Technology Challenges in Air Traffic Management Competition

The two best solutions will win 60,000 €.

Call open from May 1 to June 30, 2025

Sign up for the Infoday on Monday 19 May at 11:30

What is the Technology Challenges in Air Traffic Management Competition?

ENAIRE launches this year the 4th edition of the Technology Challenges in Air Traffic Management Competition.
The competition is open to university research groups or any other type of groups.

Technological solutions applicable to any sector of activity are admitted, as long as they are focused on the provision of air traffic/air transport services.

Challenges

For this competition we accept full or partial solutions to any of the following 5 challenges.

Challenge #1
Challenge
#1

Towards explainable and safe AI in air traffic management through certification.

The incorporation of Artificial Intelligence (AI) in Air Traffic Management (ATM) opens up new possibilities to improve the efficiency, safety and capacity of systems. However, to ensure their safe and reliable implementation, it is essential to establish a certification framework that validates these solutions from development to operational deployment.

Learn more

This challenge seeks to promote research to develop specific methodologies, tools and standards for the certification of AI systems in ATM environments. These solutions must be auditable, explainable and capable of operating in highly automated environments, while ensuring transparency in decision making, risk mitigation and resilience to failures or attacks.

One of the main challenges is the explainability of AI (XAI), which must ensure that the models used are understandable to humans, especially regulators and system operators. Techniques are required to interpret and verify the reasoning of the algorithms used in critical processes, as well as mechanisms to trace decisions in complex scenarios and in real time.

Another key aspect is the validation and certification of these solutions. It is necessary to develop regulatory frameworks and testing methodologies that allow the performance of AI-based systems to be evaluated under both nominal and unexpected conditions. This implies the creation of test benches and simulation environments where solutions can be validated in realistic contexts and clear metrics for their acceptance can be defined.

The reliability and robustness of AI models also represents a fundamental challenge. Systems must be designed to operate in dynamic environments with minimal human intervention, avoiding biases or errors that could compromise their performance. It is also essential to integrate cybersecurity measures that protect these systems from possible attacks or external manipulation.

Finally, this challenge addresses the integration of AI in the innovation life cycle, promoting the development of test platforms and test benches that facilitate the transition from prototypes to operational environments in compliance with current regulations. In addition, it seeks to establish strategies for the progressive certification of these systems, allowing their staggered implementation in the ATM ecosystem and ensuring mechanisms for their maintenance and secure updating over time.

Expected impact of the solutions to be developed in this challenge: Solutions are sought to build a regulatory and technological framework that facilitates the safe adoption of AI in the ATM environment and certification. It is also expected that the results obtained will contribute to generate confidence in the use of these systems in critical operations, establish standardized certification processes at European and international level and optimize the efficiency and capacity of ATM systems without compromising safety and human supervision.

Chalenge #2
Challenge
#2

Operational resilience in ATM: failure recovery strategies for automated systems.

Increasing automation in Air Traffic Management (ATM) promises to optimize the efficiency and safety of operations, but it also introduces greater dependence on advanced technological systems. In this context, any failure in automated systems can generate significant disruptions, compromising service continuity and operational safety.

Learn more

To address this challenge, it is essential to develop redundancy and resilience models that guarantee service continuity even in the event of partial or total system failures. Having robust architectures that include self-diagnosis and recovery mechanisms will minimize the impact of these disruptions, ensuring that air traffic can be managed with the least possible impact.

Detecting and mitigating failures in real time is another essential challenge in this context. The incorporation of artificial intelligence and machine learning will make it possible to identify anomalous patterns in automated systems, facilitating the prevention and early correction of errors. However, automatic detection is not enough; it is necessary to have strategies that trigger immediate responses and enable a smooth transition to a safe state, avoiding the escalation of operational problems.

In a highly automated environment, ensuring efficient interaction between technological systems and human operators is key to operational safety. To this end, it is essential to have “fallback” strategies, i.e., mechanisms that allow a controlled transition from automation to human intervention when a critical systems failure occurs. These strategies will ensure that controllers can regain control without creating a disproportionate increase in workload or compromising decision making under pressure. Effective human-machine interface design will be critical to facilitate this transition smoothly and safely. In addition, it is essential to have simulation and validation environments to test different failure scenarios. Assessing the impact of disruptions and analyzing the effectiveness of response strategies will help to optimize system resilience and identify improvements in operational procedures.

Cybersecurity plays a key role in the resilience of highly automated ATM systems. The increasing digitization and connectivity of these systems makes them vulnerable to potential attacks that could compromise their stability and operation. It is crucial to develop advanced protection solutions that enable real-time threat detection and neutralization, ensuring that the integrity and security of the airspace is not affected by cyber incidents.

Expected impact of the solutions to be developed in this challenge: The solutions developed in this challenge will make the ATM system more resilient to unexpected failures, ensuring operational continuity with minimal impact on air traffic management. Advances in this area are expected to contribute to improve the safety and efficiency of the system, allowing a better integration between automation and human supervision.

Challenge #3
Challenge
#3

Oversight in ATM: transparency, monitoring and control of AI in real time

The move toward highly automated systems in ATM poses the critical challenge of ensuring that human operators maintain effective control of the decisions made by the AI. Given that these systems can process large volumes of data and react in milliseconds, it is critical that operators understand their actions and have the ability to intervene when necessary. Without this real-time oversight, confidence in automation could be affected and operational safety compromised.

Learn more

To meet this challenge, it is imperative to develop explainable AI (XAI) models that allow operators to interpret and audit automated decisions. A system that cannot justify its behavior generates uncertainty and can hinder decision making in critical situations. Explainability must not only ensure transparency, but also facilitate the traceability of each decision within the ATM system.

At the same time, it requires the design of advanced visualization and alerting interfaces, capable of presenting relevant information in an intuitive and prioritized way. Automation must translate into tools that improve the operator’s situational awareness, avoiding information overload and ensuring that critical alerts are easily detectable and understandable.

Ensuring real-time intervention capability is another essential pillar for human supervision in automated environments. Efficient validation and correction mechanisms need to be developed, allowing operators to approve, modify or override automated decisions without unnecessary delays. Agility in this interaction is key to mitigating errors and ensuring that automation functions as a support, rather than a barrier, to decision making.

In addition, ATM systems must dynamically adapt to the cognitive load of the operator. Flexible automation, capable of adjusting its level of intervention according to the operational context, will help to avoid both over-reliance on AI and controller overload. This requires the implementation of strategies that balance human intervention and system autonomy in an efficient and safe manner.

Finally, the implementation of these systems must ensure that human oversight remains a fundamental pillar of aviation safety. The combination of explainability, intuitive interfaces and adaptability will allow an appropriate balance between the speed and efficiency of automation and the ability for operator oversight and control.

Expected impact of the solutions to be developed in this challenge: Advances in this area will make ATM automation more reliable, transparent and efficient, without compromising human supervision. This will strengthen confidence in AI systems, reduce the cognitive burden on operators and ensure that air traffic management decision making maintains the highest standards of safety and reliability.

Challenge #4
Challenge
#4

ATM-assisted automation: Digital assistant for air traffic controllers

The increasing complexity of air traffic management requires advanced tools to optimize decision making and reduce the cognitive load on controllers. In this context, the development of a proactive digital assistant represents a key innovation to improve operational efficiency and safety, enabling smoother collaboration between the human operator and automated systems.

Learn more

This challenge poses the creation of an AI-based assistant capable of learning from the beginning of the controller’s training, adapting to his routines, decision-making patterns and air traffic management strategies. Throughout the training, the assistant should provide personalized recommendations for conflict resolution, progressively evolving to be able to anticipate situations and propose autonomous solutions, always under human supervision.

To achieve this, the solution must address the specific challenges of the ATM environment by applying advanced technologies such as generative AI, deep learning, optimization algorithms and natural language processing. These tools will enable the assistant not only to analyze large volumes of data in real time, but also to interpret the operational context and adjust its suggestions to the dynamic conditions of the airspace.

One of the key aspects of this development is the ability of the wizard to adapt to the style of each controller, providing support that complements their skills rather than imposing a generic solution. Wizard customization should be based on progressive learning, integrating models that identify individual patterns and adjust suggestions based on the user’s experience and performance.

In addition, interaction with the assistant must be intuitive and efficient, requiring the design of advanced human-machine interfaces that facilitate the understanding of suggestions and ensure smooth communication. The integration of augmented reality interfaces, voice commands or dynamic visualizations can significantly improve the usability and adoption of this technology in high-pressure operating environments.

Another key challenge is to ensure that the assistant not only learns, but can also justify its recommendations in a transparent manner. The explainability of the AI will be crucial to build trust in the system, allowing controllers to understand the reasoning behind each suggestion and, where necessary, adjust or reject proposed decisions.

The evaluation of the assistant in simulation and operational test environments will be key to validate its effectiveness in realistic scenarios. To this end, it will be necessary to implement validation methodologies that analyze its impact on controller performance, as well as on air traffic efficiency and safety. Ensuring effective integration into the ATM ecosystem will require a rigorous approach that avoids compromising human decision making and reinforces confidence in the system.

Expected impact of the solutions to be developed in this challenge: This development will transform the way controllers interact with ATM support systems by providing an adaptive digital assistant that increases operational efficiency and reduces cognitive load without compromising human oversight.

Challenge #5
Challenge
#5

Multi-objective optimization: dynamic balancing of safety, capacity and sustainability in ATM

Air traffic management faces increasing challenges in optimizing its operations, where multiple objectives must be considered simultaneously. Operational safety remains the non-negotiable pillar of the ATM system, as does cybersecurity when directly related to aviation safety protection. However, other factors such as capacity, environmental sustainability and economic efficiency can be managed with a certain degree of flexibility, allowing the exploration of operational trade-offs depending on the conditions and priorities of the moment.

Learn more

Today’s operational scenarios require decision-making models that are not based on a single criterion, but on a broad set of interdependent factors. At certain times, an air navigation service provider may prioritize maximizing capacity to absorb peak demand, even if this implies higher operational cost and environmental impact. In other contexts, the priority may be to reduce environmental impact, which may lead to reduced capacity and increased delays.

To meet this challenge, it is essential to develop multi-objective decision and optimization models to dynamically manage the various operational criteria. The flexible assignment of weights to each objective will allow the ATM system to adapt to different strategic needs, ensuring that operational modes can be adjusted according to factors such as traffic, weather conditions, regulatory constraints or sustainability policies.

The development of these models requires the application of advanced techniques such as mathematical optimization, artificial intelligence, evolutionary algorithms and machine learning, capable of evaluating large volumes of data in real time and providing recommendations adapted to changing scenarios. These solutions must be able to manage conflicts between objectives and provide balancing strategies that maximize efficiency without compromising security.

Another key aspect is the integration of decision support tools that make it easier for ATM system operators to interpret different scenarios and their implications. Intuitive interfaces and dynamic visualizations will enable a better understanding of the trade-offs between capacity, costs and sustainability, facilitating informed decision making in real time.

Additionally, the validation of these models in simulated environments will be fundamental to measure their effectiveness and ensure their applicability in air traffic operational management. The evaluation of different scenarios will allow adjusting the multi-objective optimization models so that they can be integrated in strategic and tactical decision making within the ATM ecosystem.

Expected impact of the solutions to be developed in this challenge: The development of multi-objective optimization tools will contribute to a more flexible and adaptive ATM, where decision making can be adjusted to the needs of the moment without losing sight of safety and sustainability objectives.

Phases of the competition

June 30, 2025

June 30, 2025

1. Presentation of proposed solutions

Deadline for submitting applications through the form available on this website.

September 30, 2025

September 30, 2025

2. Evaluation of proposed solutions

The Jury will pre-select the finalists.

October 2025

October 2025

3. Jury Interviews

The finalists will present their proposed solutions to the Jury.

October 31, 2025

October 31, 2025

4. Selection, notification and acceptance of the challenge

The Jury will inform the winning research groups.

January 2026 – June 2027

January 2026 – June 2027

5. Winning solution research and follow-up phase

From the date of acceptance of the challenge, each winning research group will sign a research agreement to begin work that will last 18 months.

Prize

The winning research groups will sign a research agreement with a duration of 18 months, having at their disposal an amount of 60,000 €, of which 40,000 € will be delivered in the year 2026 as an advance payment and 20,000 € in the year 2027 after the closing of the activities.

The objective is to develop the proposed solution to demonstrate its suitability and technical and economic feasibility.

18 meses

Convenio de investigación

60.000 €

En 2 fases

18 months

Research agreement

60.000 €

In 2 phases

How to register?

To register for the competition, please complete the following steps:

  1. Download the rules of the competition and the registration form from the top of the website.
  2. Fill out the registration form and send it to the email address listed in the rules of the competition (or click here).
  3. Once you receive the confirmation email, you have successfully registered for the competition!

¿What is ENAIRE?

In Spain, all aircrafts that take off, land or transit through its airspace receive communications, navigation and surveillance services through a modern and complete network of facilities operated by ENAIRE.

In the following infographic they show how air traffic control services are provided, according to the phases of a flight.

Some of Enaire's areas of interest
Safe and smooth air traffic
Environmentally sustainable air traffic

Drone traffic integration

Airspace design and organization

Traffic demand and capacity balancing

Automation

Artificial intelligence

Intermodal transportation