Twirre is a new architecture for mini-UAV platforms designed for autonomous flight in both GPS-enabled and GPS-deprived applications. The architecture consists of low-cost hardware and software components. High-level control software enables autonomous operation. Exchanging or upgrading hardware components is straightforward and the architecture is an excellent starting point for building low-cost autonomous mini-UAVs for a variety of applications. Experiments with an implementation of the architecture are in development, and preliminary results demonstrate accurate indoor navigation
MULTIFILE
This research reviews the current literature on the impact of Artificial Intelligence (AI) in the operation of autonomous Unmanned Aerial Vehicles (UAVs). This paper examines three key aspects in developing the future of Unmanned Aircraft Systems (UAS) and UAV operations: (i) design, (ii) human factors, and (iii) operation process. The use of widely accepted frameworks such as the "Human Factors Analysis and Classification System (HFACS)" and "Observe– Orient–Decide–Act (OODA)" loops are discussed. The comprehensive review of this research found that as autonomy increases, operator cognitive workload decreases and situation awareness improves, but also found a corresponding decline in operator vigilance and an increase in trust in the AI system. These results provide valuable insights and opportunities for improving the safety and efficiency of autonomous UAVs in the future and suggest the need to include human factors in the development process.
DOCUMENT
Twirre V2 is the evolution of an architecture for mini-UAV platforms which allows automated operation in both GPS-enabled and GPSdeprived applications. This second version separates mission logic, sensor data processing and high-level control, which results in reusable software components for multiple applications. The concept of Local Positioning System (LPS) is introduced, which, using sensor fusion, would aid or automate the flying process like GPS currently does. For this, new sensors are added to the architecture and a generic sensor interface together with missions for landing and following a line have been implemented. V2 introduces a software modular design and new hardware has been coupled, showing its extensibility and adaptability
DOCUMENT
This paper introduces a novel distributed algorithm designed to optimize the deployment of access points within Mobile Ad Hoc Networks (MANETs) for better service quality in infrastructure less environments. The algorithm operates based on local, independent execution by each network node, thus ensuring a high degree of scalability and adaptability to changing network conditions. The primary focus is to match the spatial distribution of access points with the distribution of client devices while maintaining strong connectivity to the network root. Using autonomous decision-making and choreographed path-planning, this algorithm bridges the gap between demand-responsive network service provision and the maintenance of crucial network connectivity links. The assessment of the performance of this approach is motivated by using numerical results generated by simulations.
DOCUMENT
Friday 27th October 2018 the official kick-off event unfolded at Inholland University of Applied Sciences in Delft. Participants from numerous companies and research establishments congregated to make new acquaintances and share their ideas. The dean of Inholland Delft, Gerard van Oosten, gave a welcoming speech. Next lector Robotica Cock Heemskerk formally introduced the unique HiPerGreen project. Several guest speakers presented additional subject related information: Jeremy Harbinson (distinguished researcher in plant physiology atm Wageningen UR), David Pajares (AvioniCS – a company specialised in rapid prototyping and control systems for small UAVs) and Arash Noroozi (ElpaNav, a start-up company for localisation technology). Lucien Fesselet, assistant project manager, resumed the day with a brief history of the ‘Drones in de kas’ project where HiPerGreen evolved from. Then the audience were split into smaller groups to assess the risks associated within each project work package. A important outcome was the consensus that the business case validation should be started right from the beginning. The kick-off was concluded with a drink.
DOCUMENT
Artificial intelligence (AI) integration in Unmanned Aerial Vehicle (UAV) operations has significantly advanced the field through increased autonomy. However, evaluating the critical aspects of these operations remains a challenge. In order to address this, the current study proposes the use of a combination of the 'Observe-Orient-Decide-Act (OODA)' loop and the 'Analytic Hierarchy Process (AHP)' method for evaluating AI-UAV systems. The integration of the OODA loop into AHP aims to assess and weigh the critical components of AI-UAV operations, including (i) perception, (ii) decision-making, and (iii) adaptation. The research compares the results of the AHP evaluation between different groups of UAV operators. The findings of this research identify areas for improvement in AI-UAV systems and guide the development of new technologies. In conclusion, this combined approach offers a comprehensive evaluation method for the current and future state of AI-UAV operations, focusing on operator group comparison.
DOCUMENT
Sinds pakweg 2006 is een enorme verscheidenheid aan drones of beter gezegd Unmanned Aerial Vehicles (UAVs) voor zowel professionals, als amateurs beschikbaar gekomen. Sommige drones worden voor specifiek doe ontwikkeld met bijvoorbeeld een grote draagcappaciteit of juist een groot bereik. Uiteraard kunnen drones ook in de gevelbranche hun waarde laten gelden. In: Gevelbouw, ISSN 1572-1310, jaargang 15, nr. 1, p. 14-15
MULTIFILE
Wat zijn belangrijke succesfactoren om onderzoek, onderwijs en ondernemen bij elkaar te brengen, zó dat 'het klikt'. De uitdaging voor de toekomst van bedrijven in de smart factoryligt bij data science: het omzetten van ruwe (sensor) data naar (zinnige) informatie en kennis, waarmee producten en diensten verbeterd kunnen worden. Tevens programma van het symposium t.g.l. inauguratie 3 december 2015
MULTIFILE
The objective of this study is to evaluate the energetic, exergetic, sustainability, economic and environmental performances of a 4-cylinder turbodiesel aviation engine (TdAE) used on unmanned aerial vehicles for the take-off operation mode to assess the system with large aspects. Energy efficiency of the system is found as 43.158%, while exergy efficiency 40.655%. Thermoeconomic analysis gives information about the costs of the inlet and outlet energy and exergy flows of the engine. Hourly levelized total cost flow of the TdAE is found as 21.036 $/h, when the hourly fuel cost flow of the engine is found as 30.328 $/h. The waste exergy cost parameter is determined as 0.0144 MJ/h/$ from exergy cost-energy-mass (EXCEM) analysis, while it is estimated as 14.043 MJ/$ from modified-EXCEM analysis. Environmental damage cost analysis evaluates the cost formation of the exhaust emissions. The total environmental damage cost of the TdAE is computed as 12.895 $/h whilst specific environmental damage cost is determined as 0.054 $/MJ for 494.145 MJ/h TdAE power production. It is assessed that the main contributors to the environmental impact rate of the TdAE are the fuel consumption and the formation pollutants of combustion reaction.
DOCUMENT
In recent years, drones have increasingly supported First Responders (FRs) in monitoring incidents and providing additional information. However, analysing drone footage is time-intensive and cognitively demanding. In this research, we investigate the use of AI models for the detection of humans in drone footage to aid FRs in tasks such as locating victims. Detecting small-scale objects, particularly humans from high altitudes, poses a challenge for AI systems. We present first steps of introducing and evaluating a series of YOLOv8 Convolutional Neural Networks (CNNs) for human detection from drone images. The models are fine-tuned on a created drone image dataset of the Dutch Fire Services and were able to achieve a 53.1% F1-Score, identifying 439 out of 825 humans in the test dataset. These preliminary findings, validated by an incident commander, highlight the promising utility of these models. Ongoing efforts aim to further refine the models and explore additional technologies.
MULTIFILE
