Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters
4 1
Reset filters

Settings
Now showing 1 - 5 of 5
  • Publication
    Synthetic data generation for the continuous development and testing of autonomous construction machinery
    ( 2023)
    Schuster, Alexander
    ;
    Hagmanns, Raphael
    ;
    Sonji, Iman
    ;
    Löcklin, Andreas
    ;
    Petereit, Janko
    ;
    Ebert, Christof
    ;
    Weyrich, Michael
    The development and testing of autonomous systems require sufficient meaningful data. However, generating suitable scenario data is a challenging task. In particular, it raises the question of how to narrow down what kind of data should be considered meaningful. Autonomous systems are characterized by their ability to cope with uncertain situations, i.e. complex and unknown environmental conditions. Due to this openness, the definition of training and test scenarios cannot be easily specified. Not all relevant influences can be sufficiently specified with requirements in advance, especially for unknown scenarios and corner cases, and therefore the "right" data, balancing quality and efficiency, is hard to generate. This article discusses the challenges of automated generation of 3D scenario data. We present a training and testing loop that provides a way to generate synthetic camera and Lidar data using 3D simulated environments. Those can be automatically varied and modified to support a closed-loop system for deriving and generating datasets that can be used for continuous development and testing of autonomous systems.
  • Publication
    Explainable AI: Introducing trust and comprehensibility to AI engineering
    ( 2022)
    Burkart, Nadia
    ;
    Danilo Brajovic
    ;
    Huber, Marco F.
    Machine learning (ML) rapidly gains increasing interest due to the continuous improvements in performance. ML is used in many different applications to support human users. The representational power of ML models allows solving difficult tasks, while making them impossible to be understood by humans. This provides room for possible errors and limits the full potential of ML, as it cannot be applied in critical environments. In this paper, we propose employing Explainable AI (xAI) for both model and data set refinement, in order to introduce trust and comprehensibility. Model refinement utilizes xAI for providing insights to inner workings of an ML model, for identifying limitations and for deriving potential improvements. Similarly, xAI is used in data set refinement to detect and resolve problems of the training data.
  • Publication
    ROBDEKON - competence center for decontamination robotics
    ( 2022)
    Woock, Philipp
    ;
    Petereit, Janko
    ;
    Frey, Christian
    ;
    Beyerer, Jürgen
    There are still many hazardous tasks that humans perform in their daily work. This is of great concern for the remediation of contaminated sites, for the dismantling of nuclear power plants, or for the handling of hazardous materials. The competence center ROBDEKON was founded to concentrate expertise and coordinate research activities regarding decontamination robotics in Germany. It serves as a national technology hub for the decontamination needs of various stakeholders. A major scientific goal of ROBDEKON is the development of (semi-)autonomous robotic systems to remove humans from work environments that are potentially hazardous to health.
  • Publication
    PAISE® - process model for AI systems engineering
    ( 2022)
    Hasterok, Constanze
    ;
    Stompe, Janina
    The application of artificial-intelligence-(AI)-based methods within the context of complex systems poses new challenges within the product life cycle. The process model for AI systems engineering, PAISE®, addresses these challenges by combining approaches from the disciplines of systems engineering, software development and data science. The general approach builds on a component-wise development of the overall system including an AI component. This allows domain specific development processes to be parallelized. At the same time, component dependencies are tested within interdisciplinary checkpoints, thus resulting in a refinement of component specifications.
  • Publication
    Optimal multispectral sensor confgurations through machine learning for cognitive agriculture
    ( 2021)
    Becker, Florian
    ;
    Backhaus, Andreas
    ;
    Johrden, Felix
    ;
    Flitter, Merle
    Hyperspectral sensor systems play a key role in the automation of work processes in the farming industry. Non-invasive measurements of plants allow for an assessment of the vitality and health state and can also be used to classify weeds or infected parts of a plant. However, one major downside of hyperspectral cameras is that they are not very cost-effective. In this paper, we show, that for specific tasks, multispectral systems with only a fraction of the wavelength bands and costs of a hyperspectral system can lead to promising results for regression and classification tasks. We conclude that for the ongoing automation efforts in the context of cognitive agriculture reduced multispectral systems are a viable alternative.