Daniel Delahaye’s research while affiliated with Université de Toulouse and other places

... Accurately assessing the collision risk of UAVs, whether managed via autonomous airborne detect and avoid (DAA) systems or ground-based unmanned aircraft system traffic management (UTM), is essential for ensuring the safe and efficient operation of UAVs in various scenarios. The design of urban low-altitude airspace structures has an impact on the safe operation of UAVs, with methods such as airspace discretization and zonal or layer separation [9][10][11][12][13]. However, in free-flight airspace, UAVs can fly directly from the takeoff point to the destination, significantly enhancing operational efficiency. ...

Reference:

Quantifying Well Clear Thresholds for UAV in Conjunction with Trajectory Conformity

... In general, computer simulation models have long been interesting decision-support tools for airport managers for both airside and landside. For instance, Pérez et al. [9], Scozzaro et al. [10], and Derek et al. [11] utilized simulation for optimizing the staff schedules and allocations in the landside of the airport. Here, Pérez et al. [9] offered a discrete event simulation model for the terminal checkpoints to improve the shift allocation of security screening resources. ...

Reference:

Airside Optimization Framework Covering Multiple Operations in Civil Airport Systems with a Variety of Aircraft: A Simulation-Based Digital Twin

... Through effective control, a drone swarm can improve the aerodynamics and other characteristics of a group of drones [43,44]. The optimization problem of the joint flight trajectory of several drones has been studied [45][46][47]. Using UAV swarms improves mission performance by sharing artificial intelligence (AI) [48][49][50]. ...

Reference:

Investigation of a Multiflow Ejector Equipped with Variable-Length Links for Thrust Vector Control Using Euler’s Methodology

... Avella [7] et al. set up an integer programming model to consider the scheduling problem under the interference of arrival flights. Ma et al. [8,9] proposed a mixed integer programming model for departure runway scheduling and solved the model by using the simulated annealing algorithm. Bikir et al. [10] proposed a genetic algorithm-based method to help air traffic controllers organize the departure sequence according to the standard instrument departure (SID) configuration. ...

Reference:

Adaptive Dynamic Programming with Reinforcement Learning on Optimization of Flight Departure Scheduling

... Flight times between airports and shared waypoints, related to factors such as the flight performance of aircraft, bad weather, and pilot behavior, are one of the important inputs for AGCT design. Most studies have focused on AGCTs with certain flight times [1][2][3][4] and neglected the real-life conditions of uncertain flight times [5][6][7]. Obviously, AGCT schedules without consideration of uncertain times are difficult to apply in practice. Various ...

Reference:

Robust Optimization Model of Airport Group Coordinated Timetable with Uncertain Flight Time

... The frequency and capacity of flights are determined by the number of airlines operating at the airport (Adenigbo, 2016;Chao and Yu, 2013;Lotti and Caetano, 2018), cargo clearance times (Adenigbo, 2016;Chao and Yu, 2013;Gardiner et al., 2005;Zhang, 2003), airport capacity (Adenigbo, 2016;Adler and Berechman, 2001;Chao and Yu, 2013), aircraft turn-around times (Hooper and Hensher, 1997), and frequency of flight cancellations (Adenigbo, 2016). These factors affect the freight forwarder's ability (Wandelta et al., 2024) to determine whether an airport is an excellent place to send air cargo. The diversity of destinations can be determined by the number of cities to which the airport has flight connections (Chao and Yu, 2013;Gardiner and Ison, 2008;Gardiner et al., 2005;IATA, 2016;Kupfer et al., 2016). ...

Reference:

Examining airport agility at air cargo hub airports

... The flight arrival scheduling problem is classified as NP-hard [7], meaning that the complexity of finding an optimal solution grows exponentially with the problem size. This inherent complexity poses significant challenges for real-time or near-real-time optimization, as computational resources and time constraints limit the feasibility of exact solutions. ...

Reference:

Flight Arrival Scheduling via Large Language Model

... In addition, in the field of air-rail intermodal transportation system optimization, passenger flow demand distinguishes itself from traditional transportation. Chiambaretto et al. 6 , Kong mingxing et al. 7 , He wenhui et al. 8 and Buire et al. 9 mainly investigated the problem of reducing the passengers' waiting and connecting time and cost. While these studies aim to enhance intermodal system efficiency and passenger satisfaction through the construction of optimization models and timetable adjustments, they often overlook a comprehensive analysis of the specific characteristics of passenger flows. ...

Reference:

Research on airport express train schedule optimization based on demand-driven air-rail intermodal transportation

... By evaluating and understanding complexity, authorities can implement measures and strategies that contribute to efficient and safe airspace operations. Accordingly, Shi-Garrier et al. [77] adopted a novel encoder-decoder LSTM neural network to predict ATC tasks based on the presented intrinsic complexity metric. Furthermore, a novel end-to-end learning framework was introduced by Xie et al. [78] to assess sector operation complexity. ...

Reference:

Short-term multi-step-ahead sector-based traffic flow prediction based on the attention-enhanced graph convolutional LSTM network (AGC-LSTM)

... In the context of unsupervised learning, it has been used for clustering different types of data: shape clustering applied to morphometry [24], clustering of financial returns [25], image segmentation [20] and identification of diseases from medical data [26,27]. When it comes to supervised learning, it has been used to analyse the geometry in the latent space of generative models [28], to enhance robustness against adversarial attacks [29,30], in detection of out-of-distribution samples [31], as a loss function for learning under label noise [32], and to classify EEG signals of brain-computer interfaces [33]. ...

Reference:

On closed-form expressions for the Fisher–Rao distance