Drones en la agricultura

Los drones sobrevuelan la parcela (previa fijación de sus límites con las coordenadas GPS) y toman fotografías de alta resolución que envían al ordenador central, donde se analizan para localizar malas hierbas y enviar a los tractores robotizados a realizar tratamientos donde haya infestación. A la espera de una legislación europea, el Gobierno Español ha aprobado unas normas provisiona-les que permiten utilizar drones para la realización de trabajos aéreos como son actividades de investigación y desarrollo de tratamientos aéreos, fitosanitarios u otros que supongan esparcir sustancias en el suelo o la atmósfera

Empleo de drones (RPAS) para la elaboración de material audiovisual docente en asignaturas de Ingeniería Civil

El presente trabajo estudia la utilización de drones telecomandados de uso comercial (RPAS) para producir material audiovisual específico de diversas asignaturas de las titulaciones de Ingeniería Civil. Se trata de un equipamiento de alta tecnología y coste relativamente asequible, en torno a 1.300 euros, para producir material audiovisual que hasta ahora únicamente podría ser obtenido empleando medios mucho más limitados (fotografías aéreas y de satélite) o mucho más costosos, tales como vuelos fotográficos específicos. De este modo, se valorará la viabilidad de introducción de una nueva herramienta tecnológica de innovación educativa hasta ahora no empleada en la elaboración de material docente, analizando sus principales ventajas y limitaciones.

Innovación en la producción de materiales curriculares para titulaciones de Ingeniería Civil empleando drones telecomandados

El presente trabajo estudia la utilización de drones telecomandados de uso comercial (RPAS) para producir material audiovisual específico de diversas asignaturas de las titulaciones de Ingeniería Civil. Se trata de un equipamiento de alta tecnología y coste relativamente asequible, en torno a 1.300 euros, para producir material audiovisual que hasta ahora únicamente podría ser obtenido empleando medios mucho más limitados (fotografías aéreas y de satélite) o mucho más costosos, tales como vuelos fotográficos específicos. De este modo, se valorará la viabilidad de introducción de una nueva herramienta tecnológica de innovación educativa hasta ahora no empleada en la elaboración de material docente, analizando sus principales ventajas y limitaciones.

Fibrous Aerial Robotics: study of spiderweb strategies for the design of architectural envelopes using swarms of drones and inflatable formworks

La tesi approccia in modo transdisciplinare biologia, architettura e robotica, con la finalità di indagare e applicare principi costruttivi attraverso l’interazione tra sciami di droni che depositano materiale fibroso su strutture gonfiabili di supporto. L’attenzione principale è nello sviluppo (attraverso un workflow computazionale che gestisce sciami di agenti costruttori) di una tettonica che integra struttura, spazio e ornamento all’interno dello stesso processo progettuale, il quale si sviluppa coerentemente dall’ideazione fino alla fabbricazione. Sono stati studiati modelli biologici quali le colonie di ragni sociali, i quali costruiscono artefatti di grandi dimensioni relativamente a quelle del singolo individuo grazie ad un’organizzazione coordinata ed emergente e alle proprietà dei sistemi fibrosi. L’auto-organizzazione e la decentralizzazione, insieme alle caratteristiche del sistema materiale, sono stati elementi indispensabili nell’estrapolazione prima e nella codificazione poi di un insieme di regole adatte allo sviluppo del sistema costruttivo. Parallelamente alla simulazione digitale si è andati a sviluppare anche un processo fisico di fabbricazione che, pur tenendo conto dei vincoli economici e tecnici, potesse dimostrarsi una prova di concetto e fattibilità del sistema costruttivo. Sono state investigate le possibilità che un drone offre nel campo della fabbricazione architettonica mediante il rilascio di fili su elementi gonfiabili in pressione. Il processo può risultare vantaggioso in scenari in cui non è possibile allestire infrastrutture costruttive tradizionali (es. gole alpine, foreste). Tendendo conto dei vincoli e delle caratteristiche del sistema di fabbricazione proposto, sono state esplorate potenzialità e criticità del sistema studiato.

Colectivos sociales y ciborgs: hacia una lectura feminista de los drones

Este artículo analiza el papel de los drones en la emergencia de nuevas formas de participación política e impugnación del poder por parte de colectivos sociales. El artículo plantea una lectura feminista de los drones como ciborgs (humanos-máquinas) para explorar las agencias distribuidas entre actores humanos y no humanos con el propósito de visibilizar las relaciones de poder y analizar la configuración de contra-realidades. Se presentan ocho casos de colectivos sociales que, con la ayuda de un dron, disputan el poder de gobiernos, empresas transnacionales además de desempeñar innovadoras intervenciones públicas.

Drones y el orden legal internacional. Tecnología, estrategia y largas cadenas de acción

The main thesis of this article is that the increasing recourse to the use of unmanned aerial systems in asymmetric warfare and the beginning routinization of U.S. drone operations represent part of an evolutionary change in the spatial ordering of global politics -- Using a heuristic framework based on actor-network theory, it is argued that practices of panoptic observation and selective airstrikes, being in need of legal justification, contribute to a reterritorialization of asymmetric conflicts -- Under a new normative spatial regime, a legal condition of state immaturity is constructed, which establishes a zone of conditional sovereignty subject to transnational aerial policing -- At the same time, this process is neither a deterministic result of the new technology nor a deliberate effect of policies to which drones are merely neutral instruments -- Rather, military technology and political decisions both form part of a long chain of action which has evolved under the specific circumstances of recent military interventions

Embedding Video Object Detection Capabilities on Low-Power Nano-Drones

Our objective for this thesis work was the deployment of a Neural Network based approach for video object detection on board a nano-drone. Furthermore, we have studied some possible extensions to exploit the temporal nature of videos to improve the detection capabilities of our algorithm. For our project, we have utilized the Mobilenetv2/v3SSDLite due to their limited computational and memory requirements. We have trained our networks on the IMAGENET VID 2015 dataset and to deploy it onto the nano-drone we have used the NNtool and Autotiler tools by GreenWaves. To exploit the temporal nature of video data we have tried different approaches: the introduction of an LSTM based convolutional layer in our architecture, the introduction of a Kalman filter based tracker as a postprocessing step to augment the results of our base architecture. We have obtain a total improvement in our performances of about 2.5 mAP with the Kalman filter based method(BYTE). Our detector run on a microcontroller class processor on board the nano-drone at 1.63 fps.

An optimal control tool for trajectory generation of autonomous drones

In the recent years, autonomous aerial vehicles gained large popularity in a variety of applications in the field of automation. To accomplish various and challenging tasks the capability of generating trajectories has assumed a key role. As higher performances are sought, traditional, flatness-based trajectory generation schemes present their limitations. In these approaches the highly nonlinear dynamics of the quadrotor is, indeed, neglected. Therefore, strategies based on optimal control principles turn out to be beneficial, since in the trajectory generation process they allow the control unit to best exploit the actual dynamics, and enable the drone to perform quite aggressive maneuvers. This dissertation is then concerned with the development of an optimal control technique to generate trajectories for autonomous drones. The algorithm adopted to this end is a second-order iterative method working directly in continuous-time, which, under proper initialization, guarantees quadratic convergence to a locally optimal trajectory. At each iteration a quadratic approximation of the cost functional is minimized and a decreasing direction is then obtained as a linear-affine control law, after solving a differential Riccati equation. The algorithm has been implemented and its effectiveness has been tested on the vectored-thrust dynamical model of a quadrotor in a realistic simulative setup.

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.

Cuticular hydrocarbons in the stingless bee Schwarziana quadripunctata (Hymenoptera, Apidae, Meliponini): differences between colonies, castes and age

Chemical communication is of fundamental importance to maintain the integration of insect colonies. In honey bees, cuticular lipids differ in their composition between queens, workers and drones. Little is known, however, about cuticular hydrocarbons in stingless bees. We investigated chemical differences in cuticular hydrocarbons between different colonies, castes and individuals of different ages in Schwarziana quadripunctata. The epicuticle of the bees was extracted using the nonpolar solvent hexane, and was analyzed by means of a gas chromatograph coupled with a mass spectrometer. The identified compounds were alkanes, branched-alkanes and alkenes with chains of 19 to 33 carbon atoms. Discriminant analyses showed clear differences between all the groups analyzed. There were significant differences between bees from different colonies, workers of different age and between workers and virgin queens.

Unsuccessful attacks dominate a drone-preying wasp's hunting performance near stingless bee nests

Bee males (drones) of stingless bees tend to congregate near entrances of conspecific nests, where they wait for virgin queens that initiate their nuptial flight. We observed that the Neotropical solitary wasp Trachypus boharti (Hymenoptera, Cabronidae) specifically preys on males of the stingless bee Scaptotrigona postica (Hymenoptera, Apidae); these wasps captured up to 50 males per day near the entrance of a single hive. Over 90% of the wasp attacks were unsuccessful; such erroneous attacks often involved conspecific wasps and worker bees. After the capture of non-male prey, wasps almost immediately released these individuals unharmed and continued hunting. A simple behavioral experiment showed that at short distances wasps were not specifically attracted to S. postica males nor were they repelled by workers of the same species. Likely, short-range prey detection near the bees' nest is achieved mainly by vision whereas close-range prey recognition is based principally on chemical and/or mechanical cues. We argue that the dependence on the wasp's visual perception during attack and the crowded and dynamic hunting conditions caused wasps to make many preying attempts that failed. Two wasp-density-related factors, wasp-prey distance and wasp-wasp encounters, may account for the fact that the highest male capture and unsuccessful wasp bee encounter rates occurred at intermediate wasp numbers.

Industrial apiculture in the Jordan valley during Biblical times with Anatolian honeybees

Although texts and wall paintings suggest that bees were kept in the Ancient Near East for the production of precious wax and honey, archaeological evidence for beekeeping has never been found. The Biblical term ""honey"" commonly was interpreted as the sweet product of fruits, such as dates and figs. The recent discovery of unfired clay cylinders similar to traditional hives still used in the Near East at the site of Tel Rehov in the Jordan valley in northern Israel suggests that a large-scale apiary was located inside the town, dating to the 10th-early 9th centuries B.C.E. This paper reports the discovery of remains of honeybee workers, drones, pupae, and larvae inside these hives. The exceptional preservation of these remains provides unequivocal identification of the clay cylinders as the most ancient beehives yet found. Morphometric analyses indicate that these bees differ from the local subspecies Apis mellifera syriaca and from all subspecies other than A. m. anatoliaca, which presently resides in parts of Turkey. This finding suggests either that the Western honeybee subspecies distribution has undergone rapid change during the last 3,000 years or that the ancient inhabitants of Tel Rehov imported bees superior to the local bees in terms of their milder temper and improved honey yield.