Archive ouverte de l'ENAC
Not a member yet
3458 research outputs found
Sort by
Optimising security screening resources during airport access mode disruptions
No full textInternational audienceAirport access mode disruptions have a significant impact on passenger arrival times and thus on congestion level at security screening systems. During such events, information sharing between ground and air transportation stakeholders could be a key lever to optimize airport operations at a tactical level. In this work, an online reallocation of airport security teams across the different security screening checkpoints is considered. Three integer linear programming formulations of the problem are proposed to increase the level of service of an airport when a disruption occurs. A study case based on one day of operations at Paris-Charles de Gaulle airport is considered. Results show that reallocating airport security staff when outbound passengers are delayed could significantly improve airport security system performances. The different allocations obtained lead to a drop in the maximum waiting time up to 72%. In addition, the average waiting time and the number of stranded passengers at the airport are reduced
Micro-drone autopilot architecture for efficient static scheduling
No full textInternational audienceThis paper presents the internal architecture of a Modifiable Off-the-Shelf open-source autopilot. We show starting from a set of functional and hardware requirements why most autopilots use as a core thread a main loop acting as a nonpreemptive static scheduler, reacting to external events, some solicited, some unsolicited (but expected). We explain how the type of bus used to communicate with the sensor impacts the nature of the events received from the sensors (solicited or not). We show that depending on the workload that a main loop iteration has to handle, the execution time of an iteration can be larger than the period, creating potential delays in the attitude correction. Finally, we explore the degrees of freedom that can be used to reduce the impact of these overloads by smoothing the periodic workload
Reading detection of needle-type instrument in a noisy environment using computer vision-based algorithms
No full textInternational audienceThis study investigated the use of computer vision-based algorithms for detecting needle-type instrument readings in the cockpit of an aerial vehicle. A flight data recorder plays a crucial role in aviation safety investigations and flight operation review. In practice, not all aerial vehicles are equipped with flight data recorders, and this poses problems in the retrieval of instrument readings during investigations. Installing a lightweight recorder such as a camera in the cockpit to record the instrument panel is a solution to the mentioned problem. Although recorded flight data can be retrieved through human inspection, computer vision-based algorithms enable more rapid and efficient detection. Accordingly, this study developed two computer vision-based algorithms operated in both of the grayscale color space and the value layer of the hue-saturation-value color space. Performance of the four combinations is then compared and the best combination of algorithm along with operation space is suggested. The airspeed meter of a Bell 206 helicopter was selected to test the proposed detection algorithm in this study. GPS data and human inspection results were used as references. Herein, experimental results are presented, performance of algorithms is discussed, and conclusions are provided. This study contributes to aviation safety investigations and flight operation review involving aerial vehicles that are not equipped with flight data recorders
Scheduling Offset-Free Systems Under FIFO Priority Protocol
No full textInternational audienceOn UAVs, telemetry messages are often sent following a FIFO schedule, and some messages, depending on the FIFO queue state may suffer long delays, and can even be lost if the FIFO queue is full. Considering the high complexity of the problem of assigning offsets to periodic tasks, we propose a new heuristic, called GCD+, that we compare to the methods of the state of the art, showing that GCD+ significantly outperforms them on synthetic tasks sets. Then we use a real UAV use case, based on Paparazzi autopilot, to show that GCD+ behaves well. The proposed algorithm is meant to be the new Paparazzi's automatic offset assignment method for messages
Apprentissage d'un modèle d'incertitude de la prévision de trajectoire pour le contrôle aérien en-route
No full textInternational audienceApprentissage d'un modèle d'incertitude de la prévision de trajectoire pour le contrôle aérien en-rout
Deviation results for sparse tables in hashing with linear probing
No full textInternational audienceWe consider the model of hashing with linear probing and we establish the moderate and large deviations for the total displacement in sparse tables. In this context, Weibull-like-tailed random variables appear. Deviations for sums of such heavy-tailed random variables are studied in \cite{Nagaev69-1,Nagaev69-2}. Here we adapt the proofs therein to deal with conditioned sums of such variables and solve the open question in \cite{TFC12}. By the way, we establish the deviations of the total displacement in full tables, which can be derived from the deviations of empirical processes of i.i.d.\ random variables established in \cite{Wu94}.
PROCEDE DE SURVEILLANCE D'UN SYSTEME, DISPOSITIFS, SYSTEME ET PROGRAMME CORRESPONDANT
No full textL'invention se rapporte plus particulièrement à la surveillance de comportement de dispositifs, et plus particulièrement de dispositifs en mouvement au sein d'un environnement donné
A Survey on Artificial Intelligence (AI) and eXplainable AI in Air Traffic Management: Current Trends and Development with Future Research Trajectory
No full textInternational audienceAir Traffic Management (ATM) will be more complex in the coming decades due to the growth and increased complexity of aviation and has to be improved in order to maintain aviation safety. It is agreed that without significant improvement in this domain, the safety objectives defined by international organisations cannot be achieved and a risk of more incidents/accidents is envisaged. Nowadays, computer science plays a major role in data management and decisions made in ATM. Nonetheless, despite this, Artificial Intelligence (AI), which is one of the most researched topics in computer science, has not quite reached end users in ATM domain. In this paper, we analyse the state of the art with regards to usefulness of AI within aviation/ATM domain. It includes research work of the last decade of AI in ATM, the extraction of relevant trends and features, and the extraction of representative dimensions. We analysed how the general and ATM eXplainable Artificial Intelligence (XAI) works, analysing where and why XAI is needed, how it is currently provided, and the limitations, then synthesise the findings into a conceptual framework, named the DPP (Descriptive, Predictive, Prescriptive) model, and provide an example of its application in a scenario in 2030. It concludes that AI systems within ATM need further research for their acceptance by end-users. The development of appropriate XAI methods including the validation by appropriate authorities and end-users are key issues that needs to be addressed
Détection d'intrusion dans une flotte de drones
No full textIn recent years, the development of the Unmanned Aerial System (UAS) involving swarms of unmanned aerial vehicles (UAVs) has experienced unprecedented progress. However, network systems implemented in current commercial UASs are often variations of existing network systems. Thus, pre-existing vulnerabilities may still exist, while new vulnerabilities emerging from the new properties of a UAS, such as mobility and interconnectivity, are of even greater concern. As UASs operate in civilian airspace, safety and security are essential.This thesis was created in response to growing demand. In this thesis report, three strategies are explored to seek to resolve different attacks that we would expect to observe in a UAS.The first part of the thesis involves the use of cybernetic theories: robust observation techniques to achieve robust detection of anomalies in a TCP (Transmission Control Protocol) network. Work focused on the design of a robust observer based on the Lyapunov-Krasovkii functional and queuing dynamics of an Active Queue Management system in a TCP network. By exploiting the dynamics of the TCP network, which contains AQM, we can distinguish anomalous network traffic.The second part of the thesis consists in using the multifractal theory to identify the traffics presenting an anomaly. Work focused on designing a working prototype of an IDS based on Wavelet Leader Multifractal (WLM) analysis to identify anomalies such as network congestion generated by a DoS attack. In the experiment, we observe that the WLM signature of a simulated UAS network can be radically different between normal traffic and traffic affected by a DoS attack. By applying a simple analytical comparison between the different signatures, we can identify traffic with or without attack.The third part of the thesis consists in using artificial intelligence (AI) to improve detection performance. We introduced a long short-term memory (LSTM) classification network (and other neural networks) to increase detection accuracy. Here, instead of targeting an obvious attack, such as the DoS attack, we turned our attention to a more delicate attack, such as the Man in the Middle (MITM) attack. By adapting WLM analysis and Machine Learning principles, we have found that it is possible to achieve a promising level of detection for an spoofing attack on the geographic coordinates of individual UAVs in a simulated UAS network.Ces dernières années, le développement du système aérien sans pilote (UAS) impliquant des essaims de véhicules aériens sans pilote (UAV) a connu des progrès sans précédent. Cependant, les systèmes de réseau mis en œuvre dans les UAS commerciaux actuels sont souvent des variantes des systèmes de réseau existants. Ainsi, des vulnérabilités préexistantes peuvent persister, tandis que de nouvelles vulnérabilités émergeant des nouvelles propriétés des UAS, telles que la mobilité et l'interconnectivité, sont encore plus préoccupantes. Étant donné que les UAS opèrent dans l'espace aérien civil, la sûreté et la sécurité sont essentielles.Cette thèse a été créée en réponse à une demande croissante. Dans ce rapport de thèse, trois stratégies sont explorées pour chercher à résoudre différentes attaques que l'on peut s'attendre à observer dans un UAS.La première partie de la thèse implique l'utilisation de théories cybernétiques : des techniques d'observation robustes pour réaliser une détection robuste d'anomalies dans un réseau TCP (Transmission Control Protocol). Les travaux se sont concentrés sur la conception d'un observateur robuste basé la méthode des fonctionnelles de Lyapunov-Krasovkii et d'un système de gestion de file d'attente active (AQM) dans un réseau TCP. En exploitant la dynamique du réseau TCP, nous pouvons détecter un trafic réseau anormal.La deuxième partie de la thèse utilise la théorie multifractale pour identifier les trafics présentant une anomalie. Les travaux se sont concentrés sur la conception d'un prototype d'IDS fonctionnel basé sur l'analyse Wavelet Leader Multifractal (WLM) pour identifier des anomalies telles que la congestion du réseau générée par une attaque DoS. Dans l'expérience, nous observons que la signature WLM d'un réseau UAS simulé peut être radicalement différente entre un trafic normal et un trafic affecté par une attaque DoS. Par une simple comparaison analytique entre les différentes signatures, nous pouvons identifier le trafic avec ou sans attaque.La troisième partie de la thèse consiste à utiliser l'intelligence artificielle (IA) pour améliorer les performances de détection. Nous avons introduit un réseau de classification Long Short-Term memory (LSTM) (et d'autres réseaux de neurones) pour augmenter la qualité de détection. Ici, au lieu de cibler une attaque évidente, telle que l'attaque DoS, nous avons tourné notre attention vers une attaque plus délicate, telle que l'attaque Man in the Middle (MITM). En adaptant l'analyse WLM et les principes d'apprentissage automatique, nous avons constaté qu'il est possible d'atteindre un niveau de détection prometteur pour une attaque de falsification des coordonnées géographiques des drones dans un réseau UAS simulé