Fakultät IuI
Refine
Year of publication
Document Type
- Conference Proceeding (32) (remove)
Language
- English (32) (remove)
Is part of the Bibliography
- yes (32)
Keywords
- Gazebo (2)
- LiDAR (2)
- Power Consumption (2)
- Robot operating system (ROS) (2)
- Simulation and Modeling (2)
- biogas (2)
- mobile field laboratory (2)
- AI compliance (1)
- Agricultural Automation (1)
- Agricultural streering system (1)
Institute
- Fakultät IuI (32)
- Fakultät AuL (1)
- Institut für Management und Technik (1)
This article proposes the concept of a simulation framework for environmental sensors with multilevel abstraction in agricultural scenarios. The implementation case study is a simulation of a grain-harvesting scenario enabled by LiDAR sensors. Environmental sensor models as well as kinematics and dynamic behavior of machines are based on the robotics simulator Gazebo. Models for powertrain, machine process aggregates and peripheral simulation components are implemented with the help of MATLAB/ Simulink and with the robotics middleware Robot Operating System (ROS). This article deals with the general concept of a multilevel simulation framework and in particular with sensor and environmental modeling.
Artificial intelligence (AI) and human-machine interaction (HMI) are two keywords that usually do not fit embedded applications. Within the steps needed before applying AI to solve a specific task, HMI is usually missing during the AI architecture design and the training of an AI model. The human-in-the-loop concept is prevalent in all other steps of developing AI, from data analysis via data selection and cleaning to performance evaluation. During AI architecture design, HMI can immediately highlight unproductive layers of the architecture so that lightweight network architecture for embedded applications can be created easily. We show that by using this HMI, users can instantly distinguish which AI architecture should be trained and evaluated first since a high accuracy on the task could be expected. This approach reduces the resources needed for AI development by avoiding training and evaluating AI architectures with unproductive layers and leads to lightweight AI architectures. These resulting lightweight AI architectures will enable HMI while running the AI on an edge device. By enabling HMI during an AI uses inference, we will introduce the AI-in-the-loop concept that combines AI's and humans' strengths. In our AI-in-the-loop approach, the AI remains the working horse and primarily solves the task. If the AI is unsure whether its inference solves the task correctly, it asks the user to use an appropriate HMI. Consequently, AI will become available in many applications soon since HMI will make AI more reliable and explainable.
This paper presents an optimized algorithm for estimating static and dynamic gait parameters. We use a marker- and contact-less motion capture system that identifies 20 joints of a person walking along a corridor.
Based on the proposed gait cycle detection basic metrics as walking frequency, step/stride length, and support phases are estimated automatically. Applying a rigid body model, we are capable to calculate static and dynamic gait stability metrics. We conclude with initial results of a clinical study evaluating orthopaedic technical support.
Interpolation of data in smart city architectures is an eminent task for the provision of reliable services. Furthermore, it is a key functionality for information validation between spatiotemporally related sensors. Nevertheless, many existing projects use a simplified geospatial model that does not take the infrastructure, which affects events and effects in the real world, into account. There are various available algorithms for interpolation and the calculation of routes on infrastructure based graphs and distances on geospatial data. This work proposes a combined approach by interconnecting detailed geospatial data whilst regarding the underlying infrastructure model.
Knowledge of the small-scale nutrient status of a field is an important basis for decision-making when it comes to optimising the fertiliser use in crop production. Currently, the traditional method involves soil sampling in the field and soil sample analysis in the laboratory as two separate working processes.
The previous research project "soil2data" developed a mobile field laboratory for different carrier vehicles. In the follow-up project "prototypes4soil2data", the results of soil2data are further developed. A mixed soil sample is collected during the drive on the field. The soil sample is then wet-chemically prepared and analysed. The overall soil sampling and analysis process is divided into the following process steps: soil sampling planning, soil sampling, soil preparation, soil analysis and data management. The process steps are modified for the mobile field laboratory and the process steps run in parallel. The new soil extraction method is based on official German methods (VDLUFA) to ensure the interoperability of the analysis results with the VDLUFA fertiliser recommendations. An innovative key component is the NUTRISTAT analysis module (lab-on-chip with ISFET measurement technology). It can measure pH, the nutrients NO3-, H2PO4-, K+ and the electrical conductivity. In addition to the advantages of rapid data availability and no need to transport soil material to the laboratory, it provides a future basis for new application, e.g. verification of current results in the field during soil sampling with existing results or dynamic adjustment of soil sampling during work in the field.
he development of context-aware applications is a difficult and error-prone task. The dynamics of the environmental context combined with the complexity of the applications poses a vast number of possibilities for mistakes during the creation of new applications. Therefore it is important to test applications before they are deployed in a life system. For this reason, this paper proposes a testing tool, which will allow for automatic generation of various test cases from application description documents. Semantic annotations are used to create specific test data for context-aware applications. A test case reduction methodology based on test case diversity investigations ensures scalability of the proposed automated testing approach.
Smart city applications in the Big Data era require not only techniques dedicated to dynamicity handling, but also the ability to take into account contextual information, user preferences and requirements, and real-time events to provide optimal solutions and automatic configuration for the end user. In this paper, we present a specific functionality in the design and implementation of a declarative decision support component that exploits contextual information, user preferences and requirements to automatically provide optimal configurations of smart city applications. The key property of user-centricity of our approach is achieved by enabling users to declaratively specify constraints and preferences on the solutions provided by the smart city application through the Decision Support component, and automatically map these constraints and preferences to provide optimal responses targeting user needs. We showcase the effectiveness and flexibility of our solution in two real usecase scenarios: a multimodal travel planner and a mobile parking application. All the components and algorithms described in this paper have been defined and implemented as part of the Smart City Framework CityPulse.
Bamboo is an environmentally friendly alternative to conventional materials in mechanical engineering such as steel or aluminium. Bamboo is the fastest growing plant in the world. Instead of releasing CO2 during the manufacturing process, bamboo absorbs CO2 as it grows.
In addition to the sustainability aspect, bamboo tubes also offer excellent properties as a lightweight construction material, which have been optimised through evolution. Bamboo tubes have high strength and stiffness at low weight when used as tension-compression bars or bending beams. Bamboo has strong, high-density fibres at the boundary area, where bending stresses are greatest. Towards the inside, where the stresses are lower, the bamboo becomes porous to optimise weight. This, together with knots arranged in regular intervals, counteracts buckling.
In mobile applications such as cars and bicycles, lightweight construction is sought for energy efficiency reasons. Because of its excellent lightweight properties, the project investigated whether bamboo could be used in mobile, automotive or agricultural engineering. For example, a bamboo bicycle frame has been developed with the aim to be as light as possible. There are bamboo bicycles on the market, but they can only be made one at a time by hand. The bamboo tubes are joined together and functional elements such as the bottom bracket and headset are integrated by wrapping them in resin-impregnated natural or carbon fibres. This makes the joints very heavy. A different approach is taken here: the bamboo tubes are drilled out slightly to achieve a defined internal diameter, and then short aluminium tubes are glued into the bamboo canes from the inside. To prevent the cane from breaking in the circumferential direction, i.e. perpendicular to the fibre direction, the bamboo tubes are wrapped in a thin layer of natural or carbon fibre impregnated with synthetic resin. The aluminium tubes and functional elements are welded or soldered together beforehand.
The design of the bicycle frame, i.e. the dimensioning of the bamboo tubes and joints, was based on extensive bending and tensile tests to determine the strength properties of the natural material bamboo. The bonding between the bamboo cane and the aluminium tube was also investigated experimentally. Finally, several prototype bicycle frames were made and tested for durability according to DIN-EN-14764. The frames passed the tests.
The result is a bamboo bicycle that is manufactured with standardised connectors and joints. The assembly concept developed allows both fully automated and semi-automated series production of bamboo bicycles.
Compliance of agricultural AI systems – app-based legal verification throughout the development
(2024)
Significant advances in artificial intelligence (AI) have been achieved; however, practical implementation in agriculture remains limited. Compliance with emerging regulations, such as the EU AI Act and GDPR, is now vital, even for non-critical AI systems. Developers need tools to assess legal compliance, which is complex, often requiring full legal advice. To address this issue, we are developing a support app that simplifies the legal aspects of AI system development, covering the entire lifecycle, from conception to distribution. The current app, which covers the key legal area of copyright and will soon include GDPR and the AI Act, aims to bridge the gap between AI research and agriculture. An evaluation of our app by experts from both the legal and the IT domains shows that the app assists the developers so that they make legally correct statements. Consequently, it promotes legal compliance and awareness among developers, contributing to the seamless integration of AI into agriculture. The need for compliant AI systems in various industries, including agriculture, will only increase as regulations evolve.
For Delay-Tolerant Networks (DTNs) many routing algorithms have been suggested. However, their performance depends heavily on the applied scenario. Especially heterogeneous scenarios featuring known and unknown node movements as well as different kinds of data lead to either poor delivery ratios or exhausted network resources.
To overcome these problems this paper introduces Data-Driven Routing for DTNs. Data is categorized according to its requirements into priority queues. Each queue applies an appropriate DTN routing algorithm that fits the data requirements best. Simulation results show that Data-Driven Routing allows high delivery ratios for time-critical data while saving network resources during the transfer of less time-critical data at the same time.