Tunnel Gaussian Process Model for Learning Interpretable Flight’s Landing Parameters
- 1 December 2021
- journal article
- research article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Guidance, Control, and Dynamics
- Vol. 44 (12), 2263-2275
- https://doi.org/10.2514/1.g005802
Abstract
Approach and landing accidents have resulted in a significant number of hull losses worldwide. Technologies (e.g., instrument landing system) and procedures (e.g., stabilized approach criteria) have been developed to reduce the risks. This paper proposes a data-driven method to learn and interpret flight’s approach and landing parameters to facilitate comprehensible and actionable insights into flight dynamics. Specifically, two variants of tunnel Gaussian process (TGP) models are developed to elucidate aircraft’s approach and landing dynamics using advanced surface movement guidance and control system (A-SMGCS) data, which then indicates the stability of flight. TGP hybridizes the strengths of sparse variational Gaussian process and polar Gaussian process to learn from a large amount of data in cylindrical coordinates. This paper examines TGP qualitatively and quantitatively by synthesizing three complex trajectory datasets and compared TGP against existing methods on trajectory learning. Empirically, TGP demonstrates superior modeling performance. When applied to operational A-SMGCS data, TGP provides the generative probabilistic description of landing dynamics and interpretable tunnel views of approach and landing parameters. These probabilistic tunnel models can facilitate the analysis of procedure adherence and augment existing aircrew and air traffic controller’ displays during the approach and landing procedures, enabling necessary corrective actions.Keywords
Funding Information
- National Research Foundation, Singapore, and the Civil Aviation Authority of Singapore
This publication has 25 references indexed in Scilit:
- Stability Analysis of Runway SchedulesIEEE Transactions on Intelligent Transportation Systems, 2016
- Anomaly detection via a Gaussian Mixture Model for flight operation and safety monitoringTransportation Research Part C: Emerging Technologies, 2016
- Polar Gaussian Processes and Experimental Designs in Circular DomainsSIAM/ASA Journal on Uncertainty Quantification, 2016
- GP-DEMO: Differential Evolution for Multiobjective Optimization based on Gaussian Process modelsEuropean Journal of Operational Research, 2015
- Multiphase Mixed-Integer Optimal Control Approach to Aircraft Trajectory OptimizationJournal of Guidance, Control, and Dynamics, 2013
- Multi-output separable Gaussian process: Towards an efficient, fully Bayesian paradigm for uncertainty quantificationJournal of Computational Physics, 2013
- Remote Sensing of Vegetation Structure Using Computer VisionRemote Sensing, 2010
- Algorithm for Conformance Monitoring in Air Traffic ControlJournal of Guidance, Control, and Dynamics, 2010
- Graphical Models, Exponential Families, and Variational InferenceFoundations and Trends® in Machine Learning, 2007
- A-SMGCS routing and guidance functionsIEEE Aerospace and Electronic Systems Magazine, 2000