Community Research and Development Information Service - CORDIS

H2020

DART Report Summary

Project ID: 699299
Funded under: H2020-EU.3.4.7.1

Periodic Reporting for period 1 - DART (Data-driven AiRcraft Trajectory prediction research)

Reporting period: 2016-06-20 to 2016-12-19

Summary of the context and overall objectives of the project

The main research objective of DART (Data-driven AiRcraft Trajectory prediction research) is to explore the application of different data-driven techniques to the aircraft trajectory prediction problem, also accounting for complexity ATM network effects.
Specifically, DART will deliver understanding on the suitability of applying data-driven techniques both for predicting single aircraft trajectories without considering traffic, as well as for predicting multiple correlated aircraft trajectories.

As part of this objective DART emphasizes the role modern visualization techniques can have in facilitating trajectory predictions.

To achieve this high-level main research objective, the following specific research objectives have been defined:

• Definition of requirements for the input datasets needed. The requirements will consider the trajectory prediction accuracy expected.
• Study of the application of big-data techniques to trajectory related data gathering, filtering, storing, prioritization, indexing or segmentation to support the generation of reliable and homogenous input datasets.
• Study of different data-driven learning techniques to describe how a reliable trajectory prediction model will leverage them.
• Formal description of the complexity network to support correlated multiple trajectory predictions.
• Study of the application of agent-based models to the prediction of multiple correlated trajectory predictions considering complexity network.
• Description of visualization techniques to enhance trajectory data management capabilities.
• Exploration of advanced visualization processes for data-driven model algorithms formulation, tuning and validation, in the context of 4D trajectories.

The overall DART concept is shown in the DART concept figure, while the DART work structure is depicted in the DART work package structure.

Towards achieving these goals, DART has defined the operational context to be considered and delivered the specification of two scenarios, taking into account airspace users’ and Air Navigation Service Provider’s (ANSP) points of views for trajectory predictions, forming the requirements to the final trajectory prediction algorithms.
The outcomes of these techniques will be comparable thanks to the common dataset infrastructure developed in the project.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

During this first period, the project performed according to planned work the following tasks:

WP1:
• Preparation of Data Management Plan (this has been delivered in D1.1).
• Preparation of Data Transaction Pipeline (this has been delivered in D1.2).
• Preparation and release of the initial dataset to be used by WP2 and WP3.

WP2:
• Exploration and analysis of the initial dataset delivered by WP1.
• Study of state of the art algorithms for trajectory prediction with emphasis on single trajectory prediction (this has been delivered in D2.1).
• Preparation of a proposal on novel approaches to apply Data-Driven algorithms for trajectory predictions (this has been delivered in D2.1)

WP3:
• Exploration of the initial dataset delivered by WP1.
• Study of state of the art algorithms on agent-based modelling in ATM
• Specification of scenarios and requirements for single and multiple trajectory predictions (this has been delivered in D3.1)
• Initial formulation of the problem for multiple trajectories prediction using Markov Decision Processes (MDPs).

WP4:
• Specification of the project management procedures and overall plan (this has been delivered in D4.1).
• Web site construction and set-up of dissemination channels (reported in D4.2)
• Specification of the dissemination plan (this has been delivered in D4.3)

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

DART will deliver understanding on the suitability of applying data-driven techniques for predicting multiple correlated aircraft trajectories. Towards this goal, it has delivered the specification of two scenarios, taking into account airspace users’ and ANSP’s points of views for trajectory predictions, forming the requirements of WP2 and WP3.

These scenarios aim to demonstrate how DART predictive analytics capability can improve trajectory prediction in support of DCB processes at planning phase, further reducing uncertainty and improving ATM operations and services provided. In particular, for achieving the objectives of WP1, For a given flight plan, the objective is to compute the predicted trajectory that an aircraft will fly during an operation day. The WP3 scenario aims to study and determine the complexity to be considered in a trajectory prediction due to the influence of the surrounding traffic also at the planning phase, taking into account flight plans and the predictions computed by WP2. The scenario objective is to demonstrate how DART predictive analytics capability can help in trajectory forecasting when demand exceeds sectors’ capacity.

Both scenarios concern Spain and aim at analysing and evaluating machine learning algorithms for trajectory predictions: The WP2 scenario from an individual trajectory perspective (i.e. without considering traffic) and from the airspace users’ point of view, while WP3 considers Air Navigation Service Provider’s (ANSP’s) point of view, and aims to compute and evaluate collaborative trajectory predictions.

Related information

Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top