Academic literature on the topic 'Drones autonomes'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Drones autonomes.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Drones autonomes"
1
Noizet, Thomas. "Les essaims de drones, graal ou chimère ?" Revue Défense Nationale N° Hors-série, HS13 (September 20, 2023): 239–56. http://dx.doi.org/10.3917/rdna.hs13.0239.
Full textAbstract:
Dronisation et intelligence artificielle convergent aujourd’hui, donnant progressivement naissance à ce qu’il est convenu d’appeler des « essaims ». Les récents conflits renforcent l’idée que ces systèmes – y compris les essaims létaux – présentent un intérêt militaire. Ils feront partie demain des capacités amies et ennemies. Celui qui en sera doté disposera d’un avantage certain. Cependant, leur développement implique de consentir à une forme d’autonomie, ce qui suscite de nombreuses questions. Notre pays sera guidé par sa vision de l’éthique d’emploi des essaims et des armes dites « autonomes ». Pour autant, il convient d’avancer de manière résolue dans la voie des essaims, y compris vers les essaims armés.
2
Abergel, Violette, Renato Saleri, and Hervé Lequay. "Vecteurs aériens téléopérés pour l'acquisition de données spatiales d'objets patrimoniaux, Retour d'expérience." Revue Française de Photogrammétrie et de Télédétection, no. 213 (April 27, 2017): 73–79. http://dx.doi.org/10.52638/rfpt.2017.363.
Full textAbstract:
Le relevé aérien constitue, dans le domaine de l'archéologie et de l'architecture, un vaste champ d'applications et d'intérêt. Au-delà des capacités croissantes des drones existants, le potentiel opérationnel de tels outils dépasse aujourd'hui l'imagination de leur propres créateurs : initialement conçus dans le secteur de la robotique civile et militaire, de récentes expérimentations ont pu tester le vol autonome, la prise de décision automatique, ainsi que l'intelligence distribuée.Avec près de dix ans d'expérience dans le domaine du relevé aérien, le laboratoire MAP a expérimenté un large panel de vecteurs aériens, pilotés ou semi-autonomes, équipés de capteurs de différentes natures, à des fns de télédétection et d'acquisition de données spatiales, ce travail étant principalement dévolu à la modélisation et à la simulation d'environnements 3D à haute valeur patrimoniale. Les compétences du MAP concernent donc la mobilisation de vecteurs aériens sans équipage, mais aussi le développement d'outils experts pour la modélisation et représentation 3D ou encore les protocoles d'analyse d'image dans le domaine de l'architecture, de l'urbanisme et du paysage.
3
Yulianto, Ahmad Wilda, Dhandi Yudhit Yuniar, and Yoyok Heru Prasetyo. "Navigation and Guidance for Autonomous Quadcopter Drones Using Deep Learning on Indoor Corridors." Jurnal Jartel Jurnal Jaringan Telekomunikasi 12, no. 4 (December 30, 2022): 258–64. http://dx.doi.org/10.33795/jartel.v12i4.422.
Full textAbstract:
Autonomous drones require accurate navigation and localization algorithms to carry out their duties. Outdoors drones can utilize GPS for navigation and localization systems. However, GPS is often unreliable or not available at all indoors. Therefore, in this research, an autonomous indoor drone navigation model was created using a deep learning algorithm, to assist drone navigation automatically, especially in indoor corridor areas. In this research, only the Caddx Ratel 2 FPV camera mounted on the drone was used as an input for the deep learning model to navigate the drone forward without a collision with the wall in the corridor. This research produces two deep learning models, namely, a rotational model to overcome a drone's orientation deviations with a loss of 0.0010 and a mean squared error of 0.0009, and a translation model to overcome a drone's translation deviation with a loss of 0.0140 and a mean squared error of 0.011. The implementation of the two models on autonomous drones reaches an NCR value of 0.2. The conclusion from the results obtained in this research is that the difference in resolution and FOV value in the actual image captured by the FPV camera on the drone with the image used for training the deep learning model results in a discrepancy in the output value during the implementation of the deep learning model on autonomous drones and produces low NCR implementation values.
4
Rodriguez, Angel A., Mohammad Shekaramiz, and Mohammad A. S. Masoum. "Computer Vision-Based Path Planning with Indoor Low-Cost Autonomous Drones: An Educational Surrogate Project for Autonomous Wind Farm Navigation." Drones 8, no. 4 (April 17, 2024): 154. http://dx.doi.org/10.3390/drones8040154.
Full textAbstract:
The application of computer vision in conjunction with GPS is essential for autonomous wind turbine inspection, particularly when the drone navigates through a wind farm to detect the turbine of interest. Although drones for such inspections use GPS, our study only focuses on the computer vision aspect of navigation that can be combined with GPS information for better navigation in a wind farm. Here, we employ an affordable, non-GPS-equipped drone within an indoor setting to serve educational needs, enhancing its accessibility. To address navigation without GPS, our solution leverages visual data captured by the drone’s front-facing and bottom-facing cameras. We utilize Hough transform, object detection, and QR codes to control drone positioning and calibration. This approach facilitates accurate navigation in a traveling salesman experiment, where the drone visits each wind turbine and returns to a designated launching point without relying on GPS. To perform experiments and investigate the performance of the proposed computer vision technique, the DJI Tello EDU drone and pedestal fans are used to represent commercial drones and wind turbines, respectively. Our detailed and timely experiments demonstrate the effectiveness of computer vision-based path planning in guiding the drone through a small-scale surrogate wind farm, ensuring energy-efficient paths, collision avoidance, and real-time adaptability. Although our efforts do not replicate the actual scenario of wind turbine inspection using drone technology, they provide valuable educational contributions for those willing to work in this area and educational institutions who are seeking to integrate projects like this into their courses, such as autonomous systems.
5
Martin, Olivier, Christophe Meynard, Marc Pierrot-Deseilligny, Jean-Philippe Souchon, and Christian Thom. "Réalisation d'une caméra photogrammétrique ultralégère et de haute résolution." Revue Française de Photogrammétrie et de Télédétection, no. 213 (April 26, 2017): 3–9. http://dx.doi.org/10.52638/rfpt.2017.200.
Full textAbstract:
Ces dernières années, l'IGN a participé à des expériences de photogrammétrie très haute résolution au coursdesquelles des appareils photo numérique (APN) ont été utilisés sur différents types de drones. Cela nous a permisd'affiner les caractéristiques techniques importantes que devrait proposer une nouvelle caméra photogrammétrique ultralégèreet de très haute résolution dédiée à ce type d'application. Le LOEMI, laboratoire en instrumentation de l’IGN, fortde l'expérience qu'il a acquise en concevant et réalisant les caméras aériennes numériques de l'IGN, s'est lancé dans laconception de ce nouvel imageur en 2012 après avoir étudié les possibilités offertes par le marché en termes de capteuret de composant "cerveau" de la caméra. La caméra sera basée sur un capteur CMOS et son électronique d'acquisitionet de traitements sur un SoC+FPGA de la société Xilinx. Grâce à la conception modulaire du dispositif, on pourradisposer, en fonction du porteur utilisé, de configurations plus ou moins autonomes et donc plus ou moins lourdes, ouavec plus ou moins de connectivité ou de capteurs annexes. La configuration la plus légère sera constituée du seul"étage imageur" dont une version est, en ce début 2014, en cours de test. Les premiers prototypes fonctionnelsdevraient être réalisés d'ici la fin de l'année 2014.
6
Rojas-Perez, Leticia Oyuki, and Jose Martinez-Carranza. "DeepPilot: A CNN for Autonomous Drone Racing." Sensors 20, no. 16 (August 13, 2020): 4524. http://dx.doi.org/10.3390/s20164524.
Full textAbstract:
Autonomous Drone Racing (ADR) was first proposed in IROS 2016. It called for the development of an autonomous drone capable of beating a human in a drone race. After almost five years, several teams have proposed different solutions with a common pipeline: gate detection; drone localization; and stable flight control. Recently, Deep Learning (DL) has been used for gate detection and localization of the drone regarding the gate. However, recent competitions such as the Game of Drones, held at NeurIPS 2019, called for solutions where DL played a more significant role. Motivated by the latter, in this work, we propose a CNN approach called DeepPilot that takes camera images as input and predicts flight commands as output. These flight commands represent: the angular position of the drone’s body frame in the roll and pitch angles, thus producing translation motion in those angles; rotational speed in the yaw angle; and vertical speed referred as altitude h. Values for these 4 flight commands, predicted by DeepPilot, are passed to the drone’s inner controller, thus enabling the drone to navigate autonomously through the gates in the racetrack. For this, we assume that the next gate becomes visible immediately after the current gate has been crossed. We present evaluations in simulated racetrack environments where DeepPilot is run several times successfully to prove repeatability. In average, DeepPilot runs at 25 frames per second (fps). We also present a thorough evaluation of what we called a temporal approach, which consists of creating a mosaic image, with consecutive camera frames, that is passed as input to the DeepPilot. We argue that this helps to learn the drone’s motion trend regarding the gate, thus acting as a local memory that leverages the prediction of the flight commands. Our results indicate that this purely DL-based artificial pilot is feasible to be used for the ADR challenge.
7
Suzuki, Satoshi, and Kenzo Nonami. "Special Issue on Novel Technology of Autonomous Drone." Journal of Robotics and Mechatronics 33, no. 2 (April 20, 2021): 195. http://dx.doi.org/10.20965/jrm.2021.p0195.
Full textAbstract:
In the past three years, there has been rapid progress in the use of drones in society. Drones, which were previously used only experimentally in various industrial fields, are now being used in earnest in everyday operations. Drones are becoming indispensable tools in several industrial fields, such as surveying, inspection, and agriculture. At the same time, there has also been dramatic progress in autonomous drone technology. With the advancement of image processing, simultaneous localization and mapping (SLAM), and artificial intelligence technologies, many intelligent drones that apply these technologies are being researched. At the same time, our knowledge of multi-rotor helicopters, the main type of drones, has continued to deepen. As the strengths and weaknesses of multi-rotor helicopters have gradually become clearer, drones with alternate structures, such as flapping-wing drones, have come to attract renewed attention. In addition, the range of applications for drones, including passenger drones, has expanded greatly, and research on unprecedented drone operations, as well as research on systems and controls to ensure operational safety, is actively being conducted. This special issue contains the latest review, research papers, and development reports on autonomous drones classified as follows from the abovementioned perspectives. · Research on drone airframes and structures · Research on drone navigation and recognition with a focus on image processing · Research on advanced drone controls · Research and development of drone applications We hope that the readers will actively promote the use of drones in their own research and work, based on the information obtained from this special issue.
8
Muñoz-Gómez, Antonio-Miguel, Juan-Manuel Marredo-Píriz, Javier Ballestín-Fuertes, and José-Francisco Sanz-Osorio. "A Novel Charging Station on Overhead Power Lines for Autonomous Unmanned Drones." Applied Sciences 13, no. 18 (September 10, 2023): 10175. http://dx.doi.org/10.3390/app131810175.
Full textAbstract:
Innovative drone-based technologies provide novel techniques to guarantee the safety and quality of power supply and to perform these tasks more efficiently. Electric multirotor drones, which are at the forefront of technology, face significant flight time limitations due to battery capacity and weight constraints that limit their autonomous operation. This paper presents a novel drone charging station that harvests energy from the magnetic field present in power lines to charge the drone’s battery. This approach relies on a charging station that is easy to install by the drone on an overhead AC power line without modifying the electrical infrastructure. This paper analyses the inductive coupling between the energy harvester and the power line, electrical protection, the power electronics required for maximum power point tracking and the mechanical design of the charging station. A drone that perches on a cable, an end effector for installation procedures and the charging maneuver are described, along with discussion of the robotic and electrical tests performed in a relevant environment. Finally, a lightweight drone charging station capable of harvesting 145 W of power from a 600 A line current is reported.
9
Sondors, Marks, Ilmārs Apeināns, and Sergejs Kodors. "AUTONOMOUS UNMANNED DRONES FLIGHT PLANNING, USING A MODIFIED SHORTEST PATH ALGORITHM WITH A LIMITED TIME FRAME." HUMAN. ENVIRONMENT. TECHNOLOGIES. Proceedings of the Students International Scientific and Practical Conference, no. 27 (October 30, 2023): 14–18. http://dx.doi.org/10.17770/het2023.27.7375.
Full textAbstract:
The aim of this work is to develop an algorithm to find the shortest path for drone flight planning with a limited time frame. Author used the local search shortest path algorithm to find the most efficient algorithm to use for further modification to apply to a drones flight calculation. The algorithm was modified to use the distance between points as a unit of time to limit the flight path length depending on the drone's maximum flight time. As a result of the work, an algorithm was created which, upon receiving an array of points, finds the shortest distance between the points, but when it reaches the limit of the flight duration, it returns to the drone station to charge, and resumes flight once it’s done charging.
10
Gupta, Myra. "Reinforcement Learning for Autonomous Drone Navigation." Innovative Research Thoughts 9, no. 5 (2023): 11–20. http://dx.doi.org/10.36676/irt.2023-v9i5-002.
Full textAbstract:
Drone navigation involves the process of controlling the movement and flight path of unmanned aerial vehicles (UAVs). It encompasses both the hardware and software systems that enable drones to navigate and maneuver autonomously or under the guidance of a human operator. The utility of drone navigation is vast and varied, making it a critical component in numerous industries and applications. Firstly, drone navigation plays a crucial role in aerial surveillance and reconnaissance. Drones equipped with advanced navigation systems can efficiently patrol large areas, monitor activities, and gather real-time data from various perspectives. This capability is particularly valuable in security and law enforcement operations, disaster response, and environmental monitoring, where access and visibility might be limited.
Dissertations / Theses on the topic "Drones autonomes"
1
Le, Barz Cédric. "Navigation visuelle pour les missions autonomes des petits drones." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066424/document.
Full textAbstract:
Lors de dette dernière décennie, l'évolution des technologies a permis le développement de drones de taille et de poids réduit aptes à évoluer dans des environnements intérieurs ou urbains. Pour exécuter les missions qui leur sont attribuées, les drones doivent posséder un système de navigation robuste, comprenant, notamment, une fonctionnalité temps réel d'ego-localisation précise dans un repère absolu. Nous proposons de résoudre cette problématique par la mise en correspondance des dernières images acquises avec des images géoréférencées de type Google Streetview.Dans l'hypothèse où il serait possible pour une image requête de retrouver l'image géo-référencée représentant la même scène, nous avons tout d'abord étudié une solution permettant d'affiner la localisation grâce à l'estimation de la pose relative entre ces deux images. Pour retrouver l'image de la base correspondant à une image requête, nous avons ensuite étudié et proposé une méthode hybride exploitant à la fois les informations visuelles et odométriques mettant en oeuvre une chaîne de Markov à états cachés. Les performances obtenues, dépendant de la qualité de la mesure de similarité visuelle, nous avons enfin proposé une solution originale basée sur l'apprentissage supervisé de distances permettant de mesurer les similarités entre les images requête et les images géoréférencées proches de la position supposéeIn this last decade, technology evolution has enabled the development of small and light UAV able to evolve in indoor and urban environments. In order to execute missions assigned to them, UAV must have a robust navigation system, including a precise egolocalization functionality within an absolute reference. We propose to solve this problem by mapping the latest images acquired with geo-referenced images, i.e. Google Streetview images.In a first step, assuming that it is possible for a given query image to retrieve the geo-referenced image depicting the same scene, we study a solution, based on relative pose estimation between images, to refine the location. Then, to retrieve geo-referenced images corresponding to acquired images, we studied and proposed an hybrid method exploiting both visual and odometric information by defining an appropriate Hidden Markov Model (HMM), where states are geographical locations. The quality of achieved performances depending of visual similarities, we finally proposed an original solution based on a supervised metric learning solution. The solution measures similarities between the query images and geo-referenced images close to the putative position, thanks to distances learnt during a preliminary step
2
Le, Barz Cédric. "Navigation visuelle pour les missions autonomes des petits drones." Electronic Thesis or Diss., Paris 6, 2015. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2015PA066424.pdf.
Full textAbstract:
Lors de dette dernière décennie, l'évolution des technologies a permis le développement de drones de taille et de poids réduit aptes à évoluer dans des environnements intérieurs ou urbains. Pour exécuter les missions qui leur sont attribuées, les drones doivent posséder un système de navigation robuste, comprenant, notamment, une fonctionnalité temps réel d'ego-localisation précise dans un repère absolu. Nous proposons de résoudre cette problématique par la mise en correspondance des dernières images acquises avec des images géoréférencées de type Google Streetview.Dans l'hypothèse où il serait possible pour une image requête de retrouver l'image géo-référencée représentant la même scène, nous avons tout d'abord étudié une solution permettant d'affiner la localisation grâce à l'estimation de la pose relative entre ces deux images. Pour retrouver l'image de la base correspondant à une image requête, nous avons ensuite étudié et proposé une méthode hybride exploitant à la fois les informations visuelles et odométriques mettant en oeuvre une chaîne de Markov à états cachés. Les performances obtenues, dépendant de la qualité de la mesure de similarité visuelle, nous avons enfin proposé une solution originale basée sur l'apprentissage supervisé de distances permettant de mesurer les similarités entre les images requête et les images géoréférencées proches de la position supposéeIn this last decade, technology evolution has enabled the development of small and light UAV able to evolve in indoor and urban environments. In order to execute missions assigned to them, UAV must have a robust navigation system, including a precise egolocalization functionality within an absolute reference. We propose to solve this problem by mapping the latest images acquired with geo-referenced images, i.e. Google Streetview images.In a first step, assuming that it is possible for a given query image to retrieve the geo-referenced image depicting the same scene, we study a solution, based on relative pose estimation between images, to refine the location. Then, to retrieve geo-referenced images corresponding to acquired images, we studied and proposed an hybrid method exploiting both visual and odometric information by defining an appropriate Hidden Markov Model (HMM), where states are geographical locations. The quality of achieved performances depending of visual similarities, we finally proposed an original solution based on a supervised metric learning solution. The solution measures similarities between the query images and geo-referenced images close to the putative position, thanks to distances learnt during a preliminary step
3
Stolle, Martin Tobias. "Vers le vol à voile longue distance pour drones autonomes." Thesis, Toulouse, ISAE, 2017. http://www.theses.fr/2017ESAE0006.
Full textAbstract:
Les petit drones à voilure fixe rendent services aux secteurs de la recherche, de l'armée et de l'industrie, mais souffrent toujours de portée et de charge utile limitées. Le vol thermique permet de réduire la consommation d'énergie. Cependant,sans télédétection d'ascendances, un drone ne peut bénéficier d'une ascendance qu'en la rencontrant par hasard. Dans cette thèse, un nouveau cadre pour le vol à voile longue distance autonome est élaboré, permettant à un drone planeur de localiser visuellement des ascendances sous-cumulus et d’en récolter l'énergie de manière efficace. S'appuyant sur le filtre de Kalman non parfumé, une méthode de vision monoculaire est établie pour l'estimation des paramètres d’ascendances. Sa capacité de fournir des estimations convergentes et cohérentes est évaluée par des simulations Monte Carlo. Les incertitudes de modèle, le bruit de traitement de l'image et les trajectoires de l'observateur peuvent dégrader ces estimés. Par conséquent, un deuxième axe de cette thèse est la conception d'un planificateur de trajectoire robuste basé sur des cartes d'ascendances. Le planificateur fait le compromis entre le temps de vol et le risque d’un atterrissage forcé dans les champs tout en tenant compte des incertitudes d'estimation dans le processus de prise de décision. Il est illustré que la charge de calcul du planificateur de trajectoire proposé est réalisable sur une plate-forme informatique peu coûteuse. Les algorithmes proposés d’estimation ainsi que de planification sont évalués conjointement dans un simulateur de vol à 6 axes, mettant en évidence des améliorations significatives par rapport aux vols à voile longue distance autonomes actuelsSmall fixed-wing Unmanned Aerial Vehicles (UAVs) provide utility to research, military, and industrial sectors at comparablyreasonable cost, but still suffer from both limited operational ranges and payload capacities. Thermal soaring flight for UAVsoffers a significant potential to reduce the energy consumption. However, without remote sensing of updrafts, a glider UAVcan only benefit from an updraft when encountering it by chance. In this thesis, a new framework for autonomous cross-country soaring is elaborated, enabling a glider UAV to visually localize sub-cumulus thermal updrafts and to efficiently gain energy from them.Relying on the Unscented Kalman Filter, a monocular vision-based method is established, for remotely estimatingsub-cumulus updraft parameters. Its capability of providing convergent and consistent state estimates is assessed relyingon Monte Carlo Simulations. Model uncertainties, image processing noise, and poor observer trajectories can degrade theestimated updraft parameters. Therefore, a second focus of this thesis is the design of a robust probabilistic path plannerfor map-based autonomous cross-country soaring. The proposed path planner balances between the flight time and theoutlanding risk by taking into account the estimation uncertainties in the decision making process. The suggested updraftestimation and path planning algorithms are jointly assessed in a 6 Degrees Of Freedom simulator, highlighting significantperformance improvements with respect to state of the art approaches in autonomous cross-country soaring while it is alsoshown that the path planner is implementable on a low-cost computer platform
4
Garin, Raphaël. "Communication et positionnement simultanés pour les drones sous-marins autonomes." Electronic Thesis or Diss., Brest, 2023. http://www.theses.fr/2023BRES0097.
Full textAbstract:
Cette thèse porte sur la navigation des drones sous-marins autonomes (AUV) en l’absence de signaux GPS sous l’eau. Pour résoudre ce problème, elle propose une approche innovante qui combine la localisation de l’AUV avec la communication acoustique sous-marine avec une balise en surface. Cette méthode utilise l’estimation du décalage Doppler requis pour le décodage des signaux de communication afin d’estimer la vitesse relative de l’AUV. De plus, le temps de vol de la communication est utilisé pour mesurer la distance entre l’AUV et la balise. Le système final nécessite seulement des capteurs peu onéreux, tels qu’une centrale inertielle, un capteur de pression, un GPS pour l’initialisation, et un transpondeur acoustique pour le drone, combine avec un capteur de profilage de la vitesse du son. Une balise fixe communique avec le drone et est équipée d’un transpondeur acoustique. Cette approche offre une précision comparable à l’état de l’art, avec une faible empreinte spatiale et un cout réduit. Des simulations et des essais en bassin de 6 m3 ont été effectués avec succès, confirmant la faisabilité du système. De plus, des expérimentations en mer dans des conditions réelles ont montré une précision d’environ 3 mètres, démontrant l’efficacité de l’algorithme. En comparaison avec l’état de l’art, le système proposé est plus rapide à mettre en place, ne nécessite pas de calibration, est plus économique, et consomme moins d’énergie, bien qu’il soit légèrement moins précisThis thesis focuses on the navigation of autonomous underwater drones (AUVs) in the absence of underwater GPS signals. To address this issue, it proposes an innovative approach that combines AUV localization with underwater acoustic communication to a surface beacon. This method utilizes the Doppler shift estimation required for communication signal demodulation in order to estimate the relative velocity of the AUV. Additionally, the communication’s time of flight is used to measure the distance between the AUV and the beacon. The final system requires only affordable components, such as an inertial navigation system, a pressure sensor, a GPS for initialization, and an acoustic transponder for the drone, combined with a sound velocity profiling sensor. A fixed beacon communicates with the drone and is equipped with an acoustic transponder. This approach offers accuracy comparable to the state-of-the-art, with a small spatial footprint and reduced cost. Successful simulations and tests were conducted in a 6 m3 test tank, confirming the feasibility of the system. Furthermore, real-world sea trialsdemonstrated an accuracy of approximately 3 meters, showcasing the algorithm’s effectiveness.Compared to the state-of-the-art, the proposed system is quicker to set up, requires no calibration, is more cost-effective, and consumes less power, although it is slightly less accurate
5
Falomir, Bagdassarian Ema. "Calcul dynamique de chemin par des drones autonomes en essaim compact dans le cadre de missions en environnements complexes." Thesis, Bordeaux, 2019. http://www.theses.fr/2019BORD0450.
Full textAbstract:
Les drones sont aujourd’hui devenus des outils incontournables dans de nombreux domaines, aussi bien civils que militaires. Afin de diminuer la charge de travail de leurs opérateurs, certaines étapes des missions qui leur sont confiées peuvent être automatisées, jusqu’à atteindre l’autonomie complète de la plateforme qui opèrera sans intervention humaine. La mobilité en environnement complexe est une problématique majeure à traiter lorsqu’il est question d’autonomie. En effet, un drone qui découvre son environnement au fur et à mesure de ses déplacements doit régulièrement calculer un chemin vers son point cible, chemin qui doit éviter les obstacles présents sur le trajet. Dans ce contexte, la contribution principale de cette thèse est une méthode de calcul de chemin pour un drone autonome évoluant en environnement complexe. De plus, si la mission est trop complexe pour être réalisée par un seul drone (par exemple car elle nécessite l’utilisation de nombreux capteurs ou se déroule sur une zone étendue), alors on utilise un essaim composé de plusieurs appareils autonomes, qui pourront, collaborativement, remplir la mission donnée. En revanche, même si l’utilisation conjointe de plusieurs plateformes collaboratives permet d’augmenter les performances du système global, de nouvelles problématiques apparaissent, telles que la gestion des communications et l’évitement des drones voisins. La méthode de calcul de chemin que nous proposons prend en compte ces problématiques et est donc adaptée à l’utilisation par les drones d’un essaimDrones are major tools today to perform numerous tasks in a wide range of operations, both for military and civil activities. In order to reduce operators’ workload, some parts of the drones’ missions can be automated, until achieving a full autonomy of the platforms, which will reach their mission without any human intervention. Path planning is a major task to achieve autonomy. Indeed, the drones have to detect obstacles while it discovers its environment and dynamically calculate a path avoiding obstacle and allowing to fulfil their mission. In this context, our main contribution is a path planning method for an autonomous drone evolving in complex environment.Furthermore, the variety of tasks one would like to achieve increases quicker than the capacity of a single UAV, therefore one can use a swarm composed of several autonomous platforms. Usage of several drones increases the number and/or the variety of sensors, and the collaboration between them enhance the global system capabilities by supporting some form of resilience. However, swarming introduced new issues, such as communications and drone avoidance. Our path planning method considers these problematics and then, is adapted for drones forming a swarm
6
Le, Bras Florent. "Contributions à l'asservissement visuel de véhicules aériens autonomes." Nice, 2010. http://www.theses.fr/2010NICE4110.
Full textAbstract:
L’asservissement visuel est une technique de commande reposant sur des mesures issues d’une caméra. Cette technique est apparue à la fin des années 80 pour contrôler des robots mobiles ou des bras manipulateurs. Depuis peu, l’asservissement visuel est appliqué aux engins volants, pour lesquels ce type de contrôle a un fort potentiel opérationnel. Dans cette thèse, nous nous intéressons à la conception d’asservissements visuels pour deux types d’engins volants : les minidrones à voilures tournantes et les avions. Nous essayons autant que possible de spécifier le problème en termes de régulation dans l’image en prenant en compte des contraintes forte sur la nature des capteurs utilisés. Ainsi nous considérons uniquement les capteurs embarqués, autonomes, et dont la qualité est compatible d’un asservissement précis. Pour cela, nous proposons des lois d’asservissement visuels adaptés à la dynamique des engins considérés, à leurs structures de contrôle et à leurs systèmes de mesures. Pour les minidrones à voilures tournantes, une série de lois de commande est proposée pour stabiliser l’engin relativement à une cible plane dont quelques amers sont détectés en temps réel. Ces commandes ont la particularité de ne pas nécessiter de mesure de vitesse de translation. Caractéristique intéressante puisque cette grandeur est particulièrement difficile à mesurer sans GPS. L’un des algorithmes a été validé en vol sur la plateforme Hovereye de Bertin Technologies, il s’agissait, à notre connaissance du premier asservissement visuel basé image, réalisé en intérieur, sur un minidrone. Pour les engins à voilures fixes une nouvelle technique d’atterrissage autonome basée sur la détection des bords de la piste est proposée. Cette technique est basée image et prend en compte les spécificités du vol d’un avion ainsi qu’une estimation de la vitesse du vent. La validation de cette approche est réalisée sur un simulateur complexe incluant la chaîne de traitement d’image. Enfin, nous avons cherché de nouvelles applications à l’asservissement visuel basé image d’engins à voilures fixes. Une loi de commande permettant une stabilisation précise sur une orbite d’observation a ainsi été synthétisée. Elle repose sur la détection d’un unique amer et du flux optique de translation. Des simulations illustrent les performances de ce dernier algorithmeThe visual servo control technology is based on measurements form a camera. This technique appeared in the late 80’s to control mobile robots or manipulators. Recently, visual servoing is applied to flying vehicles, for which this type of control has a strong operational potential. In this thesis, we focus on the design of visual servoing for two types of flying vectors : the VTOL minidrones and fixed-wing aircrafts. We try wherever possible to specify the problem in terms of regulation in the picture by taking into account the limitations of the sensors used. Thus we consider only the onboard sensors autonomous, and whose quality is consistent with a the considered visual servoing tasks. For this, we propose visual servoing laws adapted to the considered systems intheir control structures and their measurement systems. For VTOL minidrones, a series of control laws is proposed to stabilize the vehicle with respect to a relativity flat target which some landmarks are detected in real time. These commands have the distinction of not requiring measurements of the speed of translation. This characteristic is especially interesting, since this variable is particularly difficult to measure without GPS. One of the algorithms has been, validated in fight ion the platform. HoverEye developed by Bertin Technologies, it was, to our knowledge the first image based visual servoing, conducted indoors on a minidrones. For fixed-wing aircrafts, a next autonomous landing technique based on the detection of runway’s edges is proposed. This technique is image based and takes into account the specificities of aircraft flight dynamics. Moreover a specific estimate of cross-wind is proposed. Validation of this approach is performed on a complex simulator which includes images processing. Finally, we sought new applications in image based visual servoing for fixed-wing aircrafts. A control law for precise stabilization on observation orbit has been synthesized. It is based on the detection of a single landmark and translational optical flow. Simulations illustrate the performance of that algorithm
7
Delamer, Jean-Alexis. "Planification d'une stratégie de navigation et de guidage pour des drones autonomes dans des milieux encombrés." Thesis, Toulouse, ISAE, 2019. http://www.theses.fr/2019ESAE0028.
Full textAbstract:
Avec la demande croissante pour l’utilisation de drones autonomes dans des milieuxurbains, la sûreté et l’efficacité de ces missions doivent être garanties. D’une part, il est connuque dans ces milieux la haute densité d’obstacles peut mettre en péril le vol en cas de collision.D’autre part, la capacité de navigation - estimation de la position et par conséquent l’erreurd’exécution - de ces drones dépend de la disponibilité et de la performance de leurs capteursembarqués qui varient selon l’environnement. Dans ce contexte, cette thèse propose un cadre deplanification de chemin sûr et efficace pour des drones en milieux encombrés. Nous avons fondénotre travail sur les Processus Décisionnel de Markov à Observabilité Mixte (MOMDP), carils permettent de modéliser des processus décisionnels à long terme tout en prenant en comptel’incertitude sur l’environnement et son observabilité mixte. Nous proposons une modélisationdu problème de planification qui intègre le système de guidage, navigation et contrôle (GNC),afin de mieux représenter la dynamique de la transition d’état pour un drone, ainsi que l’erreurd’exécution associée. La disponibilité probable, connue a priori, des capteurs embarqués, est aussiconsidérée dans le modèle. Afin d’assurer les contraintes de sûreté, nous proposons une fonctionde coût qui nous permet de raisonner en termes de taux de collision maximal à respecter. Cecipermet au planificateur de définir des politiques qui sont à la fois efficaces - minimisation dutemps de vol - et sûres, par le choix des chemins qui favorisent le respect du taux de collisionmaximal défini. De plus, dus à la complexité du problème de planification, nous proposons unnouvel algorithme de résolution "POMCP-GO", qui est basé sur deux algorithmes de l’état del’art. Nous avons exhaustivement évalué cet algorithme pour notre cadre d’applicationWith the growing demand for the use of UAVs in urban environments, the safetyand effectiveness of these missions must be guaranteed. It is known that in these environmentsthe high density of obstacles can put flight at risk in the case collision. The navigation capacity- estimation of the position and therefore the execution error - of these UAVs depends onthe availability and performance of their on-board sensors, which vary in the environment.In this context, this thesis proposes a safe and effective path planning framework for UAVsin clustered environments. We based our work on the Mixed Observability Markov DecisionProcesses (MOMDP) because it allows us to model long-term decision processes while takinginto account environmental uncertainty and mixed observability. We propose a planning modelthat integrates the guidance, navigation and control system (GNC), in order to better representthe dynamics of the state transition for a drone, as well as the associated execution error. Theprobable availability, known a priori, of on-board sensors is also considered in the model. Inorder to ensure safety constraints, we propose a cost function that allows us to reason in termsof maximum allowable collision rate. This allows the planner to compute policies that are botheffective - minimizing flight time - and safe, by choosing paths that comply with the definedmaximum collision rate. In addition, due to the complexity of the planning problem, we proposea new "POMCP-GO" resolution algorithm, which is based on two state-of-the-art algorithms.We have thoroughly evaluated this algorithm for our application framework
8
Bélanger, Jacky. "Contrôle de véhicules aériens autonomes avec respect de contraintes terminales." Thesis, Université Laval, 2010. http://www.theses.ulaval.ca/2010/27547/27547.pdf.
Full text
9
Myrand-Lapierre, Vincent. "Transitions autonomes entre les vols non stationnaire et stationnaire d'un véhicule aérien miniature à ailes fixes." Master's thesis, Université Laval, 2010. http://hdl.handle.net/20.500.11794/21360.
Full textAbstract:
Les véhicules aériens miniatures à ailes fixes (MiniAV) sont de petits avions avec une envergure d'ailes de moins de 1000 mm et pesant moins de 500 grammes. Grâce aux avancées qui ont été réalisées ces dernières années dans la miniaturisation des autopilotes et dans la propulsion électrique, il est maintenant possible de construire des MiniAVs qui peuvent être utilisés à des fins de reconnaissance en milieu restreint ou hostile. Pour réaliser cet objectif, le MiniAV doit être capable d'effectuer, de façon semi-autonome, des vols non stationnaires et stationnaires et être capable de réaliser des transitions autonomes entre ces modes. Ce mémoire décrit le développement d'une stratégie de contrôle pour permettre à un MiniAV de réaliser des transitions autonomes entre les modes de vol non stationnaire et stationnaire. Il est possible de diviser l'enveloppe de vol d'un MiniAV en 4 modes distincts : le mode non stationnaire, le mode non stationnaire vers stationnaire (L2H), le mode stationnaire et le mode stationnaire vers non stationnaire (H2L). Les structures des modèles pour les modes non stationnaires et stationnaires sont basées sur la linéarisation d'un modèle de MiniAV à corps rigide ayant 6 degrés de liberté. Les contrôleurs de ces deux principaux modes de vol sont présentés. Le mode L2H est gérée par le contrôleur du mode non stationnaire, tandis que le mode H2L est géré par le contrôleur du mode stationnaire. Une approche systématique, appuyée par un superviseur basé sur la logique, est développée pour gérer les transitions entre les modes. La performance du superviseur est démontrée à travers des vols expérimentaux sur un banc de test. Il est montré que la stratégie proposée est capable de mieux performer que les méthodes rencontrées dans la littérature utilisant des plateformes similaires.
10
Sadou, Ryad. "Dimensionnement sur cycle de chsînes de conversion optimales à motorisation synchrone pour des applications de drones autonomes à ailes fixes." Thesis, Nantes Université, 2022. http://www.theses.fr/2022NANU4020.
Full textAbstract:
Dans le cadre du développement d’un drone autonome à ailes fixes, la présente étude porte sur le dimensionnement optimal de la chaîne de propulsion électrique du drone incluant l’hélice, le moteur électrique et son convertisseur d’alimentation. Cette chaîne de puissance par laquelle transite jusqu’à 90 % de l’énergie consommée par le drone, a un fort potentiel en terme de gain de rendement énergétique et donc d’autonomie du drone. La prise en compte de l’intégralité du cycle de fonctionnement du drone requiert le développement d’une méthode de dimensionnement particulière, qui permet l’optimisation simultanée de la géométrie et de la commande de la machine tout en conservant un temps de calcul réduit. Cette méthode, basée sur l’utilisation de modèles analytiques, permet la prise en compte du transitoire thermique afin d’éviter un sur-dimensionnement de la machine, particulièrement avec ce type d’applications où le régime permanent thermique est rarement atteint. Dans cette étude, il a été démontré comment il était possible de prendre en compte le convertisseur d’alimentation et sa commande dès la phase de prédimensionnement de la machine, avec l’objectif de réduire la masse de la MSAP et l’ensemble des pertes {convertisseur - machine}As part of the development of an autonomous fixed-wing UAV, the present sizing of the electric propulsion chain of the drone including the propeller, the electric motor and its power converter. This power chain, through which up to 90 % of the energy consumed by the UAV passes, represents a strong potential gain in term of energy efficiency and therefore in term of the autonomy of the UAV. Taking into account the entire operating cycle of the UAV requires the development of a particular sizing method that allows the simultaneous optimization of the geometry and the control strategy of the machine, while maintaining a reduced calculation time. This method, based on analytical models, allows the consideration of the thermal transient in order to avoid oversizing the machine, particularly with this type of application where the thermal steady state is rarely reached. In this study, it was demonstrated how it was possible to take into account the power converter and its control from the pre-sizing step of the machine, with the objective of reducing the mass of the PMSM and the losses of the {converter - machine} system
Books on the topic "Drones autonomes"
1
Blubaugh, David Allen, Steven D. Harbour, Benjamin Sears, and Michael J. Findler. Intelligent Autonomous Drones with Cognitive Deep Learning. Berkeley, CA: Apress, 2022. http://dx.doi.org/10.1007/978-1-4842-6803-2.
Full text
2
Facility, Dryden Flight Research, ed. Autonomous RPRV navigation guidance and control. Hawthorne, Calif: Systems Technology, Inc., 1989.
Find full text
3
United States. National Aeronautics and Space Administration., ed. Search problems in mission planning and navigation of autonomous aircraft. West Lafayette, Ind: Purdue University, School of Aeronautics and Astronautics, 1988.
Find full text
4
Drohnen und das Recht: Völker- und verfassungsrechtliche Fragen automatisierter und autonomer Kriegführung. Tübingen: Mohr Siebeck, 2014.
Find full text
5
Crítica a la moral conservadora: Aborto, eutanasia, drogas, matrimonio igualitario. Santiago de Chile: LOM Ediciones, 2015.
Find full text
6
United States. National Aeronautics and Space Administration. Aeronautics Research Mission Directorate, ed. Crash course: Lessons learned from accidents involving remotely piloted and autonomous aircraft. Washington, DC: National Aeronautics and Space Administration, 2013.
Find full text
7
Autonome unbemannte bewaffnete Luftsysteme im Lichte des Rechts des internationalen bewaffneten Konflikts: Anforderungen an das Konstruktionsdesign und Einsatzbeschränkungen. Berlin: Duncker & Humblot, 2014.
Find full text
8
Direito à morte com dignidade e autonomia: O direito à morte de pacientes terminais e os princípios da dignidade e autonomia da vontade. Curitiba, Brasil: Juruá Editora, 2007.
Find full text
9
Musial, Marek. System architecture of small autonomous UAVs: Requirements and design approaches in control, communication, and data processing. Saarbrücken: VDM Verlag Dr. Müller, 2008.
Find full text
10
Women and empowerment: Strategies for increasing autonomy. Washington: Hemisphere, 1992.
Find full textBook chapters on the topic "Drones autonomes"
1
Schulzke, Marcus. "Evaluating Autonomous Drones." In The Morality of Drone Warfare and the Politics of Regulation, 149–71. London: Palgrave Macmillan UK, 2016. http://dx.doi.org/10.1057/978-1-137-53380-7_6.
Full text
2
Mukerji, Nikil. "Autonomous Killer Drones." In Drones and Responsibility, 197–214. Farnham, Surrey, UK England ; Burlington, VT : Ashgate, 2016. | Series: Emerging technologies, ethics and international affairs: Routledge, 2016. http://dx.doi.org/10.4324/9781315578187-12.
Full text
3
Hoek, Marga. "Autonomous Vehicles and Drones." In Tech For Good, 217–52. London: Routledge, 2023. http://dx.doi.org/10.4324/9781003392064-7.
Full text
4
Saxon, Dan. "Autonomous Drones and Individual Criminal Responsibility." In Drones and Responsibility, 17–46. Farnham, Surrey, UK England ; Burlington, VT : Ashgate, 2016. | Series: Emerging technologies, ethics and international affairs: Routledge, 2016. http://dx.doi.org/10.4324/9781315578187-2.
Full text
5
Müller, Vincent C. "Autonomous Killer Robots are Probably Good News 1." In Drones and Responsibility, 67–81. Farnham, Surrey, UK England ; Burlington, VT : Ashgate, 2016. | Series: Emerging technologies, ethics and international affairs: Routledge, 2016. http://dx.doi.org/10.4324/9781315578187-4.
Full text
6
Kumar, Kirshna, Sushil Kumar, and Rupak Kharel. "Autonomous and Connected UAVs/Drones." In Secure and Digitalized Future Mobility, 17–31. Boca Raton: CRC Press, 2022. http://dx.doi.org/10.1201/b22998-2.
Full text
7
López, Luis Bausá, Niels van Manen, Erik van der Zee, and Steven Bos. "DroneAlert: Autonomous Drones for Emergency Response." In Multi-Technology Positioning, 303–21. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-50427-8_15.
Full text
8
Dahlmann, Anja. "Drones and Lethal Autonomous Weapon Systems." In Armament, Arms Control and Artificial Intelligence, 159–73. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-11043-6_12.
Full text
9
Santamaria-Navarro, Angel, Rohan Thakker, David D. Fan, Benjamin Morrell, and Ali-akbar Agha-mohammadi. "Towards Resilient Autonomous Navigation of Drones." In Springer Proceedings in Advanced Robotics, 922–37. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-95459-8_57.
Full text
10
Dwivedi, Kriti, Priyanka Govindarajan, Deepika Srinivasan, A. Keerthi Sanjana, Ramani Selvanambi, and Marimuthu Karuppiah. "Intelligent Autonomous Drones in Industry 4.0." In Artificial Intelligence and Cyber Security in Industry 4.0, 133–63. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-2115-7_6.
Full textConference papers on the topic "Drones autonomes"
1
Velazquez, Eric Marin, and Sudhanshu Kumar Semwal. "Using Autonomous Drones Interactions towards Mobile Personal Spaces for Indoor Environments." In WSCG'2021 - 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision'2021. Západočeská univerzita, 2021. http://dx.doi.org/10.24132/csrn.2021.3002.14.
Full textAbstract:
We propose an extension of a recent work using convo-lutional neural networks and drones, such as Learning tofly by using DroNet [8] that can possibly safely drive adrone autonomously. The combination of (i) the DroNetarchitecture and weights to apply to CNNs to avoid thecrashes; (ii) combining it with DLIB tracker, a corre-lation implemented tracker based on Danelljan et al.’spaper [3] work; (iii) the extraction of descriptors usingSpeeded Up Robust Features [1]; and (iv) Fast Libraryfor Approximate Nearest Neighbors [10] for the featurematching – leads a drone to track any object and avoidcrashes autonomously without any prior informationabout the object. The main goal is to create a partnershipbetween the drone(s) and the participant as the dronefollows the participant and avoids collisions. Our workextends existing methods to also included a way for adrone to follow a person even if the person is hiddenfor a few frames. Our algorithms also work in low/poorambient light satisfactorily. In future, our technique canbe used to provide novel indoor applications for drones.
2
Bluman, James, Davonte Carter Vault, Wei Kang Soon, Ruth Talbott, Jonathan Willis, Andrew Kopeikin, and Ekaterina Prosser. "Autonomous Drone Delivery From Airdrop Systems (ADDAS): Aerially Deploying Folding-Wing Drones for Ground Reconnaissance." In ASME 2020 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2020. http://dx.doi.org/10.1115/imece2020-24046.
Full textAbstract:
Abstract Extending the long-range capabilities of unmanned aerial systems (UAS) is paramount to protecting small Soldier teams operating in remote battlefield scenarios. Currently, many small Unmanned Aerial Systems (sUAS) reconnaissance assets have the range necessary to facilitate small-unit missions. The purpose of this paper is to detail the design and testing of a system that fills this capability gap by creating folding-wing drones designed to be aerially deployed from an airdropped dispenser. The dispenser is attached to the Joint Precision Airdrop System (JPADS), which is an autonomously navigated cargo delivery parafoil that can glide several miles, and which can land within 100 meters of its target. To employ the system, the dispenser is launched from a high-altitude aircraft. The system must survive the opening of the parachute in high speed forward flight and provide cushioning to the drones and other components. Once the JPADS navigates the dispenser to a predetermined altitude and distance from the intended reconnaissance area, the dispenser deploys multiple folding-wing drones. The soldiers on the ground can access the drones’ live video feeds through a handheld video transmitter. The system combines the precision navigation and information-transmission capabilities of the fixed wing drone with the long-range capabilities of the JPADS. With a commercial-off-the-shelf drone as the folding-wing aircraft platform, the team designed a wing connection hub that allows for rapid folding and unfolding of the drone’s wings, a separate canister for each drone within the dispenser, and a dispenser capable of interfacing with both the canisters and the JPADS. Though currently in the technology-demonstration phase of the project, the team envisions the system being fully autonomous from launch of dispenser to end of mission.
3
Salim, Rufaidah, Mahmoud Rezk, Mohammed Minhas Anzil, Nawal AlJasmi, and Amit Shukla. "Vision Based Safe Navigation of UAV for Overhead Line Inspection Enabled by Virtual Safety Bubble." In ASME 2022 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2022. http://dx.doi.org/10.1115/imece2022-95358.
Full textAbstract:
Abstract Energy transmission systems have expanded significantly, given the increase in demand for power generation. This increase in size has led to the need of a robust inspection method. Overhead Line (OHL) systems consist of many critical components such as insulators, poles, and power lines, which need to be inspected regularly. With recent advancements, drones equipped with multiple sensors are flown, either manually or autonomously, for inspection. This paper proposes autonomous vision-based navigation of the drone over OHL. The navigation is achieved through the feedback from the camera onboard the drone. A deep learning-based model is developed for the detection of the various OHL components, which are then utilized to design the path for the drone to navigate. Furthermore, a virtual safety bubble (VSB) is developed around the drone upon the detection of the components. This VSB is part of local autonomy of the drone and ensures that a constant safe distance is always maintained from the components. This approach can help reduce the overall inspection time of OHL with less cognitive load on the operator. It also ensures the safety of the OHL installations and drone. Although the paper focuses mainly on running the experiments in a simulation environment, this could be imitated in real-life situations.
4
Alsifiany, Fahad. "Use of AI to Diversify and Improve the Performance of RF Sensors Drone Detection Mechanism." In 13th International Conference on Computer Science, Engineering and Applications (CCSEA 2023). Academy and Industry Research Collaboration Center (AIRCC), 2023. http://dx.doi.org/10.5121/csit.2023.130504.
Full textAbstract:
Drone terrorism may seem elementary and efforts in its mitigation may seem painless. The fact is that security bodies in many countries are still grappling with this growing security concern. The autonomous nature of drones and the unpredictable nature of drone attacks remain to be some of the unforeseen challenges undermining the mitigation efforts in combating drone terrorism. The need to upskill our security forces and the general public on the operational practices and security capabilities in the drone world cannot be overemphasized. This paper explores a futuristic solution to the current challenges encountered in the war against drone terrorism. In its design, it delves into the possibility of utilizing Artificial Intelligence (AI) in characterizing the features of drones identified in our airspace to determine their authenticity. It further enriches the employees of the security services and the general public with information on combating drone terrorism by benefiting from the accumulated experiences of the relevant and specialized affiliates
5
Stensrud, Erik, Are Torstensen, Dag-Børre Lillestøl, and Kristian Klausen. "Towards Remote Inspections of FPSO's Using Drones Instrumented with Computer Vision and Hyperspectral Imaging." In Offshore Technology Conference. OTC, 2021. http://dx.doi.org/10.4043/30939-ms.
Full textAbstract:
Abstract The Class Society DNV has performed production surveys in enclosed spaces using drones since 2016, demonstrating cost savings and increased personnel safety. The goal is to develop autonomous inspection drones to reduce the need to enter tanks and enable remote inspection. The vision is a drone that can fly by itself, track where it is, and spot rust and cracks, and measure steel thickness. We expect that drone-assisted remote inspection will reduce survey costs for the clients and be a major safety improvement for surveyors. Several drone capabilities are required to enable visual close-up inspection and non-destructive testing in enclosed, GPS-denied, and poorly lit environments. In this study, we report the most recent status from an ongoing research project, including several industry partners. We highlight technical challenges and preliminary results on drone navigation functionalities, computer vision for detection of cracks, and the use of hyperspectral imaging to detect and classify the chemical composition of coatings, rust, and other use cases.
6
Godio, Simone, Francesco Marino, Alessandro Minervini, Stefano Primatesta, Marcello Chiaberge, and Giorgio Guglieri. "Autonomous Drones in GNSS-Denied Environments: Results from the Leonardo Drone Contest." In 2023 IEEE 10th International Workshop on Metrology for AeroSpace (MetroAeroSpace). IEEE, 2023. http://dx.doi.org/10.1109/metroaerospace57412.2023.10190003.
Full text
7
IBRAHIM, CHRISTINE-OMEIRA, JONAS SIMON, LENNART T FOX, JOCHEN MOLL, and MARK-FELIX SCHÜTZ. "VIBRATION-BASED STRUCTURAL HEALTH MONITORING OF DELIVERY DRONES: ANALYSIS OF PRELIMINARY EXPERIMENTS." In Structural Health Monitoring 2021. Destech Publications, Inc., 2022. http://dx.doi.org/10.12783/shm2021/36242.
Full textAbstract:
The development of unmanned aerial vehicles (UAV) has progressed very rapidly in recent years and finds many applications in various industrial fields. The technological progress brings serious challenges, especially regarding flight safety, as any unexpected behavior of the drone can lead to serious consequences. The autonomous usage of delivery drones requires a high reliability especially in urban areas. This motivates the development and application of structural health monitoring (SHM) systems. In this work, we present and discuss the results of preliminary experiments of a vibration-based SHM system for delivery drones. In particular, we focus on the hover phase during take-off in which the airworthiness can be assessed within seconds. For this purpose, the drone is first launched and a measurement is made using acceleration sensors. The measurement data is evaluated using three different metrics one of which is the Nullspace-Based Fault Detection (NSFD) method. It was demonstrated here that added masses can be detected through the analysis of mechanical vibrations.
8
Anachkova, Maja, Marko Stankoski, Mihael Berberu, Aleksandar Atanasov, Jane Janevski, and Jovana Jovanova. "Design and Analysis of a Modular VTOL Drone With Bat-Inspired Wings." In ASME 2020 Conference on Smart Materials, Adaptive Structures and Intelligent Systems. American Society of Mechanical Engineers, 2020. http://dx.doi.org/10.1115/smasis2020-2342.
Full textAbstract:
Abstract The future of technology lies in the diverse characteristics and capabilities of autonomous machines and devices and their application in many technical challenge. Rapid technology development, market globalization and availability of affordable electronics and controllers, have recently resulted in increased scientific and technical interest in drones as autonomous solutions for professional, as well as, amateur applications. On the other hand, researchers have been improving how manmade machines move through air by attempting to replicate animals motion by mimicking their aerial abilities. In this paper, we propose a development of a bio-inspired modular drone concept motivated by the bats agility, wingspan and wings folding into various shapes. The drone can be tailored for different applications, from sea port mapping, surveying, tank inspection and port traffic control to pollution monitoring and detection of illegal activities. The aerial performances of the drone allow it to be able to conduct windmills monitoring by connecting to their local monitoring units and send alerts to officials in real-time. This small bat-inspired drone is proposed to have an ability of performing flights with precisely defined trajectories. The accent will be put on the interchangeable wings, analysis of their dynamic attributes and transformation possibilities as a crucial segment of the overall drone performance. The design and fabrication process and the flight characteristics of the various wing configurations of the drone are discussed in details. Limitations of the drone, proposed solutions for further development and recommendations are also presented.
9
Burdziakowski, Paweł. "Low Cost Hexacopter Autonomous Platform for Testing and Developing Photogrammetry Technologies and Intelligent Navigation Systems." In Environmental Engineering. VGTU Technika, 2017. http://dx.doi.org/10.3846/enviro.2017.172.
Full textAbstract:
Low-cost solutions for autonomous aerial platforms are being intensively developed and used within geodetic community. Unmanned aerial vehicles are becoming very popular and widely used for photogrammetry and remote sensing applications. Today’s market offers an affordable price components for unmanned solution with significant quality and accuracy growth. Every year market offers a new solutions for autonomous platforms with better technical specifications. Commercial drones for amateurs are widely offered and presents a quality and accuracy not available in past few years. In this paper an autonomous open source low cost haxacopter system for photogrammetry and intelligent navigation technologies evaluation is being presented. The system was designed and assembled for technologies testing and for educational purposes. The drone is based only on open source hardware and software. All components are based on open source and commercial of the shelf products. That approach to the drones construction provides a many capabilities to test, implement and execute new algorithms, solutions and tasks. Providing basic configuration tools system enables students to safely perform elementary setup and testing. An advanced configurations system tool and open source structure enables to execute advanced scientific test and research. Paper presents results of designed process, system configuration and specification, technical issues that was being solved during test flights and practical research results.
10
Iob, Pietro, Luca Frau, Piero Danieli, Lorenzo Olivieri, and Carlo Bettanini. "Avalanche Rescue with Autonomous Drones." In 2020 IEEE 7th International Workshop on Metrology for AeroSpace (MetroAeroSpace). IEEE, 2020. http://dx.doi.org/10.1109/metroaerospace48742.2020.9160116.
Full textReports on the topic "Drones autonomes"
1
Alexander, Serena, Bo Yang, Owen Hussey, and Derek Hicks. Examining the Externalities of Highway Capacity Expansions in California: An Analysis of Land Use and Land Cover (LULC) Using Remote Sensing Technology. Mineta Transportation Institute, November 2023. http://dx.doi.org/10.31979/mti.2023.2251.
Full textAbstract:
There are over 590,000 bridges dispersed across the roadway network that stretches across the United States alone. Each bridge with a length of 20 feet or greater must be inspected at least once every 24 months, according to the Federal Highway Act (FHWA) of 1968. This research developed an artificial intelligence (AI)-based framework for bridge and road inspection using drones with multiple sensors collecting capabilities. It is not sufficient to conduct inspections of bridges and roads using cameras alone, so the research team utilized an infrared (IR) camera along with a high-resolution optical camera. In many instances, the IR camera can provide more details to the interior structural damages of a bridge or a road surface than an optical camera, which is more suitable for inspecting damages on the surface of a bridge or a road. In addition, the drone inspection system is equipped with a minicomputer that runs Machine Learning algorithms. These algorithms enable autonomous drone navigation, image capture of the bridge or road structure, and analysis of the images. Whenever any damage is detected, the location coordinates are saved. Thus, the drone can self-operate and carry out the inspection process using advanced AI algorithms developed by the research team. The experimental results reveal the system can detect potholes with an average accuracy of 84.62% using the visible light camera and 95.12% using a thermal camera. This developed bridge and road inspection framework can save time, money, and lives by automating and having drones conduct major inspection operations in place of humans.
2
Kulhandjian, Hovannes. AI-Based Bridge and Road Inspection Framework Using Drones. Mineta Transportation Institute, November 2023. http://dx.doi.org/10.31979/mti.2023.2226.
Full textAbstract:
There are over 590,000 bridges dispersed across the roadway network that stretches across the United States alone. Each bridge with a length of 20 feet or greater must be inspected at least once every 24 months, according to the Federal Highway Act (FHWA) of 1968. This research developed an artificial intelligence (AI)-based framework for bridge and road inspection using drones with multiple sensors collecting capabilities. It is not sufficient to conduct inspections of bridges and roads using cameras alone, so the research team utilized an infrared (IR) camera along with a high-resolution optical camera. In many instances, the IR camera can provide more details to the interior structural damages of a bridge or a road surface than an optical camera, which is more suitable for inspecting damages on the surface of a bridge or a road. In addition, the drone inspection system is equipped with a minicomputer that runs Machine Learning algorithms. These algorithms enable autonomous drone navigation, image capture of the bridge or road structure, and analysis of the images. Whenever any damage is detected, the location coordinates are saved. Thus, the drone can self-operate and carry out the inspection process using advanced AI algorithms developed by the research team. The experimental results reveal the system can detect potholes with an average accuracy of 84.62% using the visible light camera and 95.12% using a thermal camera. This developed bridge and road inspection framework can save time, money, and lives by automating and having drones conduct major inspection operations in place of humans.
3
Cook, Stephen, and Loyd Hook. Developmental Pillars of Increased Autonomy for Aircraft Systems. ASTM International, January 2020. http://dx.doi.org/10.1520/tr2-eb.
Full textAbstract:
Increased automation for aircraft systems holds the promise to increase safety, precision, and availability for manned and unmanned aircraft. Specifically, established aviation segments, such as general aviation and light sport, could utilize increased automation to make significant progress towards solving safety and piloting difficulties that have plagued them for some time. Further, many emerging market segments, such as urban air mobility and small unmanned (e.g., small parcel delivery with drones) have a strong financial incentive to develop increased automation to relieve the pilot workload, and/or replace in-the-loop pilots for most situations. Before these advances can safely be made, automation technology must be shown to be reliable, available, accurate, and correct within acceptable limits based on the level of risk these functions may create. However since inclusion of these types of systems is largely unprecedented at this level of aviation, what constitutes these required traits (and at what level they must be proven to) requires development as well. Progress in this domain will likely be captured and disseminated in the form of best practices and technical standards created with collaboration from regulatory and industry groups. This work intends to inform those standards producers, along with the system designers, with the goal of facilitating growth in aviation systems toward safe, methodical, and robust inclusion of these new technologies. Produced by members of the manned and unmanned small aircraft community, represented by ASTM task group AC 377, this work strives to suggest and describe certain fundamental principles, or “pillars”, of complex aviation systems development, which are applicable to the design and architectural development of increased automation for aviation systems.
4
McQueen, Bob. Unsettled Issues in Advanced Air Mobility Certification. SAE International, June 2021. http://dx.doi.org/10.4271/epr2021014.
Full textAbstract:
Advanced air mobility (AAM) refers to urban transportation systems that move people and goods by air. This has significant implications for reducing traffic congestion in cities and for providing an integrated approach to urban mobility. With the emergence of drone technology and the possibility of more autonomous aircraft, interest has grown considerably in AAM. Unsettled Issues in Advanced Air Mobility Certification discusses the impact of AAM on private sector solution providers including aerospace and technology companies and goes into solutions for urban planners and transportation professionals for better integration across all AAM modes.
5
Christensen, Lance. PR-459-133750-R03 Fast Accurate Automated System To Find And Quantify Natural Gas Leaks. Chantilly, Virginia: Pipeline Research Council International, Inc. (PRCI), November 2019. http://dx.doi.org/10.55274/r0011633.
Full textAbstract:
Miniature natural gas sensors weighing a few hundred grams with 10 ppb s-1 sensitivity towards methane and ppb s-1 sensitivity towards methane and ethane present the energy industry with cost effective ways to improve safety, comply with State and Federal regulations, decrease natural gas emissions, and attribute natural gas indications to thermogenic or biogenic sources. One particularly promising implementation is on small unmanned aerial systems (sUASs) flown by service providers or in-house personnel or even more ambitiously as part of larger network conducting autonomous, continual monitoring. This report describes refinement of the OPLS measurement system to include all ancillary instruments needed to put OPLS methane and ethane measurements into context for leak surveillance, localization, and quantification. Flights were conducted on a variety of VTOLs and fixed wing drones as described below to ensure that the overall system development resulted in a system that was platform agnostic. This report describes: - The complete agnostic OPLS measurement system.The individual components are described and their performance investigated.Technical issues that arose during testing and field deployment are described. - Field experiments of the refined OPLS measurement system at a real-world oil and gas production site.These experiments exercise the OPLS system's ability to do leak surveillance, localization, and quantification. - Laboratory development of the OPLS instrument to improve its performance in terms of signal-to-noise and accuracy. - Field experiments demonstrating the successful application of OPLS on a fixed-wing hybrid flown at altitudes higher than 50 m. - Field experiments demonstrating the utility of source attribution using the ethane measurement capability. There is a related webinar.