Archives Ouvertes HAL

Toutes les publications de l'ENAC en direct.
All ENAC publications.

[hal-02525149] A Rao-Blackwellized particle filter with variational inference for state estimation with measurement model uncertainties

Publications ENAC - Jeudi, 2 avril 2020 - 03:57:11
This paper develops a Rao-Blackwellized particle filter with variational inference for jointly estimating state and time-varying parameters in non-linear state-space models (SSM) with non-Gaussian measurement noise. Depending on the availability of the conjugate prior for the unknown parameters, the joint posterior distribution of the state and unknown parameters is approximated by using an auxiliary particle filter with a probabilistic changepoint model. The distribution of the SSM parameters conditionally on each particle is then updated by using variational Bayesian inference. Experiments are first conducted on a modified nonlinear benchmark model to compare the...

[hal-02521101] On the Use of Variational Adjoint Approach on Wide-Angle Approximation of Parabolic Equation with the Method of Split-Step Wavelet

Publications ENAC - Mardi, 31 mars 2020 - 11:22:12
This paper introduces a validation step for inferring atmosphere from RF data in an effort towards an 'refractivity from clutter' (RFC) system. The method retrieves the vertical refractive index distribution point-by-point in the lower troposphere from the measurements sampled in bistatic configuration. The new method utilizes wide-angle parabolic equation (WAPE) solved with the method of split-step wavelet (SSW) as the forward model, which is less computationally costly than the typical method used in the literature. The gradient of the cost function is estimated via the adjoint SSW solver developed by means of the variational adjoint approach. The high-dimensional...

[hal-02512103] Air Traffic Complexity Map based on Linear Dynamical Systems

Publications ENAC - Vendredi, 20 mars 2020 - 09:45:07
This paper presents a new air traffic complexity metric based on linear dy-namical systems, of which goal is to quantify the air traffic control difficulty. Previous works have shown that the structure and organization of air traffic are important factors in the perception of the complexity of an air traffic situation, but they usually were not able to explicitly address any pattern organization. The new metric, by identifying the organization properties of trajectories in a traffic pattern, captures some of the key factors involved in ATC complexity. The key idea of this work is to find a linear dynamical system which fits a vector field as closely as possible to the...

[hal-02508893] Synchronised Demand and Capacity Balancing in Collaborative Air Traffic Flow Management

Publications ENAC - Lundi, 16 mars 2020 - 12:45:14
This paper introduces a novel approach for synchronised demand and capacity balancing within a proposed Collaborative Air Traffic Flow Management framework. The approach is aimed to realise optimising traffic flow and scheduling airspace configuration in a more harmonised manner. Options such as delay assignment and alternative trajectories (generated and //////// shared submitted by Airspace Users) are intended for regulating the traffic flow. Airspace reconfiguration involves, on the other side, adjusting the opening schemes of predefined configurations, or creating new ones (if needed) through dynamic sectorisation. Results suggest that, using the proposed approach ,...

[hal-02506640] Door-to-door Air Travel Time Analysis in the United States using Uber Data

Publications ENAC - Vendredi, 13 mars 2020 - 16:44:43
NextGen and ACARE Flightpath 2050 set some ambitious goals for air travel, including improving the passenger travel experience using door-to-door travel times as a possible metric. Using recently released Uber data along with other online databases, a reliable estimation of door-to-door travel times is possible, which then enables a comparison of cities performance regarding the good integration of their airports as well as a per segment analysis of the full trip. This model can also be used to better evaluate where progress should and can be made with respect to air passenger travel experience.

[hal-02506611] Predicting Passenger Flow at Charles De Gaulle Airport Security Checkpoints

Publications ENAC - Vendredi, 13 mars 2020 - 15:18:53
Airport security checkpoints are critical areas in airport operations. Airports have to manage an important passenger flow at these checkpoints for security reason while maintaining service quality. The cost and quality of such an activity depend on the human resource management for these security operations. An appropriate human resource management can be obtained using an estimation of the passenger flow. This paper investigates the prediction at a strategic level of the passenger flows at Paris Charles De Gaulle airport security checkpoints using machine learning techniques such as Long Short-Term Memory neural networks. The derived models are compared to the current...

[hal-02506305] Aircraft atypical approach detection using functional principal component analysis

Publications ENAC - Vendredi, 13 mars 2020 - 15:09:30
In this paper, a post-operational detection method based on functional principal component analysis and clustering is presented and compared with regard to designed operational criteria. The methodology computes an atypical scoring on a sliding window. It enables not only to detect but also to localize where trajectories deviate statistically from the others. The algorithm is applied to the total energy management, estimated from ground-based data, during approach and landing. The detected atypical flights show non-nominal energy behaviors such as glide interceptions from above or high speed approaches. This promising methodology could help to enhance flight data...

[hal-02506741] Approach and landing aircraft on-board parameters estimation with LSTM networks

Publications ENAC - Vendredi, 13 mars 2020 - 14:38:45
This paper addresses the problem of estimating aircraft on-board parameters using ground surveillance available parameters. The proposed methodology consists in training supervised Neural Networks with Flight Data Records to estimate target parameters. This paper investigates the learning process upon three case study parameters: the fuel flow rate, the flap configuration, and the landing gear position. Particular attention is directed to the generalization to different aircraft types and airport approaches. From the Air Traffic Management point of view, these additional parameters enable a better understanding and awareness of aircraft behaviors. These estimations can...

[hal-02503796] X-Road: Virtual Reality Glasses for Orientation and Mobility Training of People with Visual Impairments

Publications ENAC - Jeudi, 12 mars 2020 - 02:41:57
Orientation and Mobility (O&M) classes teach people with visual impairments how to navigate the world, for instance how to cross a road. Yet, this training can be difficult and dangerous due to conditions such as traffic and weather. Virtual Reality (VR) can overcome these challenges by providing interactive controlled environments. However, most existing VR tools rely on visual feedback, which limits their use with students with visual impairment. In a collaborative design approach with O&M instructors, we designed an affordable and accessible VR system for O&M classes, called X-Road. Using a smartphone and a bespoke headmount, X-Road provides both visual...
Back to top