Skip to main content

A software engine for multi-criteria decision support in flight management

Periodic Reporting for period 1 - Pilot3 (A software engine for multi-criteria decision support in flight management)

Reporting period: 2019-11-01 to 2020-10-31

Pilot3 is developing a software engine model for supporting crew decisions for civil aircraft providing a set of options to support the crew to select the most suitable one considering multi-criteria business objectives of the airline. Currently, when disruption occurs pilots do not count on a system which enables them to have a full understanding of the trade-offs involved in trajectory changes.

Pilot3 integrates airlines' objectives, which have been defined as on-time performance (OTP) and cost (fuel, passenger disruptions and other costs), when generating alternatives. Sub-objectives will be considered as part of the ranking of solutions; the crew could also introduce constraints and preferences to explore the alternatives. Pilot3 tackles two of the main problems faced during the flight: visibility on the end objectives of the airlines, by computing the expected costs as a function of delay at the gate, and the incorporation of uncertainty on the operations due to operational aspects (such as holdings at arrival).

Pilot3 is composed on five different subsystems: Indicators Estimator, Operational ATM Estimator, Alternatives Generator, Performance Assessment and HMI. The first four are being developed during the project, while the HMI is designed.

The Indicators Estimator computes of the different performance indicators for a given trajectory needed to estimate the expected cost of delay. The Operational ATM Estimator focuses on predicting operational uncertainties (procedure at arrival, holding, distance flown at the TMA and taxi-in time). Both modules provide the possibility to indicate how to estimate the different indicators: with airborne or ground information, and with analysis of data and heuristics or with machine learning.

The Alternatives Generator optimises the trajectory on the vertical profile (altitude and speed). The system will allow the pilot to add constraints.

The Performance Assessment Module compares the expected performance of each alternative trajectory and rank them according to the airlines' preferences on sub-objectives.
The first technical activities of the project focused on achieving an agreed understanding on the scope, high-level requirements, and preliminary datasets, indicators and scenarios to be explored. These activities of WP1 were the trigger for the different workpackages which further develop these concepts. The consortium considered of paramount importance to incorporate the views of relevant stakeholders in these early stages of the project. A workshop with the Advisory Board was carried out in London (07FEB20) and a follow up survey and bilateral discussions with some members of the board and the Topic Manager conducted. These actives led to the definition of the objectives to be considered by the optimiser, the addition of the Operational ATM Estimator module and provided input regarding the most suitable methods for optimisation. This was reported in D1.1 - Technical resources and problem definition (18MAR20 - M5).

The multi-criteria decision making technique selection process of WP2 benefited from the input of the Advisory Board workshop and from the dedicated follow up survey. These activities in WP2 not only selected a method but defined the prototype optimisation framework: generation phase (with a Lexicographic ordering multi-criteria optimisation method), ranking phase (supported by a compromise ranking method (VIKOR) to consider airline's preference on sub-objectives), and selection phase (underpinned by the HMI). These considerations, including a thorough literature review were reported in D2.1 - Trade-off report on multi-criteria decision making techniques (29MAY20 - M7) reaching MS2 - Multi-criteria decision making technique selected. The activities of WP2 included also the development of requirements for the HMI.

The data collection and management focused on the interaction with stakeholders. These activities involved the processing and analysis of the outcome of the workshop, survey and bilateral discussions as reported in D3.1 - Airlines data collection report (31JUL20 - M9) and used in WP1 and WP2 activities. The finalisation of these activities achieved MS3 - Airlines data collected and analysed. WP3 continued with the setting up of the data infrastructure ('BeSt') and the collection of datasets required for the model development.

A verification and validation plan has been defined as part of WP5 and reported in D5.1 - Verification and validation plan (07AUG20 - M10). This document provides information on the verification, and internal and external validation activities. It also provides research questions to be tackled with the validation, it further defines the methodology to define experiments in Pilot3, and it provides a schedule for the model development and the verification and validation activities.

The final technical tasks performed during the period covered by the report are the modelling activities of WP4. This includes the development of requirements for the HMI, the creation of a first prototype of the interface, the definition of the modules of Pilot3 and the interface between them. The development environment has been set and shared among the relevant partners.

Communication and dissemination activities include: the definition of the communication, dissemination and exploitation plan (D7.1 - 29MAY20 - M7), the launch of the project website, publication of three blog entries, participation at the AGIFORS conference and the PACEDays event, and several further dissemination actions via social media (LinkedIn).

Finally, the project management has been conducted as part of WP8 leading to D8.1 - Project management plan (29NOV19 - M1), D8.2 - Proof of signature of Consortium Agreement (24JAN20 - M3) and three periodic monitoring reports (PRM). The milestone MS1 - Project kick-off was reached at M1 (kick-off meeting on the 13NOV19 in Brussels).
The multi-criteria decision making techniques selection was performed following a domain-driven approach. This led to a solution which is tailored to the trajectories for tactical crew support problems. This represents a progress beyond the state of the art, as far as the consortium is aware, this has not been performed in the past. The consideration of explicit cost functions and modelling of the impact of operational uncertainties (such as holding at arrival) are also new contributions to the field of tactical trajectory optimisation. The development of these elements are on-going as part of WP4, but the definition of the optimisation framework and their consideration have already been performed.

The modular solution of Pilot3 should enable us to produce benefits on different fields (cost estimation, operational uncertainty estimation and trajectory optimisation). These elements could potentially be used beyond Pilot3 on different solutions, for example, the cost estimations could be used as part of decision making processes performed on-ground by the airlines operating centre, or the trajectory optimiser technique could incorporate new objectives as the environmental impact of the flight. These additions are out of scope of the project but will be potential evolutions of Pilot3.

Pilot3 solutions will enable crew to make more informed decisions, particularly regarding the expected uncertainties at arrival leading to more efficient and environmentally optimal solutions.
Pilot3 methodology to select multi-criteria optimisation methods
Pilot3 architecture
Pilot3 optimisation phases