182 resultados para UAV


Relevância:

10.00% 10.00%

Publicador:

Resumo:

Gli UAV, o meglio conosciuti come ‘droni’, sono aeromobili a pilotaggio remoto il cui utilizzo si estende dal settore militare a quello civile. Quest’ultimi, possono essere attrezzati con numerosi dispositivi accessori, come ad esempio disturbatori di frequenze. La simbiosi UAV-jammer attacca le comunicazioni wireless tramite interferenze a radiofrequenza, per degradare o interrompere il servizio offerto dalle reti. Questo elaborato, si concentra sull’analisi di algoritmi di localizzazione passiva, per stimare la posizione dell’UAV e interrompere l’interferenza. Inizialmente, viene descritto il segnale emesso dall’UAV, che utilizza lo standard di comunicazione 802.11a. A seguire, dato che la localizzazione passiva si basa sulle misure TDOA rilevate da una stazione di monitoraggio a terra, vengono presentati tre algoritmi di stima TDOA, tra i quali fast TDOA, adaptive threshold-based first tap detection e un algoritmo sviluppato per i nuovi sistemi GNSS. Successivamente, vengono esaminati tre algoritmi di localizzazione passiva, che sfruttano il principio dei minimi quadrati (LS), ovvero il CTLS, LCLS e CWLS. Infine, le prestazioni degli algoritmi di localizzazione vengono valutate in un ambiente di simulazione realistico, con canale AWGN o con canale ITU Extended pedestrian A.

Relevância:

10.00% 10.00%

Publicador:

Resumo:

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.