- Robotics and Sensor-Based Localization
- Robotic Path Planning Algorithms
- 3D Surveying and Cultural Heritage
- Guidance and Control Systems
- Software Reliability and Analysis Research
- Risk and Safety Analysis
- Safety Systems Engineering in Autonomy
- Remote Sensing and LiDAR Applications
- Aerospace Engineering and Applications
- Aerospace and Aviation Technology
- Infrared Target Detection Methodologies
- Fault Detection and Control Systems
- UAV Applications and Optimization
- Real-time simulation and control systems
- Nuclear Physics and Applications
- Currency Recognition and Detection
- Video Surveillance and Tracking Methods
- Radiation Detection and Scintillator Technologies
- Robotics and Automated Systems
- Control and Dynamics of Mobile Robots
- Smart Agriculture and AI
- Aerospace Engineering and Control Systems
- Advanced Control Systems Design
- Optical measurement and interference techniques
- Inertial Sensor and Navigation
Vanderbilt University
2021-2024
Integrated Software (United States)
2021
Obuda University
2010-2020
Network Technologies (United States)
2020
John von Neumann University
2018
This paper introduces a solution to stand-alone system based, real-time object-detection, can efficiently facilitate the search for missing persons with an unmanned aerial vehicle. The challenge is implementation of systems and training given deep neural network desired task. describes methods procedures currently in use, as well possible tools. Subsequently, autonomous aircraft system, which carries detection introduced. In section about detection, we will introduce TensorFlow lite-based...
The AERObot is a special ARM microcontroller-based autopilot for small and medium size UAVs 1 developed at Óbuda Universtiy research purposes.The aim of the was to create generic which capable controlling different design, weight structure airframes without any complex parameter or model recalculation as usual e.g.switching between tailless classic tail aircafts.For this purpose simple, desired heading-based guidance method easy visualize needs only few parameters be set while quality...
Autonomous Cyber Physical Systems (CPSs) are often required to handle uncertainties and self-manage the system operation in response problems increasing risk operating paradigm. This may arise due distribution shifts, environmental context, or failure of software hardware components. Traditional techniques for assessment focus on design-time such as hazard analysis, reduction, assurance cases among others. However, these static, do not consider dynamic contexts failures systems face at...
The tuning of the navigation controllers for an Unmanned Aerial Vehicle (UAV) is a relatively long process. reason that can be tuned during test flights only. This must started in calm weather then continue higher and wind, while UAV reaches its given limits. aim this research to develop method small-size UAVs reduce time tuning. verification hardware loop (HIL) simulation has high priority. result process shown by comparison simulations. Studies have been made with various methods HIL...
AirGuardian is a complex of an Unmanned Aerial Vehicle and ground station UAV hardware software systems which has been developed at Obuda University. The the autopilot (AERObot), antenna tracker control were simultaneously created resulting in optimal cooperation modules. aim research on AERObot – special was to create generic capable controlling different designs, weights structures airframes without any mathematical model recalculation.
The AERObot autopilot for small and medium size unmanned aerial vehicles (UAVs) developed at Óbuda Universtiy has multiple control systems. It is possible to switch between the systems even during in flight. purpose of current research was examine applicability full fuzzy flight (takeoff, cruise land) instead partial or hybrid [1, 2, 3]. easy tuning parameters features quite important because one should different sized designed planes. Since safety flight, life value most important, real...
Parameters of the onboard electronics a small sized (0.5-3m) and light weight (0.5-5kg) UAV is highly limited. Usually there only low powered, narrow bandwidth 2.4 GHz radio modem (e.g. XBee or XStream) for communication. The useful range these modules 1-2 km. Over that distance, noise channel very high. There no way to use high gain, physically large omnidirectional antenna on UAV. High gain directional yagi patch) can be used ground station only. These modems operate in half-duplex mode....
With the spread of photogrammetry processes, photo-based 2D/3D reconstruction became general, in research as well industry. Source images are taken using either a handheld camera or an automated fixed to carrier, UAV, then they matched during post-processing. The price digital microbolometer-based high-resolution (1 megapixel) thermal cameras is currently very high, but these, compared RGB (16-20 megapixel), still considered have low-resolution, this way employing present case not feasible....
Autonomous Cyber-Physical Systems (CPS) must be robust against potential failure modes, including physical degradations and software issues, are required to self-manage contingency actions for these failures. Physical often have a significant impact on the vehicle dynamics causing irregular behavior that can jeopardize system safety mission objectives. The paper presents novel Behavior Tree-based autonomy architecture includes Fault Detection Isolation Learning-Enabled Component (FDI LEC)...
In unmanned aerial vehicle operations as well in aviation the airflow direction and speed plays a major role. The wind may limit use of aircraft, determines takeoff landing. case small size UAVs (0.5 - 4 m wingspan, 0.5 10 kg weight) strength is quite important, because airspeed same scale, turbulence can affect flight path. general methods measurement cannot be applied onboard UAV. Although ground measured data sufficient for takeoff, but it irrelevant when UAV landing different place, e.g....
During their flight, small-sized drones use satelite navigation (the most widespread is GPS). This means that frequent coordinate information can be recorded in the entire duration of flight with varying frequency according to type. Several aerial photography applications utilize these data. If drone equipped a sensitive gamma detector coordinates assigned measurement These groups data provide an opportunity during detector-based scan area determine its radiation distribution. The method...
Air pollution in settlements constitutes a rapidly increasing problem. As long as the size and consistence of given settlement are quantitatively unknown, effective counter-measures can not be taken. is static, other words, it may greatly vary over time. Using this experimental method, spatial temporal distribution settlement's air pollutants, including their composition, exhibited. The components pollutants show type pollutant emission area. industrial or residential heating source...
Abstract In the last decade, rate of industrial usage fixed-wing and blended wing aircraft has increased. A 1–2-km 2 area can be surveyed by such a drone within 30 to 60 minutes, without any special infrastructure, this repeated at time. This provides an opportunity conduct automatized surveys time series data testing, which used as basis decide specific processes. The state development plants monitored well spread pests efficiency procedures that protect against them. During surveys,...
Unmanned aerial vehicles from micro to large scale are a common research topic in the latest years. Small size (under 3 m wingspan and between 1-15 kg all up weight) UAVs autopilots usually have no redundancy been not prepared for emergency situations. Loss of control, power management, engine or faulty sensor could cause serious damage. To prevent disaster many things must be considered added UAV such as redundant manual autonomous controller, fault detection isolation subsystem (FDI)...
In today's world the expansion of autonomous robots is getting bigger and bigger, while in everyday life people can meet devices which are capable managing a wide range tasks independently. order to manage these equipped with sensors, they use be able sample analyze parameters their environment. The obtained information modify help own operation or rather its smooth running. Particular navigate themselves using data utilized for orientation if necessary obstacle avoidance order, that robot...
Efficient path optimization for drones in search and rescue operations faces challenges, including limited visibility, time constraints, complex information gathering urban environments. We present a comprehensive approach to optimize UAV-based neighborhood areas, utilizing both 3D AirSim-ROS2 simulator 2D simulator. The planning problem is formulated as partially observable Markov decision process (POMDP), we propose novel ``Shrinking POMCP'' address constraints. In the AirSim environment,...
Nowadays the autonomous robots are spreading more widely, meanwhile people can meet such devices in everyday life, which do different tasks independently. The equipped with sensors to sampling environment's parameters and analyze data achieve their goals. recovered information will modify help own operations smoothly. Such also be cameras that provide visual about environment of robot. Stereo allow 3D reconstruction spatial accurate efficient algorithms. aim task is create a system includes...
Photogrammetry based 3D model creation provides a new opportunty to survey and evaluate natural arificial surface formations. The photos needed for building can be taken using fixed wing aircraft or multicopters. These machines are more economical capable of precise route tracking than big operated by human personnel. Depending on the size area (0.5 10km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ), finished within an hour. volume...
Abstract In the last decade modern agriculture used significant resources for automated evaluation. Game damage and crop evaluation prediction are main focus of precision agriculture. At John von Neumann Faculty Informatics, Óbuda University, Hungary, researchers together with agricultural experts developing methods high-resolution survey data. With locally developed unmanned aerial vehicles (UAVs) can be easily done 1-2km 2 area from a single flight. The paper presents detailed method early...
Small-sized drones, either having classical fixed-wing design or the so rapidly widespread rotorcraft design, are now revolutionizing complete work process of aerial surveys. In paper, we will discuss possibilities quality characteristics large-scale point cloud processing, already introduced in our previous work, and primarily reduction execution time large-point processing presented work. Based on developed by us, survey area, typically a quarry, using UAVs, then create high resolution 3D...
With new methods of 3D model creation, the examination real objects and natural or artificial formations in virtual space become possible. A precondition is that models be created along principles photogrammetry. The bases method introduced paper are precise flight ability small-sized machines piloted by a robot mounted camera with distortion-free optics. Surveys conducted such devices can faster more economical than usage conventional aircraft requiring human personnel. As long as all...