Repository der Technischen Hochschule Ingolstadt
Not a member yet
4170 research outputs found
Sort by
Artificial Intelligence in Knowledge Management: Overview and Selection of Software for Automotive Reporting
Get PDFKnowledge Management is essential for modern organizations, enabling the systematic capture, organization, and sharing of knowledge to enhance decision-making and innovation. Traditional Knowledge Management tools, focused on document storage and retrieval, struggle with unstructured data and collaboration, necessitating advanced technological solutions, particularly those incorporating Artificial Intelligence. - Artificial Intelligence-driven Knowledge Management systems revolutionize data handling through automation, and real-time insights. This is particularly valuable in data-intensive industries like automotive, finance, and healthcare. In the automotive sector, annual reports provide critical insights but are complex and time-consuming to analyze and are a complex example and therefore a good test case. Annual reports of 5 major automotive companies BMW, Volkswagen group, Toyota Motors, General Motors and Tesla were selected as the testing dataset. Artificial Intelligence tools, using natural language processing and machine learning, streamline data extraction. - Despite their benefits, organizations face challenges in selecting the right Artificial Intelligence-driven Knowledge Management software due to a lack of standardized evaluation frameworks. This research applies a systematic methodology for assessing such software, considering usability, adaptability, cost-effectiveness, and data privacy compliance, specifically tailored to automotive reporting and gives recommendation for software tools
What do you mean by ‘(un-)suitable’? Analysing the diversity of social acceptance towards the deployment of renewable energies in different landscapes
Get PDFLocal energy transitions are shaped by diverse stakeholder perspectives on land use, reflecting competing values, knowledge systems, and political views. This study applies the landscape services framework to systematically assess renewable energy (RE) suitability across different landscapes, capturing both ecological and socio-cultural dimensions. Through stakeholder surveys in two German regions and statistical comparative analysis, we reveal how suitability perceptions vary significantly: (1) between stakeholder groups (e.g. conservationists vs. developers), (2) across regions (industrial vs. ecological-cultural contexts), and (3) even within groups sharing similar objectives. Key findings show strong preference for RE development in industrial and agricultural zones (‘acceptance corridors’) and opposition in ecologically sensitive areas, though with notable regional exceptions. The landscape services approach proves effective in mapping these conflicts and consensus areas, providing actionable insights for spatially sensitive RE planning. Our results underscore the need to complement technical siting criteria with structured assessments of social landscape values to enable just and locally accepted energy transitions
A Systematic Literature Review on Vehicular Collaborative Perception – A Computer Vision Perspective
No full textTWICE Dataset: Digital Twin of Test Scenarios in a Controlled Environment
No full textEnsuring the safe and reliable operation of autonomous vehicles under adverse weather remains a significant challenge. To address this, we have developed a comprehensive dataset composed of sensor data acquired in a real test track and reproduced in the laboratory for the same test scenarios. The provided dataset includes camera, radar, LiDAR, inertial measurement unit (IMU), and GPS data recorded under adverse weather conditions (rainy, night-time, and snowy conditions). We recorded test scenarios using objects of interest such as car, cyclist, truck and pedestrian -- some of which are inspired by EURONCAP (European New Car Assessment Programme). The sensor data generated in the laboratory is acquired by the execution of simulation-based tests in hardware-in-the-loop environment with the digital twin of each real test scenario. The dataset contains more than 2 hours of recording, which totals more than 280GB of data. Therefore, it is a valuable resource for researchers in the field of autonomous vehicles to test and improve their algorithms in adverse weather conditions, as well as explore the simulation-to-reality gap
Simulation-Based Parameter Identification for Accuracy Definitions in Virtual Environment Models for Validation of Automated Driving
No full textAn Unsupervised Random Forest Clustering Technique for Automatic Traffic Scenario Categorization
No full text
