Data-Driven Modeling of Air Traffic Controllers’ Policy to Resolve Conflicts

With the aim to enhance automation in conflict detection and resolution (CD&R) tasks in the air traffic management (ATM) domain, this article studies the use of artificial intelligence and machine learning (AI/ML) methods to learn air traffic controllers’ (ATCOs) policy in resolving conflicts among aircraft assessed to violate separation minimum constraints during the en route phase of flights, in the tactical phase of operations. The objective is to model how conflicts are being resolved by ATCOs. Towards this goal, the article formulates the ATCO policy learning problem for conflict resolution, addresses the challenging issue of an inherent lack of information in real-world data, and presents AI/ML methods that learn models of ATCOs’ behavior. The methods are evaluated using real-world datasets. The results show that AI/ML methods can achieve good accuracy on predicting ATCOs’ actions given specific conflicts, revealing the preferences of ATCOs for resolution actions in specific circumstances. However, the high accuracy of predictions is hindered by real-world data-inherent limitations.

[1]  G. Vouros,et al.  Data-driven prediction of Air Traffic Controllers reactions to resolving conflicts , 2022, Inf. Sci..

[2]  Laura Wynter,et al.  A Deep Ensemble Method for Multi-Agent Reinforcement Learning: A Case Study on Air Traffic Control , 2021, ICAPS.

[3]  Pheng-Ann Heng,et al.  Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise , 2020, AAAI.

[4]  Hwanjun Song,et al.  Learning From Noisy Labels With Deep Neural Networks: A Survey , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[5]  James Bailey,et al.  Normalized Loss Functions for Deep Learning with Noisy Labels , 2020, ICML.

[6]  Joost Ellerbroek,et al.  Review of Conflict Resolution Methods for Manned and Unmanned Aviation , 2020, Aerospace.

[7]  E. van Kampen,et al.  Toward Individual-Sensitive Automation for Air Traffic Control Using Convolutional Neural Networks , 2020, Journal of Air Transportation.

[8]  Laura Wynter,et al.  A Deep Ensemble Multi-Agent Reinforcement Learning Approach for Air Traffic Control , 2020, ArXiv.

[9]  Thomas Brox,et al.  SELF: Learning to Filter Noisy Labels with Self-Ensembling , 2019, ICLR.

[10]  Eder Santana,et al.  Exploring the Limitations of Behavior Cloning for Autonomous Driving , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[11]  Sim Kuan Goh,et al.  An Intelligent Interactive Conflict Solver Incorporating Air Traffic Controllers' Preferences Using Reinforcement Learning , 2019, 2019 Integrated Communications, Navigation and Surveillance Conference (ICNS).

[12]  Sim Kuan Goh,et al.  Reinforcement Learning for Two-Aircraft Conflict Resolution in the Presence of Uncertainty , 2019, 2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF).

[13]  Hanan Samet,et al.  Prescriptive analytics system for long-range aircraft conflict detection and resolution , 2018, SIGSPATIAL/GIS.

[14]  Ivor W. Tsang,et al.  Masking: A New Perspective of Noisy Supervision , 2018, NeurIPS.

[15]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[16]  Esther Calvo-Fernández,et al.  Conflict-Free Trajectory Planning Based on a Data-Driven Conflict-Resolution Model , 2017 .

[17]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[18]  Sotiris B. Kotsiantis,et al.  Decision trees: a recent overview , 2011, Artificial Intelligence Review.

[19]  Marcel Mongeau,et al.  A light-propagation model for aircraft trajectory planning , 2012, Journal of Global Optimization.

[20]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[21]  J. Friedman.  Stochastic gradient boosting , 2002 .

[22]  Shun-ichi Amari,et al.  Backpropagation and stochastic gradient descent method , 1993, Neurocomputing.

[23]  Chen Gong,et al.  Robust early-learning: Hindering the memorization of noisy labels , 2021, ICLR.

[24]  R. Tamassia,et al.  Prescriptive Analytics System for Long-Range Aircraft Conflict Detection and Resolution , 2018 .

[25]  Daniel Delahaye,et al.  Large-Scale 4D Trajectory Planning , 2017 .

[26]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[27]  Nicolas Durand,et al.  Genetic Algorithms Applied to Air Traffic Management , 2006 .

[28]  Heinz Erzberger,et al.  Automated Conflict Resolution For Air Traffic Control , 2005 .

[29]  Chao Chen,et al.  Using Random Forest to Learn Imbalanced Data , 2004 .

[30]  L. Breiman.  Random Forests , 2001, Machine Learning.

[31]  Christopher M. Bishop,et al.  Regularization and complexity control in feed-forward networks , 1995 .

[32]  E. Clothiaux,et al.  Neural Networks and Their Applications , 1994 .

[33]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .