optimal traffic assignment for future urban airspace. Transportation research part C (in press)
- P.Juntama, S.Alam, S. Chaimatanan and D.Delahaye. Air Traffic Structuration based on Linear Dynamical Systems. In proceeding. SID conference 2020.
- S.Ikli, C.Mancel, M.Mongeau, X.Olive, and E.Rachelson. The aircraft runway scheduling problem: A survey. Computers and Operations Research, Volume 132, August 2021.
- E. Munin, A.Blais A and N.Couellan, GNSS Multipath Detection Using Embedded Deep CNN on Intel Neural Compute Stick, Proceedings of the 33rd International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2020), , September 2020, pp. 2018-2029.
- N.Couellan, Probabilistic robustness estimates for feed-forward neural networks, Neural Networks, vol. 142, pp 138-147 2021.
- N. Couellan, The coupling effect of Lipschitz regularization in deep neural networks, to appear in SN Computer Science. 2021
- N .Couellan and S. Jan, Feature uncertainty bounds for explicit feature maps and large robust nonlinear SVM classifiers, Annals of Mathematics and Artificial Intelligence. 2020
Know more
AI, the new transport eldorado
Civil planes, drones, land links: optimization in transport is an issue of safety and fluidity, but also a major environmental issue. With AI, a new generation of transport is taking shape. Demonstration with Daniel Delahaye, teacher-researcher at the National School of Civil Aviation (ENAC).