Filtern
Erscheinungsjahr
- 2023 (130) (entfernen)
Dokumenttyp
- Wissenschaftlicher Artikel (49)
- Konferenzveröffentlichung (25)
- Video (21)
- Teil eines Buches (Kapitel) (16)
- Beitrag zu einer (nichtwissenschaftlichen) Zeitung oder Zeitschrift (4)
- Sonstiges (4)
- Rezension (3)
- Buch (Monographie) (2)
- Masterarbeit (2)
- Preprint (2)
Schlagworte
- Bionik (4)
- Dissipative Particle Dynamics (2)
- Field measurement (2)
- Solar modules (2)
- 360° Panorama (1)
- AI (1)
- Additive manufacturing Directed energy deposition-arc 316L stainless steel Corrosion behavior Electrochemical corrosion (1)
- Arbeitskräftemangel (1)
- Augmented Multiphase (1)
- Augmented Three-Phase AC-Railgun (1)
Institut
- Informatik und Kommunikation (27)
- Fachbereiche (15)
- Wirtschaftsrecht (15)
- Maschinenbau Bocholt (10)
- Institut für biologische und chemische Informatik (8)
- Westfälisches Energieinstitut (7)
- Wirtschaft Gelsenkirchen (6)
- Wirtschaft und Informationstechnik Bocholt (6)
- Maschinenbau und Facilities Management (5)
- Institute (2)
Problem
- How to effectively use aerial robots to support rescue forces?
- How to achieve good flight characteristics and long flight times?
- How to enable simple and intuitive control?
- How to efficiently record image data of the environment?
- How to generate flight and image data for rescue forces?
Implementation:
The flying robot was designed in Autodesk Fusion360. In order to achieve high stability as well as low weight, the frame was milled from carbon. Mounts such as for GPS and 360° camera were 3D printed. A special feature is that the flying robot is not visible in the panoramic view of the 360° camera. The flight controller of the robot was set up using Ardupilot. The communication with the robot is done via MAVLink (UDP).To support different platforms, a software was realized as a web application. The front end was created using HTML, CSS and Javascript.
The back end is based on Flask-Socket-IO (Python). For the intelligent recognition of motor vehicles a micro controller with an integrated camera is used. For the post-processing of flight and video data a pipeline was implemented for automation.
The video shows a very high resolution 3D point cloud !!! of the outdoor area of the German Rescue Robotics Center. For the recording, a 25-second POI flight was performed with a Mavic 3. From the 4K video footage captured during this flight, 77 images were cropped and localized within 4 minutes using colmap and processed using Neural Radiance Fields (NeRF). The nerfacto model of Nerfstudio was trained on an Nvidia RTX 4090 for 8 minutes. In summary, a top 3D model is available to task forces after about 13 minutes. The calculation is performed locally on site by the RobLW of the DRZ. The video shown here shows a free camera path rendered at 60 hz (Full HD).
In this paper, we investigate the influence of different disease groups on the size of different 1 anatomical structures. To this end, we first modify and improve an existing anatomical segmentation 2 model. Then, we use this model to segment 104 anatomical structures from computed tomography 3 (CT) scans and compute their volumes from the segmentation. After correlating the results with each 4 other, we find no new significant correlations. After correlating the volume data with known diseases 5 for each case, we find two weak correlations, one of which has not been described before and for 6 which we present a possible explanation.
Nerf(acto) for the 3D modeling of the Computer Science building of Westfälische Hochschule GE
(2023)
The video shows a very high resolution 3D point cloud !!! of the computer science building of the University of Applied Science Gelsenkirchen. For the recording a 3 minute flight with a M30T was performed. The 105 images taken by the wide-angle camera during this flight were localized within 3 minutes using colmap and processed using Neural Radiance Fields (NeRF). The nerfacto model of Nerfstudio was trained on an Nvidia RTX 4090 for 8 minutes. Thus, a top 3D model is available after about 15 minutes.
The video shown here shows a free camera path rendered at 60 hz (Full HD).
From the 360° images of the former video (
• German rescue robotic center captured... ) we now generate the 3D point cloud. The UAV needs 3 minutes to capture the outdoor scenario and the hall from inside and outside. The 3D point cloud generation is 5x slower than the video. It uses a VSLAM algorithm to localize the k-frames (green) and with 3 k-frames it use a 360° PatchMatch algorithm implemented at a NVIDIA graphic card (CUDA) to calculated the dense point clouds.The hall ist about 70 x 20 meters.
The video shows the first test of a small spherical UAV (35 cm) with 4 rotors for missions in complex environments such as buildings, caves or tunnels. The spherical design protects the vehicle's internal components and allows the UAV to roll over the ground when the environment allows. The drone can land and take off in any position and come into contact with objects without endangering the propellers and can restart even after crashes.
Sperical UAV: Crash Test with 1/2 liter bottle from 2 meters
Gaussian Splatting: 3D Reconstruction of a Chemical Company After a Tank Explosion in Kempen 8/2023
(2023)
The video showcases a 3D model of a chemical company following a tank explosion that occurred on August 17, 2023, in Kempen computed with the gaussian splatting algorithm. Captured by a compact mini drone measuring 18cm x 18cm and equipped with a 360° camera, these images offer an intricate perspective of the aftermath. The computation need 29 minutes and uses 2770 images (~350 equirectangular images). After a comprehensive aerial survey and inspection of the 360° images taken within the facility, authorities confirmed that it was safe for the evacuated residents to return to their homes. See also:
https://www1.wdr.de/fernsehen/aktuelle-stunde/alle-videos/video-grosser-chemieunfall-in-kempen-100.html
The video showcases a 3D model of a chemical company following a tank explosion that occurred on August 17, 2023, in Kempen computed with the AI algorithm Neural Radiance Field (NeRF). Captured by a compact mini drone measuring 18cm x 18cm and equipped with a 360° camera, these images offer an intricate perspective of the aftermath. After a comprehensive aerial survey and inspection of the 360° images taken within the facility, authorities confirmed that it was safe for the evacuated residents to return to their homes. See also:
https://www1.wdr.de/fernsehen/aktuelle-stunde/alle-videos/video-grosser-chemieunfall-in-kempen-100.html
ARGUS is a tool for the systematic acquisition, documentation and evaluation of drone flights in rescue operations. In addition to the very fast generation of RGB and IR orthophotos, a trained AI can automatically detect fire, people and cars in the images captured by the drones. The video gives a short introduction to the Aerial Rescue and Geospatial Utility System -- ARGUS
Check out our Github repository under
https://github.com/RoblabWh/argus/
You can find the dataset on kaggle under
https://www.kaggle.com/datasets/julienmeine/rescue-object-detection
This video features a flight test conducted in our robotics lab, showcasing a custom-built thermal camera drone. We've enhanced a DJI Avata with a specialized thermal camera system. With its compact dimensions measuring 18 x 18 x 17 cm, this drone is designed to navigate and provide critical thermal information within post-fire or post-explosion environments. For more insights, be sure to check out our previous videos on this channel.
Desert ants Cataglyphis spec. monitor inclination and distance covered through force-based sensing in their legs. To transfer this mechanism to legged robots, artificial neural networks are used to determine the inclination angle of an experimental ramp from the motor data of the legs of a commercial hexapod walking robot. It is possible to determine the inclination angle of the ramp based on the motor data of the robot legs read out during a run. The result is independent of the weight and orientation of the robot on the ramp and hence robust enough to serve as an independent odometer.
In the realm of digital situational awareness during disaster situations, accurate digital representations,
like 3D models, play an indispensable role. To ensure the
safety of rescue teams, robotic platforms are often deployed
to generate these models. In this paper, we introduce an
innovative approach that synergizes the capabilities of compact Unmaned Arial Vehicles (UAVs), smaller than 30 cm, equipped with 360° cameras and the advances of Neural Radiance Fields (NeRFs). A NeRF, a specialized neural network, can deduce a 3D representation of any scene using 2D images and then synthesize it from various angles upon request. This method is especially tailored for urban environments which have experienced significant destruction, where the structural integrity of buildings is compromised to the point of barring entry—commonly observed post-earthquakes and after severe fires. We have tested our approach through recent post-fire scenario, underlining the efficacy of NeRFs even in challenging outdoor environments characterized by water, snow, varying light conditions, and reflective surfaces.
360° and IR- Camera Drone Flight Test: Superimposition of two data sources for Post-Fire Inspection
(2023)
This video highlights a recent flight test carried out in our cutting-edge robotics lab, unveiling the capabilities of our meticulously crafted thermal and 360° camera drone! We've ingeniously upgraded a DJI Avata with a bespoke thermal and 360° camera system. Compact yet powerful, measuring just 18 x 18 x 17 cm, this drone is strategically engineered to effortlessly navigate and deliver crucial thermal and 360° insights concurrently in post-fire or post-explosion environments.
The integration of a specialized thermal and 360° camera system enables the simultaneous capture of both data sources during a single flight. This groundbreaking approach not only reduces inspection time by half but also facilitates the seamless superimposition of thermal and 360° videos for comprehensive analysis and interpretation.
At the integration sprint of the E-DRZ consortium in march 2023 we improve the information captured by the human spotter (of the fire brigade) by extending him through a 360° drone i.e. the DJI Avata with an Insta360 on top of it. The UAV needs 3 minutes to capture the outdoor scenario and the hall from inside and outside. The hall ist about 70 x 20 meters. When the drone is landed we have all information in 360° degree at 5.7k as you can see it in the video. Furthermore it is a perfect documentation of the deployment scenario. In the next video we will show how to spatial localize the 360° video and how to generate a 3D point cloud from it.
Problem: A group of robots, called a swarm, is placed in an unknown environment and is supposed to explore it independently. The goal of the exploration is the creation of a common map.
Implementation
- Equipping six Kobuki robots with appropriate sensor technology, a large battery, a router and the Jetson board
- Setup of the Jetson-Boards with self-made ROS2 nodes and the set up mesh network
- Writing of launch files for the common start of all functions
- Reinforcement learning is used to train an AI that controls the swarm by selecting points for the robots to approach and navigating to them and navigating them there.
- Setting up a responsive website using Angular and the Bootstrap
Framework.
At the integration sprint of the E-DRZ consortium in march 2023 we improve the information captured by the human spotter (of the fire brigade) by extending him through a 360° drone. The UAV needs 3 minutes to capture the outdoor scenario and the hall from inside and outside. The hall ist about 70 x 20 meters. When the drone is landed we have all information in 360° degree at 5.7k as you can see it in the video. Furthermore it is a perfect documentation of the deployment scenario. In the next video we will show how to spatial localize the 360° video and how to generate a 3D point cloud from it.
In this paper, we present a method for detecting objects of interest, including cars, humans, and fire, in aerial images captured by unmanned aerial vehicles (UAVs) usually during vegetation fires. To achieve this, we use artificial neural networks and create a dataset for supervised learning. We accomplish the assisted labeling of the dataset through the implementation of an object detection pipeline that combines classic image processing techniques with pretrained neural networks. In addition, we develop a data augmentation pipeline to augment the dataset with utomatically labeled images. Finally, we evaluate the performance of different neural networks.
The dataset is used for 3D environment modeling, i.e. for the generation of dense 3D point clouds and 3D models with PatchMatch algorithm and neural networks. Difficult for the modeling algorithm are the reflections of rain, water and snow, as well as windows and vehicle surface. In addition, lighting conditions are constantly changing.
Theoretischer Hintergrund: Mut ist ein bislang wenig erforschtes Konstrukt. In der Forschung existieren unterschiedliche Betrachtungsweisen und Annahmen, u.a. hinsichtlich der Art des Konstruktes oder der Einflussfaktoren. Es existieren zudem, insbesondere im deutschsprachigen Raum, nur wenige Instrumente zur Messung von Mut. Diese zeigen zudem oftmals verbesserungsfähige oder unzureichende psychometrische Gütekriterien.
Fragestellung: Auf Basis einer umfangreichen Literaturrecherche ist unser Ziel, neben einem wissenschaftlichen Beitrag zur Klärung des Konstruktes, einen Selbstbeschreibungsfragebogen zur Messung von Mut im Arbeitskontext zu konstruieren, welcher den gängigen psychometrischen Gütekriterien entspricht und perspektivisch im Rahmen der Personalauswahl und Personalentwicklung eingesetzt werden könnte.
Methodik: Der Erstentwurf des Selbstbeschreibungsfragebogens zu Mut im Arbeitskontext besteht aus den Dimensionen sozialer Mut und persönlicher Mut. Zur psychometrischen Überprüfung des Fragebogenentwurfs haben wir eine Querschnittstudie in Form einer Online-Befragung durchgeführt (N = 253). Der Fokus lag auf der Itemanalyse, sowie auf der Überprüfung der Reliabilität und der Validität.
Ergebnisse: Die Reliabilität beträgt α = .92 und α = .91. Die exploratorische Faktorenanalyse stützt das 2-Faktoren-Modell. Es existieren erwartungsgemäß signifikante positive Korrelationen mit inhaltsähnlichen Konstrukten, u.a. arbeitsplatzbezogene Selbstwirksamkeit oder Extraversion und negative signifikante Korrelationen zu Neurotizismus und Psychopathie. Zusätzlich zeigen Mittelwertsvergleiche für
Geschlecht und Führungsverantwortung Ergebnisse gemäß dem aktuellen Stand der Forschung.
Diskussion Der Selbstbeschreibungsfragebogen zeigt klares Potenzial für die Nutzung im Rahmen der Personalauswahl und Personalentwicklung. Im Rahmen der Fragebogenkonstruktion ist es entscheidend das Konstrukt so eng wie möglich einzugrenzen. Die Fokussierung auf eine spezifische Form von
Mut scheint der Schlüssel zu sein, um ein den gängigen Anforderungen an psychometrische Gütekriterien entsprechendes Instrument zu entwickeln.
Sowohl im Online-, aber auch im stationären Handel sind schon etliche innovative immersive Anwendungen entstanden, die neue kognitive und affektive Interaktions- und Informationsmöglichkeiten bieten. In den Bereichen Kunst, Immobilien, Architektur, Gaming, Fashion, Stadtplanung und -führungen finden sich ebenfalls mehr und mehr AR/VR Anwendungen. In diesem Beitrag wird nach einer Sichtung ausgewählter immersiver Projekte ein Konzept zur Nutzung von AR bzw. VR für Leerstände in einer ehemals attraktiven Einkaufsmeile in Gelsenkirchen vorgestellt.
Eine der ersten Informationen, die man von seinem Gegenüber wahrnehmen kann, ist meist das äußere Erscheinungsbild. Wird dies als attraktiv bewertet, wirkt es sich in vielen Lebensbereichen, wie auch im beruflichen Umfeld, vorteilhaft aus (Willis & Todorov, 2006; Marlowe et al., 1996; Langlois et al., 2000; Frieze et al., 1991). Im Rahmen der Bachelor-Thesis wurde der Einfluss physischer Attraktivität in Bezug
auf das Fehlverhalten von Mitarbeitenden in Form einer Vignettenstudie untersucht. Es wurden die folgenden Forschungsfragen formuliert: Werden attraktive Mitarbeitende trotz eines gezeigten Fehlverhaltens als vertrauenswürdiger eingeschätzt als unattraktive Mitarbeitende? Wird eine Bestrafung in Form einer Abmahnung und einer Kündigung bei unattraktiven Mitarbeitenden für angemessener gehalten als bei attraktiven Mitarbeitenden? Es wurde vermutet, dass sich auch hier die physische Attraktivität positiv auswirken kann.
Die postulierten Hypothesen wurden mit einem Stichprobenumfang von N = 679 im Between-Subjects Design eines Online-Experiments untersucht. Insgesamt gab es vier Vignetten, die sich in der Attraktivität einer dargestellten Mitarbeiterin und der Art des kontraproduktiven Arbeitsverhaltens unterschieden. Die Datenanalyse zeigte eine signifikante Interaktion zwischen der physischen Attraktivität und der Art des kontraproduktiven Arbeitsverhaltens auf, F(1,675) = 4.02, p = .046, η² = .01. Im Falle eines interpersonal schädigenden Arbeitsverhaltens wurde eine Kündigung bei der attraktiven Mitarbeiterin als angemessener bewertet. Im Falle eines organisationalschädigenden Arbeitsverhaltens hingegen wurde eine Kündigung bei der unattraktiven Mitarbeiterin als angemessener bewertet. Aus diesen Forschungsergebnissen wurden praktische Implikationen, wie zum Beispiel die Sensibilisierung für derartige Einflüsse durch Schulungen, abgeleitet. Auch Ansätze für zukünftige Forschungen, wie die Variation im Geschlecht der Stimulusperson, wurden vorgeschlagen.
Theoretischer Hintergrund: In der psychologischen Führungsforschung zeigt sich ein Shift von traditionellem Management hin zu progressiveren Führungsmodellen, in denen das Gemeinwohl und die nachhaltige Führung von Mitarbeitenden anstelle des Selbstinteresses von Führungskräften treten.
Diese Modelle bewegen sich allerdings weiter im traditionellen Paradigma, dass effektive Führung komplexe Systeme gezielt beeinflussen und auf erwünschte Zielzustände hin ausrichten kann.
Fragestellung: Folgt man dem systemischen Ansatz, so können Führungskräfte das organisationale System nicht beeinflussen, sondern lediglich die Relationen seiner Bestandteile und Rahmenbedingungen für Emergenz schaffen. So lässt es sich beispielsweise aus der Theorie komplexer adaptiver Systeme und dem darauf basierenden Complexity Leadership Ansatz ableiten. Wenngleich viele Wissenschaftler*innen hierin Potential effektiver Führung sehen, mangelt es doch an konzeptionellen und psychometrischen Grundlagen sowie empirischer Evidenz für die Effektivität systemischer Führung.
Methodik: Wir stellen einen Fremdbeschreibungsfragebogen zur Messung systemischer Führung vor (N ges = 8770) sowie die mit diesem Instrument gewonnenen Ergebnisse verschiedener Feldstudien (k = 28) zu Antezedenzien, Auswirkungen und Randbedingungen systemischer Führung. Wir berücksichtigen auch die inkrementelle Varianzaufklärung über transformationale Führung.
Ergebnisse: Das Systemic Leadership Inventory ermöglicht die Einschätzung systemischer Kompetenzen
von Führungskräften.
Diskussion: Zukünftige Forschung sollte sich mit der Entwickelbarkeit systemischer Führung beschäftigen. Limitationen unseres Forschungsprojekts werden diskutiert.
Der sozioanalytischen Theorie folgend argumentieren wir, dass Machiavellismus nur im Falle einer hohen emotionalen Einflusskompetenz zuträglich für den objektiven Karriereerfolg ist.
In den Daten unserer fragebogenbasierten Querschnittsstudie zum jährlichen Bruttoeinkommen mit N = 149 Mitarbeitenden aus der Privatwirtschaft zeigen sich unter Kontrolle von Alter, Geschlecht und Führungsspanne weder signifikante Haupteffekte für Machiavellismus, noch für emotionale Intelligenz, dafür aber ein hypothesenkonformer Interaktionseffekt.
Unter Berücksichtigung methodischer Limitationen, die vorrangig an die Messung der beiden die Studie konstituierenden Konstrukte geknüpft sind, werden wissenschaftliche und praktische Implikationen dieses Befunds diskutiert.
The number of publications describing chemical structures has increased steadily over the last decades. However, the majority of published chemical information is currently not available in machine-readable form in public databases. It remains a challenge to automate the process of information extraction in a way that requires less manual intervention - especially the mining of chemical structure depictions. As an open-source platform that leverages recent advancements in deep learning, computer vision, and natural language processing, DECIMER.ai (Deep lEarning for Chemical IMagE Recognition) strives to automatically segment, classify, and translate chemical structure depictions from the printed literature. The segmentation and classification tools are the only openly available packages of their kind, and the optical chemical structure recognition (OCSR) core application yields outstanding performance on all benchmark datasets. The source code, the trained models and the datasets developed in this work have been published under permissive licences. An instance of the DECIMER web application is available at https://decimer.ai.
Die neue Aufgabe der internen Kommunikation: schwierige Unternehmenspersönlichkeiten erkennen
(2023)
Measurement studies are essential for research and industry alike to understand the Web’s inner workings better and help quantify specific phenomena. Performing such studies is demanding due to the dynamic nature and size of the Web. An experiment’s careful design and setup are complex, and many factors might affect the results. However, while several works have independently observed differences in
the outcome of an experiment (e.g., the number of observed trackers) based on the measurement setup, it is unclear what causes such deviations. This work investigates the reasons for these differences by visiting 1.7M webpages with five different measurement setups. Based on this, we build ‘dependency trees’ for each page and cross-compare the nodes in the trees. The results show that the measured trees differ considerably, that the cause of differences can be attributed to specific nodes, and that even identical measurement setups can produce different results.
This paper reveals various approaches undertaken over more than two decades of teaching undergraduate programming classes at different Higher Education Institutions, in order to improve student activation and participation in class and consequently teaching and learning effectiveness.
While new technologies and the ubiquity of smartphones and internet access has brought new tools to the classroom and opened new didactic approaches, lessons learned from this personal long-term study show that neither technology itself nor any single new and often hyped didactic approach ensured sustained improvement of student activation. Rather it needs an integrated yet open approach towards a participative learning space supported but not created by new tools, technology and innovative teaching methods.
This paper presents a pragmatic approach for stepwise introduction of peer assessment elements in undergraduate programming classes, discusses some lessons learned so far and directions for further work. Students are invited to challenge their peers with their own programming exercises to be submitted through Moodle and evaluated by other students according to a predefined rubric and supervised by teaching assistants. Preliminary results show an increased activation and motivation of students leading to a better performance in the final programming exams.
In this work a mathematical approach to calculate solar panel temperature based on measured irradiance, temperature and wind speed is applied. With the calculated module temperature, the electrical solar module characteristics is determined. A program developed in MatLab App Designer allows to import measurement data from a weather station and calculates the module temperature based on the mathematical NOCT and stationary approach with a time step between the measurements of 5 minutes. Three commercially available solar panels with different cell and interconnection technologies are used for the verification of the established models. The results show a strong correlation between the measured and by the stationary model predicted module temperature with a coefficient of determination R2 close to 1 and a root mean square deviation (RMSE) of ≤ 2.5 K for a time period of three months. Based on the predicted temperature, measured irradiance in module plane and specific module information the program models the electrical data as time series in 5-minute steps. Predicted to measured power for a time period of three months shows a linear correlation with an R2 of 0.99 and a mean absolute error (MAE) of 3.5, 2.7 and 4.8 for module ID 1, 2 and 3. The calculated energy (exemplarily for module ID 2) based on the measured, calculated by the NOCT and stationary model for this time period is 118.4 kWh, resp. 116.7 kWh and 117.8 kWh. This is equivalent to an uncertainty of 1.4% for the NOCT and 0.5% for the stationary model.
n-type silicon modules
(2023)
The photovoltaic industry is facing an exponential growth in the recent years fostered by a dramatic decrease in installation prices. This cost reduction is achieved by means of several mechanisms. First, because of the optimization of the design and installation process of current PV projects, and second, by the optimization, in terms of performance, in the manufacturing techniques and material combinations within the modules, which also has an impact on both, the installation process, and the levelized cost of electricity (LCOE).
One popular trend is to increase the power delivered by photovoltaic modules, either by using larger wafer sizes or by combining more cells within the module unit. This solution means a significant increase in the size of these devices, but it implies an optimization in the design of photovoltaic plants. This results in an installation cost reduction which turns into a decrease in the LCOE.
However, this solution does not represent a breakthrough in addressing the real challenge of the technology which affects the module requirements. The innovation efforts must be focused on improving the modules capability to produce energy without enlarging the harvesting area. This challenge can be faced by approaching some of the module characteristics which are summarized in this chapter.