Studio e ottimizzazione della ipersostentazione del velivolo V-173

Studio della ipersostentazione di un velivolo non convenzionale degli anni ‘40, il Vought V-173 Flying Pancake. Per realizzare l’intero lavoro si sono adoperati dei software di fluidodinamica computazionale come Flow Simulation di SolidWorks e il programma JavaFoil, inoltre, si è scelto l’ambiente Matlab di supporto ai calcoli e per rappresentare i risultati ottenuti a seguito delle simulazioni, realizzando script e funzioni per l’approssimazione di questi e la loro successiva raffigurazione grafica. In particolar modo, a partire dal modello tridimensionale in SolidWorks del V-173 si sono ricreate le curve CL-α e CD-α a partire dai punti ottenuti dalle simulazioni per diverse configurazioni del velivolo. In una prima fase si è valutata l’aerodinamica del velivolo ‘pulito’ senza la presenza delle eliche e di ipersostentatori, successivamente si sono seguite due strade diverse per valutare il comportamento del velivolo: nel primo caso si sono eseguiti studi dell’aerodinamica del Pancake in presenza degli ipersostentatori già presenti sul velivolo (i plain flap), proponendo soluzioni alternative per migliorare l’ipersostentazione del V-173 tramite spillamenti (slots) e diverse configurazioni di vortex generator che energizzassero lo strato limite e ottimizzassero le prestazioni del velivolo con particolare attenzione alla fase di atterraggio. In secondo luogo, tenendo in considerazione che il Pancake è un aeroplano bielica, si è voluta studiare l’influenza delle due eliche sulla sua aerodinamica: dopo aver riprodotto nel modo più verosimile entrambe le eliche utilizzando SolidWorks si è fatto uno studio di massima ricavando risultati che potessero indicare la compatibilità tra elica e velivolo a seguito dei risultati sperimentali ottenuti con Flow Simulation.

Unmanned Aerial Wireless Networks For The Internet of Things

The need for data collection from sensors dispersed in the environment is an increasingly important problem in the sector of telecommunications. LoRaWAN is one of the most popular protocols for low-power wide-area networks (LPWAN) that is made to solve the aforementioned problem. The aim of this study is to test the behavior of the LoRaWAN protocol when the gateway that collects data is implemented on a flying platform or, more specifically, a drone. This will be pursued using performance data in terms of access to the channel of the sensor nodes connected to the flying gateway. The trajectory of the aircraft is precomputed using a given algorithm and sensor nodes’ clusterization. The expected results are as follows: simulate the LoraWAN system behavior including the trajectory of the drone and the deployment of nodes; compare and discuss the effectiveness of the LoRaWAN simulator by conducting on-field trials, where the trajectory design and the nodes’ deployment are the same.

Neural Network based Non Orthogonal Random Access for 6G NTN-IoT

Pervasive and distributed Internet of Things (IoT) devices demand ubiquitous coverage beyond No-man’s land. To satisfy plethora of IoT devices with resilient connectivity, Non-Terrestrial Networks (NTN) will be pivotal to assist and complement terrestrial systems. In a massiveMTC scenario over NTN, characterized by sporadic uplink data reports, all the terminals within a satellite beam shall be served during the short visibility window of the flying platform, thus generating congestion due to simultaneous access attempts of IoT devices on the same radio resource. The more terminals collide, the more average-time it takes to complete an access which is due to the decreased number of successful attempts caused by Back-off commands of legacy methods. A possible countermeasure is represented by Non-Orthogonal Multiple Access scheme, which requires the knowledge of the number of superimposed NPRACH preambles. This work addresses this problem by proposing a Neural Network (NN) algorithm to cope with the uncoordinated random access performed by a prodigious number of Narrowband-IoT devices. Our proposed method classifies the number of colliding users, and for each estimates the Time of Arrival (ToA). The performance assessment, under Line of Sight (LoS) and Non-LoS conditions in sub-urban environments with two different satellite configurations, shows significant benefits of the proposed NN algorithm with respect to traditional methods for the ToA estimation.

Continual learning on nano drones

Miniaturized flying robotic platforms, called nano-drones, have the potential to revolutionize the autonomous robots industry sector thanks to their very small form factor. The nano-drones’ limited payload only allows for a sub-100mW microcontroller unit for the on-board computations. Therefore, traditional computer vision and control algorithms are too computationally expensive to be executed on board these palm-sized robots, and we are forced to rely on artificial intelligence to trade off accuracy in favor of lightweight pipelines for autonomous tasks. However, relying on deep learning exposes us to the problem of generalization since the deployment scenario of a convolutional neural network (CNN) is often composed by different visual cues and different features from those learned during training, leading to poor inference performances. Our objective is to develop and deploy and adaptation algorithm, based on the concept of latent replays, that would allow us to fine-tune a CNN to work in new and diverse deployment scenarios. To do so we start from an existing model for visual human pose estimation, called PULPFrontnet, which is used to identify the pose of a human subject in space through its 4 output variables, and we present the design of our novel adaptation algorithm, which features automatic data gathering and labeling and on-device deployment. We therefore showcase the ability of our algorithm to adapt PULP-Frontnet to new deployment scenarios, improving the R2 scores of the four network outputs, with respect to an unknown environment, from approximately [−0.2, 0.4, 0.0,−0.7] to [0.25, 0.45, 0.2, 0.1]. Finally we demonstrate how it is possible to fine-tune our neural network in real time (i.e., under 76 seconds), using the target parallel ultra-low power GAP 8 System-on-Chip on board the nano-drone, and we show how all adaptation operations can take place using less than 2mWh of energy, a small fraction of the available battery power.