Periodic Reporting for period 2 - AISA (AI Situational Awareness Foundation for Advancing Automation)
Período documentado: 2021-06-01 hasta 2022-11-30
Current air traffic throughput for a given sector is constrained by ATCO workload. Increased number of aircraft causes controller’s workload to rise to the level where it is possible for ATCO to lose situational awareness (SA) which leads to unsafe operations. Demand capacity balancing (DCB) measures are then employed to reduce the workload on individual ATCOs, and ATFM delay is thus created. Automation is one of the most promising solutions for the capacity problem, however, to implement advanced automation concepts it is required that the AI and human are able to share the situational awareness. Therefore, sharing the same team situational awareness will enable the automated system to reach the same conclusions as ATCOs when confronted with the same problem and to be able to explain the reasoning behind those conclusions.
Exploring the effect of, and opportunities for, distributed human-machine situational awareness in en-route ATC operations was one of the main objectives of this project. Instead of automating isolated individual tasks, such as conflict detection or coordination, we proposed building a foundation for automation by developing an intelligent situationally-aware system.
The machine situational awareness achieved by the AISA system was shown to have sufficient accuracy for a proof-of-concept system. The system provided ATCOs with additional support since it enhanced their situational awareness which allowed them to preserve it regardless of the traffic situation. Most of the planned monitoring tasks for the AISA system have been developed and were fully functional. This project also brought together the unification of existing aeronautical exchange models and additionally identified knowledge to represent concepts relevant in en-route Air Traffic Control. This methodology and the accompanying tool are general and applicable to anyone interested in utilizing the same approach.
Exploring the effect of, and opportunities for, distributed human-machine situational awareness in en-route ATC operations was one of the main objectives of this project. Instead of automating isolated individual tasks, such as conflict detection or coordination, we proposed building a foundation for automation by developing an intelligent situationally-aware system.
The machine situational awareness achieved by the AISA system was shown to have sufficient accuracy for a proof-of-concept system. The system provided ATCOs with additional support since it enhanced their situational awareness which allowed them to preserve it regardless of the traffic situation. Most of the planned monitoring tasks for the AISA system have been developed and were fully functional. This project also brought together the unification of existing aeronautical exchange models and additionally identified knowledge to represent concepts relevant in en-route Air Traffic Control. This methodology and the accompanying tool are general and applicable to anyone interested in utilizing the same approach.
During the second reporting period, several meetings and a workshop were held for the AISA project. The AISA Advisory Board (AB) met on September 20, 2021 and the AB and consortium members participated in a risk assessment workshop on March 8, 2022. Members of the SESAR 3 Joint Undertaking (S3JU) were invited to and participated in a steering board meeting on May 13, 2022 where project results were discussed. The final review meeting (FRM) was held in Brussels on June 30, 2022 and a follow-up meeting via Webex was held on July 19, 2022 to discuss project achievements and Technology Readiness Level criteria fulfillment. The final AISA workshop was held at the 12th European Aeronautics Science Network International Conference in Barcelona on October 20, 2022. The project's close-out meeting on November 25, 2022 marked the end of project activities.
Task 2.1 and D2.1 developed a Concept of Operations (ConOps) for en-route air traffic control (ATC) performed by a human-machine team with shared situational awareness (SA). Task 2.2 analyzed requirements for automation of monitoring tasks via AI SA, showing which tasks can be automated and what requirements are needed. Task 3.1 developed a 4D trajectory prediction module using a neural network and a two-step approach. Task 3.2 developed a Conflict Detection module, which performed well in identifying errors but needed further research. Task 3.3 developed a complexity assessment model to determine air traffic complexity. Task 4.1-4.4 focused on creating a knowledge graph system in Java, connecting it with Prolog, and encoding facts and rules about ATC operations. Task 5.1 evaluated SA among AI and ATCOs through various measurement tools in Experiment 1 and Experiment 2. Task 5.2 conducted a risk assessment of the AI SA system and proposed measures to ensure safety. Task 5.3 evaluated the impact of AI system on human performance in distributed SA, showing high accuracy for most tasks, particularly for conflict detection.
The project has successfully developed a Proof-of-Concept (PoC) knowledge-based system for automating en-route air traffic control (ATC) tasks. Most of the ATCO tasks chosen in the project's ConOps were successfully automated, tested, and applied to traffic data (46 out of 57 tasks), with a focus on monitoring tasks but also including some tasks that involve prediction and decision-making. This has laid the foundation for further automation within the human-machine ATCO team.
The accuracy of the PoC system was deemed very high according to an analysis of its performance, and it was concluded that there is great potential for real-time operation considering it takes about 5 seconds to process a single traffic situation graph, which is similar to the refresh rate of an ATCO's working position. Machine learning (ML) modules were partially integrated into the system, with the conflict detection module showing an accuracy of 70%.
Different assessments of situation awareness (SA) were completed, including assessments of human SA, machine (or artificial) SA, and team SA. The results of these assessments showed that ATCOs are more critical in judging their own SA when they are aware of machine SA, and that inputs from the AI SA system might be beneficial for ATCOs in terms of SA with some minor adjustments, such as providing warnings for important time-critical aspects and providing other information in a more passive manner. Machine SA was assessed through the system's properties and functions and through comparison with human SA, and the results indicated that the ML modules can predict the future state of traffic.
Overall, the PoC system has shown promising results in terms of automating ATC tasks and improving SA within the ATCO team.
Task 2.1 and D2.1 developed a Concept of Operations (ConOps) for en-route air traffic control (ATC) performed by a human-machine team with shared situational awareness (SA). Task 2.2 analyzed requirements for automation of monitoring tasks via AI SA, showing which tasks can be automated and what requirements are needed. Task 3.1 developed a 4D trajectory prediction module using a neural network and a two-step approach. Task 3.2 developed a Conflict Detection module, which performed well in identifying errors but needed further research. Task 3.3 developed a complexity assessment model to determine air traffic complexity. Task 4.1-4.4 focused on creating a knowledge graph system in Java, connecting it with Prolog, and encoding facts and rules about ATC operations. Task 5.1 evaluated SA among AI and ATCOs through various measurement tools in Experiment 1 and Experiment 2. Task 5.2 conducted a risk assessment of the AI SA system and proposed measures to ensure safety. Task 5.3 evaluated the impact of AI system on human performance in distributed SA, showing high accuracy for most tasks, particularly for conflict detection.
The project has successfully developed a Proof-of-Concept (PoC) knowledge-based system for automating en-route air traffic control (ATC) tasks. Most of the ATCO tasks chosen in the project's ConOps were successfully automated, tested, and applied to traffic data (46 out of 57 tasks), with a focus on monitoring tasks but also including some tasks that involve prediction and decision-making. This has laid the foundation for further automation within the human-machine ATCO team.
The accuracy of the PoC system was deemed very high according to an analysis of its performance, and it was concluded that there is great potential for real-time operation considering it takes about 5 seconds to process a single traffic situation graph, which is similar to the refresh rate of an ATCO's working position. Machine learning (ML) modules were partially integrated into the system, with the conflict detection module showing an accuracy of 70%.
Different assessments of situation awareness (SA) were completed, including assessments of human SA, machine (or artificial) SA, and team SA. The results of these assessments showed that ATCOs are more critical in judging their own SA when they are aware of machine SA, and that inputs from the AI SA system might be beneficial for ATCOs in terms of SA with some minor adjustments, such as providing warnings for important time-critical aspects and providing other information in a more passive manner. Machine SA was assessed through the system's properties and functions and through comparison with human SA, and the results indicated that the ML modules can predict the future state of traffic.
Overall, the PoC system has shown promising results in terms of automating ATC tasks and improving SA within the ATCO team.
The expected outcome of the project is to explore the principles to develop the AI situationally aware system as a foundation for automation in en-route ATC operations. More specifically, the developed automated system will reach the same conclusions as ATCOs when confronted with the same problem through sharing the same team situational awareness (TSA) among ATCO team members and AI. In this way, the artificial situational awareness system will be the enabler of future advanced automation based on machine learning. This is the innovative approach where distributed human-machine situational awareness (team situational awareness) will serve as a basis for the automating monitoring tasks in en-route operations while combining machine learning (ML) with knowledge graph system.
Summarized project results are as follows:
• Development of principles for the AI Situational Awareness System
• Development of human-machine SA concept
• Development of modules for translation of selected aeronautical data into knowledge graph
• Creation of components of the ATC-specific knowledge graph
• Development of reasoning engine
• Concept assessment.
The potential and expected impact of the project is the development of principles that could enable a higher level of automation with direct positive effects on safety and capacity. Indirectly will this approach have a positive impact on all performance areas and by improving them, positive impacts can be expected in the society due to reduced costs of air traffic.
Summarized project results are as follows:
• Development of principles for the AI Situational Awareness System
• Development of human-machine SA concept
• Development of modules for translation of selected aeronautical data into knowledge graph
• Creation of components of the ATC-specific knowledge graph
• Development of reasoning engine
• Concept assessment.
The potential and expected impact of the project is the development of principles that could enable a higher level of automation with direct positive effects on safety and capacity. Indirectly will this approach have a positive impact on all performance areas and by improving them, positive impacts can be expected in the society due to reduced costs of air traffic.