Deep learning has transformed computer vision for precision agriculture, yet apple orchard monitoring remains limited by dataset constraints. The lack of diverse, realistic datasets and the difficulty of annotating dense, heterogeneous scenes. Existing datasets overlook different growth stages and stereo imagery, both essential for realistic 3D modeling of orchards and tasks like fruit localization, yield estimation, and structural analysis. To address these gaps, we present AppleGrowthVision, a large-scale dataset comprising two subsets. The first includes 9,317 high resolution stereo images collected from a farm in Brandenburg (Germany), covering six agriculturally validated growth stages over a full growth cycle. The second subset consists of 1,125 densely annotated images from the same farm in Brandenburg and one in Pillnitz (Germany), containing a total of 31,084 apple labels. AppleGrowthVision provides stereo-image data with agriculturally validated growth stages, enabling precise phenological analysis and 3D reconstructions. Extending MinneApple with our data improves YOLOv8 performance by 7.69 % in terms of F1-score, while adding it to MinneApple and MAD boosts Faster R-CNN F1-score by 31.06 %. Additionally, six BBCH stages were predicted with over 95 % accuracy using VGG16, ResNet152, DenseNet201, and MobileNetv2. AppleGrowthVision bridges the gap between agricultural science and computer vision, by enabling the development of robust models for fruit detection, growth modeling, and 3D analysis in precision agriculture. Future work includes improving annotation, enhancing 3D reconstruction, and extending multimodal analysis across all growth stages.

F\"ur eine fr\"uhzeitige Erkennung von Lieferengp\"assen m\"ussen Lieferketten in einer geeigneten digitalen Form vorliegen, damit sie verarbeitet werden k\"onnen. Der f\"ur die Datenmodellierung ben\"otigte Arbeitsaufwand ist jedoch, gerade IT-fremden Personen, nicht zuzumuten. Es wurde deshalb im Rahmen dieser Arbeit eine Webanwendung entwickelt, welche die zugrunde liegende Komplexit\"at f\"ur den Benutzer verschleiern soll. Konkret handelt es sich dabei um eine grafische Benutzeroberfl\"ache, auf welcher Templates instanziiert und miteinander verkn\"upft werden k\"onnen. F\"ur die Definition dieser Templates wurden in dieser Arbeit geeignete Konzepte erarbeitet und erweitert. Zur Erhebung der Benutzerfreundlichkeit der Webanwendung wurde abschlie{\ss}end eine Nutzerstudie mit mehreren Testpersonen durchgef\"uhrt. Diese legte eine Vielzahl von n\"utzlichen Verbesserungsvorschl\"agen offen. -- For early detection of supply bottlenecks, supply chains must be available in a suitable digital form so that they can be processed. However, the amount of work required for data modeling cannot be expected of people who are not familiar with IT topics. Therefore, a web application was developed in the context of this thesis, which is supposed to disguise the underlying complexity for the user. Specifically, this is a graphical user interface on which templates can be instantiated and linked to each other. Suitable concepts for the definition of these templates were developed and extended in this thesis. Finally, a user study with several test persons was conducted to determine the usability of the web application. This revealed a large number of useful suggestions for improvement.

Conversational question answering (ConvQA) is a convenient means of searching over RDF knowledge graphs (KGs), where a prevalent approach is to translate natural language questions to SPARQL queries. However, SPARQL has certain shortcomings: (i) it is brittle for complex intents and conversational questions, and (ii) it is not suitable for more abstract needs. Instead, we propose a novel two-pronged system where we fuse: (i) SQL-query results over a database automatically derived from the KG, and (ii) text-search results over verbalizations of KG facts. Our pipeline supports iterative retrieval: when the results of any branch are found to be unsatisfactory, the system can automatically opt for further rounds. We put everything together in a retrieval augmented generation (RAG) setup, where an LLM generates a coherent response from accumulated search results. We demonstrate the superiority of our proposed system over several baselines on a knowledge graph of BMW automobiles.

Since the advent of Deepfakes in digital media, the development of robust and reliable detection mechanism is urgently called for. In this study, we explore a novel approach to Deepfake detection by utilizing electroencephalography (EEG) measured from the neural processing of a human participant who viewed and categorized Deepfake stimuli from the FaceForensics++ datset. These measurements serve as input features to a binary support vector classifier, trained to discriminate between real and manipulated facial images. We examine whether EEG data can inform Deepfake detection and also if it can provide a generalized representation capable of identifying Deepfakes beyond the training domain. Our preliminary results indicate that human neural processing signals can be successfully integrated into Deepfake detection frameworks and hint at the potential for a generalized neural representation of artifacts in computer generated faces. Moreover, our study provides next steps towards the understanding of how digital realism is embedded in the human cognitive system, possibly enabling the development of more realistic digital avatars in the future.

Since OpenAI's release of ChatGPT, generative AI has received significant attention across various domains. These AI-based chat systems have the potential to enhance the productivity of knowledge workers in diverse tasks. However, the use of free public services poses a risk of data leakage, as service providers may exploit user input for additional training and optimization without clear boundaries. Even subscription-based alternatives sometimes lack transparency in handling user data. To address these concerns and enable Fraunhofer staff to leverage this technology while ensuring confidentiality, we have designed and developed a customized chat AI called FhGenie (genie being a reference to a helpful spirit). Within few days of its release, thousands of Fraunhofer employees started using this service. As pioneers in implementing such a system, many other organizations have followed suit. Our solution builds upon commercial large language models (LLMs), which we have carefully integrated into our system to meet our specific requirements and compliance constraints, including confidentiality and GDPR. In this paper, we share detailed insights into the architectural considerations, design, implementation, and subsequent updates of FhGenie. Additionally, we discuss challenges, observations, and the core lessons learned from its productive usage.

Differential GPS, commonly referred as DGPS, is a well-known and very accurate localization system for many outdoor applications in particular for mobile outdoor robotics. The most common drawback of DGPS systems are the high costs for both base station and receivers. In this paper, we present a setup that uses third-party open-source software and a Ublox ZED-F9P chip to build a ROS-enabled low-cost DGPS setup that is ready to use in a few hours. The main goal of this paper is to analyze and evaluate the repetitive and absolute accuracy of the system. The first measurement also examines the differences between a SAPOS base station and a locally installed one consisting of low-cost components. During the evaluation process of the absolute accuracy, a moving mobile robot is used on the receiver side. It is tracked through a highly accurate VICON motion capture system.

Fraunhofer developed O3dyn to explore new concepts of AMR motion and dynamics for logistics operations. The Fraunhofer Institute in Germany conducts practical research in a number of important fields, including AI, cybersecurity, and medicine. One of its 76 research institutes, the Fraunhofer IML group, seeks to advance robotics and logistics. The researchers are testing the simulation capabilities of NVIDIA Isaac Sim to potentially enhance the design of robots. Its most recent mobile robot development, O3dyn, uses technologies developed by NVIDIA for simulation and robotics to produce an indoor-outdoor autonomous mobile robot (AMR).

Research in the field of machine learning and AI, now a key technology in practically every industry and company, is far too voluminous for anyone to read it all. This column aims to collect some of the most relevant recent discoveries and papers -- particularly in, but not limited to, artificial intelligence -- and explain why they matter. This week AI applications have been found in several unexpected niches due to its ability to sort through large amounts of data, or alternatively make sensible predictions based on limited evidence. We've seen machine learning models taking on big data sets in biotech and finance, but researchers at ETH Zurich and LMU Munich are applying similar techniques to the data generated by international development aid projects such as disaster relief and housing. The team trained its model on millions of projects (amounting to $2.8 trillion in funding) from the last 20 years, an enormous dataset that is too complex to be manually analyzed in detail.

The United Nations Agencies are tackling natural disaster management using artificial intelligence (AI) with a new 2021 Focus Group on AI for Natural Disaster Management (FG-AI4NDM). The ITU focuses on information and communications technologies (ICT) and their support of the United Nations 17 Sustainable Development Goals (SDGs). As noted by ITU, "facilitate international connectivity in communications networks, we allocate global radio spectrum and satellite orbits, develop the technical standards that ensure networks and technologies seamlessly interconnect, and strive to improve access to ICTs to underserved communities worldwide. Every time you make a phone call via the mobile, access the Internet or send an email, you are benefitting from the work of ITU." Relatable standards work would be in video compression (H26X series), phone area codes, performance standards in AI for healthcare, the phonetic alphabet used in radio communications, and the term "Internet of Things (IoT)" was originally coined by the ITU. As noted by WMO, "behaviour of the Earth's atmosphere, its interaction with the land and oceans, the weather and climate it produces, and the resulting distribution of water resources."

Sunny California seems to be the global pacemaker of major innovations in the IT and high–tech industries: The Internet giants Google, Facebook, Apple and Amazon, like many other tech companies, have their headquarters in Silicon Valley. The innovative start–up scene in the Bay Area is at the forefront of developments in artificial intelligence (AI) – closely followed by China. And where do we stand? How does the German economy manage to keep up in the race? Germany & Silicon Valley: Shaping a shared digital future" in Mountain View, leading voices from politics, business and science have conducted a global assessment of the current situation. We participated in the conference with the project "FutureWork360". The aim of the project is to use virtual reality to make our innovation laboratories accessible worldwide on an Internet platform and thereby promoting international networking. For three days, the Computer History Museum – not far from Google's headquarters – was transformed into a forum for the exchange of knowledge on AI. Leaders from the digital economy, research and politics came together to discuss how Germany and the Silicon Valley can work together to harness the tremendous opportunities of AI, robotics and other new digital technologies while effectively addressing the social, economic and political challenges they present. Because we are in the midst of a huge social upheaval – we are walking into a future in which AI–controlled machines think, make decisions and perform tasks, which we once thought were clearly "human". The USA is the breeding ground of digital talent among all countries with about 3000 PhD students per year in the field of AI (for comparison: in Germany there are about 170). Furthermore, five of the top ten and 134 of the 500 most powerful commercially available supercomputers are currently located in the US. The largest number of AI start–ups also gather there. Three–quarters of all internationally enforced AI patents were filed by US players, compared to only two percent from the German counterparts. The figures show how urgent it is for Europeans, and especially Germans, to catch up in the key technology of artificial intelligence. Christoph Keese, CEO of Axel Springer hy GmbH, summarizes the situation in his words: "We must finally wake up and stop investing so little in AI.