Skip to main content
main-content

Über dieses Buch

This volume presents the conference proceedings from FinDrones2020. The book highlights recent developments in drone technology by experts, academicians, and entrepreneurs for applications in agriculture, forestry, and other industries. Emphasis is placed on contextualizing the conference presentations and content to Finland and the unique challenges typical to this region. The work will be of interest to academicians and professionals involved in remote sensing applications of unmanned aerial vehicles, as well as enthusiasts of drone technological developments.

Inhaltsverzeichnis

Frontmatter

Unmanned Aircraft Systems and the Nordic Challenges

Abstract
The European Union (EU) regulations regarding the unmanned aircraft system (UAS) that came into force in 2021 emphasise technological and operational safety. Those regulations have been developed on the common rules in the field of civil aviation and establishing a European Union Aviation Safety Agency (EASA). The implementation of the regulations and compliant UAS operator activities are still the ground of the future. Therefore, it is essential to systematically gather information about all the factors affecting UAS operations in a safe and meaningful manner. This book chapter introduces the Nordic as well as generic challenges for UAS operations. The challenges can be divided into two main categories: technological and operational. Based on the extensive literature review and authors’ practical experience, both types of challenges are grouped by relevance topics. For example, the weather-related phenomena challenges overlap in both technological and operational categories but still can be mitigated differently. Technological challenges are usually mitigated by UAS design and human-computer interactions, while operational challenges may be mitigated with legislation and organisational activities and personal UAS operator qualities. Finally, the needs for further research on the challenges affecting safe UAS operations are discussed.
Vadim Kramar, Juha Röning, Juha Erkkilä, Henry Hinkula, Tanja Kolli, Anssi Rauhala

Applying an Icing Wind Tunnel for Drone Propeller Research, Validation of New Measurement Instrument

Abstract
Unmanned aerial vehicles have increased in popularity in recent years, especially the numbers of small multicopters. At the same time, icing research of such systems has been left behind, and results especially for propellers in this scale and in VTOL configuration are few. While the numbers of such systems have grown, also their usage in cold and icing conditions has increased.
A lot of research has been conducted for full-size airplanes and rotorcraft, but for drones the Reynolds numbers are relatively low in comparison. For this reason, it is important to research these systems in order to develop anti-icing methods and operate drones safely in all weather conditions. Also, currently used numerical tools are developed and validated for high Reynolds number conditions, but such validation has not yet been conducted for low Reynolds number flows.
VTT has operated an icing wind tunnel since 2009 primarily for experimental research in wind power technologies. Part of this line of research, methods for preventing icing of wind turbine blades, has been developed, and numerical tools developed in-house have been validated.
For developing the icing wind tunnel capabilities, a propeller dynamometer was added as a research instrument. This provides the means to research propellers used in drones to be researched in the wind tunnel. During the commissioning of the instrument, experiments in warm and dry conditions were conducted for validation and repeatability purposes. Experiments showed that the thrust measurements were accurate and repeatable, but torque measurement requires more development.
Petri Suurnäkki, Tuomas Jokela, Mikko Tiihonen

Self-Swarming for Multi-Robot Systems Deployed for Situational Awareness

Abstract
Machine-based situational awareness is a key element to conscious and intelligent interaction with the complex world we live in, be it for the individual unit, a complex dynamical system, or even complex systems. To create this awareness, the frequent gathering of accurate and real-time intelligence data is required to ensure timely, accurate, and actionable information. Unmanned Aerial Vehicles (UAVs) and other semi-autonomous cyber-physical systems are increasing among the mechanisms and systems employed to assess the state of the world around us and collect intelligence through surveillance and reconnaissance missions. The current state of the art for humanitarian and military operations is still relying on human-controlled flight/asset operations, but with increasingly autonomous systems comes an opportunity to offload this to the devices themselves. In this chapter, we present a principled and expandable methodology for evaluating the relative performance of a collective of autonomous devices in various scenarios. The proposed approach, which is illustrated with drone swarms as an example use case, is expected to develop into a generic tool to inform the deployment of such collectives. It is expected to provide the means to infer key parameter values from problem specifications, known constraints, and objective functions.
Fabrice Saffre, Hanno Hildmann, Hannu Karvonen, Timo Lind

Toward Invisible Drones: An Ultra-HDR Optical Cloaking System

Abstract
In order to reduce the visual detectability of drones, an active cloaking system was developed to match their color against the background sky. The system consists of an embedded control system connected to a smart LED tapestry and two color sensors, all capable of operating over an extreme dynamic range of 1 : 1 000 000. The cloaking system was applied to a commercial drone, and the results under widely varying outdoors conditions are reported. The cloaking system successfully matches all background sky conditions, save the solar disk or halo.
Karri Palovuori

Long-Term Autonomy in Forest Environment Using Self-Corrective SLAM

Abstract
Vehicles with prolonged autonomous missions have to maintain environment awareness by simultaneous localization and mapping (SLAM). Closed-loop correction used for SLAM consistency maintenance is proposed to be substituted by interpolation in rigid body transformation space in order to systematically reduce the accumulated error over different scales. The computation is divided into an edge-computed lightweight SLAM and iterative corrections in the cloud environment. Tree locations in the forest environment are sent via a potentially limited communication bandwidth. Data from a real forest site is used in the verification of the proposed algorithm. The algorithm adds new iterative closest point (ICP) cases to the initial SLAM and measures the resulting map quality by the mean of the root mean squared error (RMSE) of individual tree clusters. Adding 4% more match cases yields the mean RMSE of 0.15 m on a large site with 180 m odometric distance.
Paavo Nevalainen, Parisa Movahedi, Jorge Peña Queralta, Tomi Westerlund, Jukka Heikkonen

Future Possibilities and Challenges for UAV-Based Imaging Development in Smart Farming

Abstract
Technologies related to UAV (unmanned aerial vehicle) are developing rapidly. On the other hand, technologies related to farming are developing also, and several possibly revolutionizing technologies are about to become reality in farming. These technologies can set new goals and targets for the UAV imaging in smart farming. This work first reviews forthcoming technologies from measurement technologies, data management, execution technologies, and farming methods and then, as a top-down basis, formed possible imaging concepts for the future. The core future concepts were new imaging techniques with UAVs, data collection for digital twins and mapping for on-demand acting working UAVs and robotics. The presented technologies are at very early development stage.
Jere Kaivosoja

Role of Drones in Characterizing Soil Water Content in Open Field Cultivation

Abstract
Soil water content is a central topic in open field cultivation. In Finland’s boreal region with four thermal seasons, it has many roles which alter throughout the year. Climate change is changing the weather patterns, affecting all water-related processes and challenging the current farming practices. Better understanding of soils and their characteristics regarding response to water processes is called for, and data collection has a key role in this. Precision agriculture has been driving data intensification in farming. Unmanned aerial vehicles, or drones, have many applications and overall wide interest as an emerging technology in agriculture. Yet they lack an established role in day-to-day farming practices. Regarding data collection in open field cultivation, drones can be compared – or combined – with satellites, rovers, stationary devices, as well as plain old on-site observations by the farmer. In this study we give an overview of recent published literature, looking at data collection from the perspective of soil water information. We assess the opportunities and challenges of using drones in characterizing soil water content, mainly using soil and plant properties as proxies for it. Drones are useful in on-demand, nonintrusive, high-resolution spatial mapping of field properties. Soil moisture monitoring however requires frequent measurements, limiting the applicability of current drones.
Antti Halla, Nathaniel Narra, Tarmo Lipping

Ground-Penetrating Radar-Mounted Drones in Agriculture

Abstract
For precision farming, we need more and more accurate information not only about the crop, but also the soil. Surface measurement is fairly easy, with huge amounts of data being received from satellites all the time. With the help of drones, that data can still be refined, but the measurement price increases depending on the equipment as well as working time. With regard to soil measurement, measurement slows down and becomes more expensive.
The study mapped research papers of ground-penetrating radar and those different topics where they have been used. The topics were limited to agriculture only. The used frequencies were discovered from every topic. The study investigated artificial intelligence papers related to ground-penetrating radar and needs to begin an own artificial intelligence study in this subject. Finally, various concepts were evaluated for conducting ground-penetrating radar research. One of these concepts was to connect a ground-penetrating radar to a drone.
Petri Linna, Antti Halla, Nathaniel Narra

A Minimalist Approach to Yield Mapping of Standing Wheat Crop with Unmanned Aerial Vehicles

Abstract
Yield estimation and mapping of standing crops are often based on tedious data gathering procedures that can be daunting and not cost-effective in the absence of harvester-mounted yield mappers. A cost-effective solution with reasonable accuracy has greater potential for adoption especially if one can leverage latest machine learning tools to supplant tedious processes. This study conducts a feasibility test in using drones in a minimalist sampling strategy to estimate wheat yields over different productivity zones. The first step is to use unsupervised clustering of spatio-temporal multivariate data to delineate zones of homogeneous vegetation vigour. These zones are assumed to capture the variability in yield and aid in designing an efficient sampling strategy. The second step involves using a UAV-mounted camera to capture digital images to estimate the wheat head count and then to derive a yield estimate within the image field of view. Using physical counting of grains within a 0.5 × 0.5 m reference frame, the performance of the estimation procedure was observed. The results show that while the workflow is tractable and friendly in low-resource environments, the accuracy is poor at this stage. Pertinent challenges and potential improvement strategies are discussed.
Nathaniel Narra, Antti Halla, Petri Linna, Tarmo Lipping

Assessment of Crop Yield Prediction Capabilities of CNN Using Multisource Data

Abstract
The growing abundance of digitally available spatial, geological, and climatological data opens up new opportunities for agricultural data-based input–output modeling. In our study, we took a convolutional neural network model previously developed on Unmanned Aerial Vehicle (UAV) image data only and set out to see whether additional inputs from multiple sources would improve the performance of the model. Using the model developed in a preceding study, we fed field-specific data from the following sources: near-infrared data from UAV overflights, Sentinel-2 multispectral data, weather data from locally installed Vantage Pro weather stations, topographical maps from National Land Survey of Finland, soil samplings, and soil conductivity data gathered with a Veris MSP3 soil conductivity probe. Either directly added or encoded as additional layers to the input data, we concluded that additional data helps the spatial point-in-time model learn better features, producing better fit models in the task of yield prediction. With data of four fields, the most significant performance improvements came from using all input data sources. We point out, however, that combining data of various spatial or temporal resolution (i.e., weather data, soil data, and weekly acquired images, for example) might cause data leakage between the training and testing data sets when training the CNNs and, therefore, the improvement rate of adding additional data layers should be interpreted with caution.
Petteri Nevavuori, Nathaniel Narra, Petri Linna, Tarmo Lipping

Backmatter

Weitere Informationen

Premium Partner

    Bildnachweise