Deep generative modelling of aircraft trajectories in terminal maneuvering areas

Krauth, Timothé; Lafage, Adrien; Mitard, J.; Olivé, Xavier; Waltert, Manuel

doi:10.1016/j.mlwa.2022.100446

Cited by 7 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Having defined the geometrical shape to represent aircraft, the first step in modelling the collision probabilities is to simulate pairs of aircraft trajectories with Monte Carlo simulation runs. The pairs of trajectories can be obtained in various ways, including (i) from an air traffic simulator such as Bluesky [26], which relies on a performance model like OpenAp [27] or EUROCONTROLs base of aircraft data (BADA) [28], (ii) from a data-driven model as proposed by Krauth et al [29], or (iii) by re-enacting observed aircraft trajectories, such as historical radar tracks. For each Monte Carlo simulation run, two aircraft trajectories are randomly selected.…”

Section: Methodsmentioning

confidence: 99%

Data-Driven Mid-Air Collision Risk Modelling Using Extreme-Value Theory

Figuet

Monstein

Waltert

et al. 2023

Preprint

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Data-Driven Mid-Air Collision Risk Modelling Using Extreme-Value Theory

Figuet

Monstein

Waltert

et al. 2023

Preprint

View full text Add to dashboard Cite

“…As such, the models associated with this approach are built on data-driven techniques such as data analytics and visualization [43][44][45][46][47], as well as machine learning [48][49][50][51][52]. The machine learning-based techniques are especially useful for trajectory prediction [53][54][55]. In particular, unsupervised clustering schemes are typically employed to establish the approximate layout of approach paths from different arrival directions [56][57][58].…”

Section: A Existing Approaches To Arrival Traffic Modelingmentioning

confidence: 99%

A Comparative Analysis of Terminal Area Navigation and Conventional Standard Arrival Routes with Cellular Automata

Ogedengbe

Wong

Liem

2023

AIAA AVIATION 2023 Forum

View full text Add to dashboard Cite

Aircraft arrival at airports is limited by the physical configuration and layout of the terminal maneuvering area (TMA), which might result in a bottleneck. In a bottleneck situation, navigation is made difficult because arriving aircraft will need special considerations to manage congestion and guarantee safety. In addition, the operating cost of airline operators increases with higher fuel consumption encountered in the extra airborne time. Likewise, passengers incur more travel time with the additional arrival delays. Traditional arrival adopts conventional standard arrival route (STAR), with trajectories that are rigidly coordinated by air traffic controller (ATC). However, a more flexible approach to general navigation has also been introduced, namely the area navigation (RNAV), which makes provision for flexibility in aircraft path selection. This flexibility is enabled by abstract navigational elements, namely waypoints that are unlike conventional navigational aids (NAVAIDs). We look at a modeling framework that juxtaposes the key elements of the traditional STAR (procedure-based) navigation and RNAV (performance-based) navigation. We adopt the cellular automata (CA) framework that has the capability to model the dynamic interaction between aircraft, inherent environmental uncertainties, and arrival route as defined by waypoints. To this end, we develop a modeling environment that enables a fair comparison between these two approaches under similar conditions to determine their respective viability. The effect of the number of waypoints in the TMA under different traffic conditions is illustrated using the relationship between TMA occupancy, traffic flow, and the landing rate. Results show that RNAV navigation exhibits more sensitivity to waypoint distribution within the TMA in terms of throughput, compared to STAR navigation. STAR navigation, on the other hand, demonstrates inherent latency that allows for higher capacities, albeit at the risk of initiating abrupt jamming when a high number of waypoints are active. Consequently, we are able to establish guidelines that justify the adoption RNAV over STAR and vice versa. Furthermore, we also identify performance disparities between them, and where each approach is desirable.

show abstract