Archive ouverte de l'ENAC
Not a member yet
3458 research outputs found
Sort by
Test comparison for Sobol Indices over nested sets of variables
No full textSensitivity indices are commonly used to quantify the relative influence of any specific group of input variables on the output of a computer code. One crucial question is then to decide whether a given set of variables has a significant impact on the output. Sobol indices are often used to measure this impact but their estimation can be difficult as they usually require a particular design of experiment. In this work, we take advantage of the monotonicity of Sobol indices with respect to set inclusion to test the influence of some of the input variables. The method does not rely on a direct estimation of the Sobol indices and can be performed under classical iid sampling designs
Multi-label Classification of Aircraft Heading Changes using Neural Network to Resolve Conflicts
No full textInternational audienceAn aircraft conflict occurs when two or more aircraft cross at a certain distance at the same time. Aircraft heading changes are the common resolution at the en-route level (high altitude). One or more alternative heading changes are possible to resolve a single conflict. We consider this problem as a multi-label classification problem. We developed a multi-label classification model which provides multiple heading advisories for a given conflict. This model we named CRMLnet is based on the use of a multi-layer neural network that classifies all possible heading resolution in a multi-label classification manner. When compared to other machine learning models that use multiple single-label classifiers such as SVM, K-nearest, and LR, our CRMLnet achieves the best results with an accuracy of 98.72% and ROC of 0.999. The simulated data set which consists of conflict trajectories and heading resolutions we have developed and used in our experiments is delivered to the research community o n demand. It is freely accessible online at: https://independent.academia.edu/MDSIDDIQURRAHMAN
Event-based Extraction of Navigation Features from Unsupervised Learning of Optic Flow Patterns
No full textInternational audienceWe developed a Spiking Neural Network composed of two layers that processes event-based data captured by a dynamic vision sensor during navigation conditions. The training of the network was performed using a biologically plausible and unsupervised learning rule, Spike-Timing-Dependent Plasticity. With such an approach, neurons in the network naturally become selective to different components of optic flow, and a simple classifier is able to predict self-motion properties from the neural population output spiking activity. Our network has a simple architecture and a restricted number of neurons. Therefore, it is easy to implement on a neuromorphic chip and could be used for embedded applications necessitating low energy consumption
Application mobile d'aide à la navigation aérienne : une perspective de conception participative
No full textInternational audiencePiloting an aircraft takes place in a complex, changing and dynamic environment. It requires a rapid decision-making process as well as the mobilization of high-level cognitive capacities. For example, pilots have to select, process, and memorize a large flow of information. In this paper, we present the participatory design process we conducted to design a mobile navigation aid for pilots of light aircraft. This application allows pilots to prepare the flight, obtain information while flying and set alarms. We describe the iterative design process over two iterations of the prototype, including brainstorming sessions, co-design sessions, tests in flight simulators and a final test in an aircraft. We conclude with design recommandations which can be used for the design of future mobile navigation aid applications for aircraft. CCS CONCEPTS • Human-centered computing → HCI design and evaluation methods; Touch screens; Gestural input; Laboratory experiments.Le pilotage d’un avion s’inscrit dans un environnement complexe, changeant et dynamique, nécessitant un processus de prise de décisions rapide ainsi qu’une mobilisation des capacités cognitives de haut niveau. Les pilotes doivent par exemple sélectionner, traiter, et mémoriser un flot important d’informations. Dans cet article, nous présentons le processus de conception participative que nous avons mis en place pour concevoir une application mobile d'aide à la navigation pour les pilotes d'aviation générale. Cette application permet aux pilotes de préparer le vol en amont, obtenir des informations durant le vol et programmer des alarmes. Notre processus de conception comporte deux itérations de notre prototype, comprenant des séances de brainstorming, des séances de co-conception, des tests sur simulateurs de vol et un test final en conditions réelles dans un avion. Nous concluons par des recommandations de design qui peuvent être utilisées pour la conception de futures applications mobiles d'aide à la navigation aérienne
Field report: Deployment of a fleet of drones for cloud exploration
No full textInternational audienceDrones are commonly used for civil applications and are accessible to those with limited piloting skills in several scenarios. However, the deployment of a fleet in the context of scientific research can lead to complex situations that require an important preparation in terms of logistics, permission to fly from authorities, and coordination during the flights. This paper is a field report of the flight campaign held at the Barbados Island as part of the NEPHELAE project. The main objectives were to fly into trade wind cumulus clouds to understand the microphysical processes involved in their evolution, as well as to provide a proof of concept of sensor-based adaptive navigation patterns to optimize the data collection. After introducing the flight strategy and context of operation, the main challenges and the solutions to address them will be presented, to conclude with the evaluation of some technical evolution developed from these experiments
Project VILAGIL-MaaS: literature review: Towards personalization of a MaaS
No full textThis document concerns the MaaS (Mobility As A Service) action of the VILAGIL project and contains the literature review carried out by each partner (CLLE, ENAC, ONERA and UPS with IRIT-SEPIA team and IRIT-SMAC team) involved in this action.The objective of the MaaS research action is to develop innovative functionalities that can be integrated in a virtual mobility assistant in order to make it personalized. This assistant aims to proactively offer multimodal routes adapted to its user (according to his needs, mobility profile and mobility preferences) by informing him/her of the environmental impact of each proposed route
VETA: Visual eye-tracking analytics for the exploration of gaze patterns and behaviours
No full textInternational audienceEye tracking is growing in popularity for multiple application areas, yet analysing and exploring the large volume of complex data remains difficult for most users. We present a comprehensive eye tracking visual analytics system to enable the exploration and presentation of eye-tracking data across time and space in an efficient manner. The application allows the user to gain an overview of general patterns and perform deep visual analysis of local gaze exploration. The ability to link directly to the video of the underlying scene allows the visualisation insights to be verified on the fly. The system was motivated by the need to analyse eye-tracking data collected from an ‘in the wild’ study with energy network operators and has been further evaluated via interviews with 14 eye-tracking experts in multiple domains. Results suggest that, thanks to state-of-the-art visualisation techniques and by providing context with videos, our system could enable an improved analysis of eye-tracking data through interactive exploration, facilitating comparison between different participants or conditions, thus enhancing the presentation of complex data analysis to non-experts. This research paper provides four contributions: (1) analysis of a motivational use case demonstrating the need for rich visual-analytics workflow tools for eye-tracking data; (2) a highly dynamic system to visually explore and present complex eye-tracking data; (3) insights from our applied use case evaluation and interviews with experienced users demonstrating the potential for the system and visual analytics for the wider eye-tracking community
Can We Use EOG to Identify When Attention Switches Away from the Outside World to Focus on Our Mental Thoughts?
No full textInternational audienc
Long-endurance UAS operations translated to neuroergonomics
No full textInternational audienceUnmanned Aerial Systems (UASs) are now fully automated systems, which generates - as with most automated system- several issues inherent to their use including rolonged sessions, night working, and working environment physically detached from the flight conditions. Most importantly, they are becoming exceedingly capable of operating for extended periods of time, rendering operator mental fatigue into a serious issue as it affects a multitude of cognitive processes that are critical to the safe operation of UASs, including cognitive flexibility, attention and situational awareness (Chappelle et al., 018,Caid et al., 2016). Objective: The main objective of this study, placed within the context of French military UAS operations, is to report on preliminary work conducted in order to determine long-endurance UAS operations’ tasks and cognitive functions involved, specifically for the remote pilot. The idea is to gather insight from experts in the field on how time-on-task, and more generally mental fatigue, might impact the remote pilots’ cognitive functioning. Methods: In this preliminary work, the first step was to perform interviews for us to learn about UAS operations. We performed 3 interviews: one from aformer military UAS pilot, and two from high-ranked officers. Results: In this study, we will present a general description of potentially problematic cognitive states arising from prolonged operations in the activity of French UAS remote pilots. More precisely, we will present key elements extracted from these interviews regarding the impact of time-on-task on pilot functioning and link these with cognitive functions that might be impacted and that would explain the subjective experience of these experts.As could of course be expected the use of long-endurance UASs implies specific work conditions for the operators, namely shift work and night work for which pilots report that fatigue remains a major issue. Moreover, despite the high degree of automation within a UAS, a pilot’s mental workload may be strained when a monotonous and somnolent inducing mission is interrupted by an intense phase of high workload. Cognitive fatigue may result from these rapid and unexpected shifts in workload. Also,rapid and dynamic changing of mission objectives, so-called retask as well as the hanging of pilots within a mission, are unique challenges to UAS operations. In both cases maintaining and regaining situational awareness following such an event are particular challenges to pilots. Hence, following this preliminary assessment of experts’ reports on UAS pilots’ experiences with long-duration missions, one of the main issues that we deemed as critical and that will lead to subsequent experimental work is studying the effect of time-on-task on cognitive flexibility. Perspectives: In addition to currently developing a laboratory task resembling UAS pilot operations thanks to the Paparazzi software (Brisset et al., 2006), a fundamental task is also under development to precisely determine the extend to which timeon-task affects cognitive flexibility, and a comprehensive assessment thanks to the neuroergonomics approach is planned later on with the view to enhance piloting experience and increase both safety and performance of UAS operations