Publication Server of Kempten University
Not a member yet
2351 research outputs found
Sort by
Mehr Raum! Neue Impulse der vierten Dimension
No full textWissenschaftliche Reflexion über die Bedeutung des Raums für die offene Kinder- und Jugendarbeit. Im Vortrag werden aktuelle theoretische Diskussionsstränge mit Ergebnissen empirischer Forschung verbunden und zu praktischen Handlungsimpulsen verarbeitet
Alle Zeit der Welt oder permanente Rushhour? Reflexionen zur Bedeutung der Zeit im Tourismuskontext
No full textFragen zum Themenkreis Transformation sind angesichts aktueller wie drohender Krisen in aller Munde. Dies gilt besonders, wenn auch bei weitem nicht ausschließlich, für den Tourismus, da dieser Veränderungen bekanntermaßen zeitgleich sowohl verursacht als auch von ihnen beeinflusst wird. Entsprechend eindringlich wird nach Konzepten gesucht, die einen Umgang mit sich wandelnden Rahmenbedingungen (u. a. Klimawandel, gesellschaftlicher Umbruch, politische Konflikte) erlauben. Zur Beantwortung sind dabei alle Disziplinen aufgefordert, so auch die Philosophie, die sich typischerweise mit den sogenannten ersten Fragen, also den Ursprüngen, Voraussetzungen und grundsätzlichen Annahmen von Sachverhalten beschäftigt (vgl. König 2013). Als Voraussetzung der Teilhabe am Tourismus wird schon seit langem eine Dualität von Verfügbarkeiten erfasst: Menschen benötigen frei verfügbares Geld sowie frei verfügbare Zeit, um touristisch aktiv sein zu können. Der Schwerpunkt des vorliegenden Beitrags soll auf letzterem liegen: Es soll darum gehen die Bedeutung der Zeit im Tourismuskontext zu erfassen, um zu eruieren, ob sie etwaige Hebel zur Transformation bereithält. Denn schließlich ist Zeit „[…] auf jeden Fall eine fundamentale Dimension in der wir leben.“ (Sieroka 2016
LiDAR Sensor Parameter Augmentation and Data-Driven Influence Analysis on Deep-Learning-Based People Detection
No full textLight detection and ranging (LiDAR) sensor technology for people detection
offers a significant advantage in data protection. However, to design these systems cost and energy-efficiently, the relationship between the measurement data and final object detection output with deep neural networks (DNNs) has to be elaborated. Therefore, this paper presents augmentation methods to analyze the influence of the distance, resolution,
noise, and shading parameters of a LiDAR sensor in real point clouds for people detection. Furthermore, their influence on object detection using DNNs was investigated. A significant reduction in the quality requirements for the point clouds was possible for the measurement setup with only minor degradation on the object list level. The DNNs PointVoxel-Regionbased Convolutional Neural Network (PV-RCNN) and Sparsely Embedded Convolutional Detection (SECOND) both only show a reduction in object detection of less than 5% with a reduced resolution of up to 32 factors, for an increase in distance of 4 factors, and with a Gaussian noise up to µ = 0 and σ = 0.07. In addition, both networks require an unshaded height of approx. 0.5 m from a detected person’s head downwards to ensure good people detection performance without special training for these cases. The results obtained, such as shadowing information, are transferred to a software program to determine the minimum number of sensors and their orientation based on the mounting height of the sensor, the sensor parameters, and the ground area under consideration, both for detection at the point cloud level and object detection level
Autonomy in Agriculture - unlocking the automation potential of agricultural engineering -
No full textThe agricultural sector is undergoing a profound transformation driven by technological innovation, demographic shifts, and growing sustainability demands. As labor shortages and economic pressures intensify, the implementation of high levels of automation in agricultural machinery is evolving from a visionary concept to an urgent necessity. Currently the automation in agricultural engineering builds upon well-established technologies such as satellite-based guidance systems, variable rate control (VRC), and section control. These solutions form the backbone of modern precision farming and provide a stable foundation for advancing toward higher levels of autonomy.
Autonomy in Agriculture is not limited to, but includes autonomous navigation, real-time object detection for enhanced safety, and collaborative multi-machine operations. While such capabilities are widely explored in on-road contexts, their adaptation to agricultural environments requires addressing unique challenges – including unstructured terrain, environmental variability, and multifaceted task requirements. Key concepts like Operational Design Domains (ODD), originally developed in the automotive sector, are target for being reinterpreted for off-road use. Standardization efforts, including the adoption of tools and protocols from the automotive domain, play a critical role in ensuring reliable development and testing of autonomous systems tailored to agricultural applications.
This context highlights the importance of sector-wide collaboration. Industry groups, academic institutions, and international associations such as VDMA, CEMA, and ISO committees are jointly working to define technical standards, safety protocols, and validation strategies. A particular challenge remains in the fragmentation of requirements due to bilateral negotiations between sensor providers and OEMs. Harmonizing processes, methods, and metrics promises to streamline development, reduce redundancy, and support scalable, reliable solutions across industries.
This contribution aims to provide an integrated overview of current developments, cross-sector initiatives, and future directions for automation in agriculture. It serves as an invitation to interdisciplinary exchange and collaboration
Individual driver emission reduction due to electric vehicle-based residential load shifting: Insights from Germany
No full textCommuters require measures tailored to their individual behavior to reduce emissions associated with their residential electricity demand. This paper investigates the operation of a spatiotemporal residential load-shifting concept where Electric Vehicles (EVs) charge low-emission electricity from the grid at the workplace (rather than at a commuter's residence), function as mobile energy storage device, and cover residential electricity demand through battery discharging. The success of this strategy in reducing emissions hinges on aligning electricity demand with the country- and time-specific emissions associated with grid electricity constrained by individual behavioral habits. In this paper, we analyze why and how much seasons and driver behavior (in terms of both the commuter's driving and residential electricity demand behavior) change the emission reduction impact of EV-based residential load shifting. We contribute to the literature by explaining the changes in emission reduction and validating previous results with German conditions using real-world behavioral and grid data. While winter yields a −0.3 % median emission reduction, summer offers a promising median potential of 24 % and a maximum of 42 %. Commuters with a daily driving distance above 110 km who arrive home after 08:00 p.m. stand out, as they reduce emissions by more than 10 % above the average. These insights contextualize optimistic assessments of EV-based residential load shifting, indicating that the individual impact for Germany-like conditions is rather small
Efficient Federated Learning Integration into Existing MLOps Pipelines via Centralized Model Management
No full textFederated Learning (FL) offers a solution to the challenges of traditional centralized machine learning by enabling decentralized training and exchanging only model updates instead of raw data. This approach addresses key issues such as privacy concerns and high data transfer costs. However, integrating FL into existing Machine Learning Operations (MLOps) pipelines presents challenges, particularly regarding model versioning, synchronization, and scalability. This paper introduces a concept for centralized model management that enables the integration of FL into existing MLOps pipelines without the need to overhaul the existing architecture. The concept is specifically developed for deployment in an industrial setting, with plans for implementing both FL and Transfer Learning (TL) in the future. The proposed approach emphasizes flexibility, ensuring that it can be easily extended to accommodate additional methods and seamlessly integrated into diverse, pre-existing infrastructure. The management of the system is facilitated using the open-source tool MLflow, which offers significant advantages over specialized FL frameworks, particularly in terms of adaptability and resource optimization
Cyber-physical-human systems for mobile robots in energy asset management: Current practices and future opportunities
No full textRapid advancement of digital technologies has resulted in an acceleration of cyber–physical systems for autonomous mobile robots to improve energy asset management activities within inspection, maintenance and repair. Within this systems-based approach, the role of the human-in-the-loop has also increased leading to cyber–physical-human systems requiring real-time interaction of robotics and digital twins with a human operator. Subject to existing network systems and physical systems, cyber–physical-human systems face enormous challenges requiring further investigation. This review presents the state-of-the-art in discovery, design, development and deployment of cyber–physical-human systems for mobile robots in energy asset management. To address dominant concepts and misconceptions in this area, key terminologies, system concepts and applications are presented. Then a state-of-the-art review with associated trends for several applications within academic and industrial sectors is presented where current practises and limitations are then discussed. Finally, future opportunities are explored alongside highlighted concepts providing a pathway for rapid adoption and improved key performance indicators of mobile fleets for facility operators and those in the wider community
Integrated measurement of tool wear in punching processes using a pneumatic gauging system
No full textPunching is an essential production process for manufacturing large volumes of uniform, cost-effective parts. Despite its widespread use, the efficiency and quality of this process are highly sensitive to numerous parameters, many of which are not fully understood. Achieving optimal, reproducible, and transparent process control, it is crucial to have a detailed understanding of the wear condition of the punching tool. Currently, direct methods for measuring tool wear are unavailable, leading to reliance on indirect measurements through physical surrogate variables. These techniques predominantly focus on indirectly monitoring the quality of the punched parts after processing. In this study, we developed an innovative pneumatic gauging system capable of periodically measuring punch wear directly. We demonstrate the feasibility of integrating a measurement nozzle into the cutting tool, which enables direct assessment of the cutting edge wear. Additionally, we have developed a dedicated measuring transducer and conducted a comparative analysis against an industrial standard. Our methodology includes a comprehensive calibration process within the punching operation. To validate our approach, we performed a series of tests and cross-validation to demonstrate that tool wear degradation can be effectively measured. We explored the potential of this monitoring approach for predicting tool wear. Our findings indicate that real-time measurement of the punch’s cutting edge wear in punching and blanking operations is achievable, which paves the way for advancements in process control and maintenance
Multi-objective Reinforcement Learning for Energy-Efficient Industrial Control
No full textIndustrial automation increasingly demands energy-efficient control strategies to balance performance with environmental and cost constraints. In this work, we present a multi-objective reinforcement learning (MORL) framework for energy-efficient control of the Quanser Aero 2 testbed in its one-degree-of-freedom configuration. We design a composite reward function that simultaneously penalizes tracking error and electrical power consumption.
Preliminary experiments explore the influence of varying the energy penalty weight, , on the trade-off between pitch tracking and energy savings. Our results reveal a marked performance shift for values between 0.0 and 0.25, with non-Pareto optimal solutions emerging at lower values, on both the simulation and the real system. We hypothesize that these effects may be attributed to artifacts introduced by the adaptive behavior of the Adam optimizer, which could bias the learning process and favor bang-bang control strategies. Future work will focus on automating selection through Gaussian Process-based Pareto front modeling and transitioning the approach from simulation to real-world deployment
Meeting- & EventBarometer Bayern 2024/2025
No full textUm mehr über Bayern als MICE-Destination zu erfahren, hat das Bayerische Zentrum für Tourismus im Jahr 2025 eine Studie des Meeting- & EventBarometers zum MICE-Markt in Bayern in Auftrag gegeben. Bezogen auf das Geschäftsjahr 2024 wurden Anbieter von Veranstaltungsstätten in Bayern und Deutschland sowie deutsche und internationale Veranstalter aus ausgewählten Quellmärkten befragt. Die Studie liefert neben den Kennzahlen zur Nachfrage in Bezug auf Veranstaltungen in Bayern und deren Teilnehmenden sowie dem bayerischen Angebot im MICE-Segment auch Einblicke in die zukünftige Entwicklung des Marktes sowie Trend- und Fokusthemen der Veranstaltungsbranche