Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters
Reset filters

Settings
Now showing 1 - 10 of 72
No Thumbnail Available
Publication

DecaWave ultra-wideband warm-up error correction

2021 , Sidorenko, Juri , Schatz, Volker , Scherer-Negenborn, Norbert , Arens, Michael , Hugentobler, Urs

In the field of indoor localization, ultra-wideband (UWB) technology is no longer dispensable. The market demands that the UWB hardware has to be cheap, precise and accurate. These requirements lead to the popularity of the DecaWave UWB system. The great majority of the publications about this system deals with the correction of the signal power, hardware delay or clock drift. It has traditionally been assumed that this error only appears at the beginning of the operation and is caused by the warm-up process of the crystal. In this article, we show that the warm-up error is influenced by the same error source as the signal power. To our knowledge, no scientific publication has explicitly examined the warm-up error before. This work aims to close this gap and, moreover, to present a solution which does not require any external measuring equipment and only has to be carried out once. It is shown that the empirically obtained warm-up correction curve increases the accuracy for the twoway- ranging (TWR) significantly.

View
No Thumbnail Available
Publication

Modular and scalable automation for field robots. Lighthouse project "cognitive agriculture"

2020 , Osten, Julia , Weyers, Catrin , Petereit, Janko

Agricultural technology is under pressure due to unsolved farm successions, labour shortage and climate protection goals. Precision farming and smart farming are expected to have a high impact on sustainability on a long time scale. The Fraunhofer lighthouse project ""Cognitive Agriculture"" (COGNAC) is working on increasing the efficiency and sustainability of agricultural processes by developing a living digital ecosystem called Agriculture Data Space. A short introduction to parts of the ecosystem such as the ADS-enabling platform and the automated charging field robots are presented.

View
No Thumbnail Available
Publication

Informed Machine Learning - A Taxonomy and Survey of Integrating Knowledge into Learning Systems

2019-03-29 , Rüden, Laura von , Mayer, Sebastian , Beckh, Katharina , Georgiev, Bogdan , Giesselbach, Sven , Heese, Raoul , Kirsch, Birgit , Pfrommer, Julius , Pick, Annika , Ramamurthy, Rajkumar , Schuecker, Jannis , Garcke, Jochen , Bauckhage, Christian , Walczak, Michal

Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process, which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. First, we provide a definition and propose a concept for informed machine learning, which illustrates its building blocks and distinguishes it from conventional machine learning. Second, we introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Third, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.

View
No Thumbnail Available
Publication

Editorial

2019 , Müller-Quade, J. , Beyerer, J. , Broadnax, B.

View
No Thumbnail Available
Publication

Tiefe neuronale Netze

2021 , Bauckhage, Christian , Hübner, Wolfgang , Hug, Ronny , Paaß, Gerhard

View
No Thumbnail Available
Publication

Smart Services in the Physical World: Digital Twins

2020 , Stojanovic, Ljiljana , Bader, Sebastian R.

Comprehensive, independently operating digital representations of physical assets, provisioned and manipulated through standardized interaction patterns, dissolve between the tangible and virtual world. Real-world developments are reflected in digital models and vice versa. The concept of digital twins combines these facets to integrated entities, specifying the description, appearance, and behavior of real-world entities in virtual models. This chapter explains how smart services enact as digital twins but also how they interact in flexible, loosely coupled networks.

View
No Thumbnail Available
Publication

Model-based routing in flexible manufacturing systems

2019 , Windmann, Stefan , Balzereit, Kaja , Niggemann, Oliver

In this paper, a model-based routing approach for flexible manufacturing systems (FMS) with alternative routes for the work pieces is proposed. For each work piece, an individual task has to be accomplished, which consists of several processing steps. Each processing step can be executed on alternative working stations of the FMS. The proposed routing method employs a model of the conveying system to find energy efficient and fast routes for the respective work pieces. The conveying system model is based on a directed graph, where the individual conveyors are modeled as weighted edges. It can be straightforwardly applied to several types of FMS by adjusting the application-dependent parameters. Efficient computation of the fastest route through the conveying system is accomplished by means of dynamic programming, i. e., by integration of Dijkstra's algorithm in a dynamic programming framework, which is based on the proposed conveying system model. Additional consideration of energy efficiency aspects leads to a Mixed Integer Quadratically Constraint Program (MIQCP), which is solved by substitution of Dijkstra's algorithm by a branch and bound method. Experimental results for an application scenario, where the energy efficient routing method is applied to route work pieces between the working stations of an FMS, lead to 20 % reduction of energy consumption on average.

View
No Thumbnail Available
Publication

Grundlagen des Maschinellen Lernens

2021 , Bauckhage, Christian , Hübner, Wolfgang , Hug, Ronny , Paaß, Gerhard , Rüping, Stefan

Zu definieren, was die menschliche Intelligenz sowie intelligentes Handeln – und da­mit auch die Künstliche Intelligenz – ausmacht, ist außerordentlich schwer und be­schäftigt Philosophen und Psychologen seit Jahrtausenden. Allgemein anerkannt istaber, dass die Fähigkeit zu lernen ein zentrales Merkmal vonIntelligenzist. So ist auchdas Forschungsgebiet desMaschinellen Lernens(engl.machine learning, ML) ein zen­traler Teil der Künstlichen Intelligenz, das hinter vielen aktuellen Erfolgen von KI-Sys­temen steckt.

View
No Thumbnail Available
Publication

Deutsche Normungsroadmap Künstliche Intelligenz

2020 , Adler, R. , Kolomiichuk, Sergii , Hecker, Dirk , Lämmel, Philipp , Ma, Jackie , Marko, Angelina , Mock, Michael , Nagel, Tobias , Poretschkin, Maximilian , Rennoch, Axel , Röhler, Marcus , Ruf, Miriam , Schönhof, Raoul , Schneider, Martin A. , Tcholtchev, Nikolay , Ziehn, Jens , Böttinger, Konstantin , Jedlitschka, Andreas , Oala, Luis , Sperl, Philip , Wenzel, Markus , et al.

Die deutsche Normungsroadmap Künstliche Intelligenz (KI) verfolgt das Ziel, für die Normung Handlungsempfehlungen rund um KI zu geben, denn sie gilt in Deutschland und Europa in fast allen Branchen als eine der Schlüsseltechnologien für künftige Wettbewerbsfähigkeit. Die EU geht davon aus, dass die Wirtschaft in den kommenden Jahren mit Hilfe von KI stark wachsen wird. Umso wichtiger sind die Empfehlungen der Normungsroadmap, die die deutsche Wirtschaft und Wissenschaft im internationalen KI-Wettbewerb stärken, innovationsfreundliche Bedingungen schaffen und Vertrauen in die Technologie aufbauen sollen.

View
No Thumbnail Available
Publication

Quality-of-Service monitoring of hybrid industrial communication networks

2019 , Ehrlich, Marco , Neumann, Arne , Biendarra, Alexander , Jasperneite, Jürgen

Today many hybrid (wired & wireless) industrial communication networks with a huge variety of heterogeneous technologies and protocols are present in the manufacturing and automation domain. The increasing requirements regarding e. g., latency, reliability, or determinism create the need for a holistic network management concept in order to assure a network-wide Quality-of-Service (QoS) resource provisioning and the assurance of the admissioned resources. Consequently, a monitoring of the whole network is required to feed the network management system with the needed information about the underlying network processes. Various technical approaches using different methods of extracting the information from network traffic are available for the purpose of QoS parameter observance and measurement at the moment. Therefore, this paper provides a state of the art research about network management and QoS provisioning respectively QoS assurance concepts. In addition, the passive network monitoring approach using the flow export technique based on the Internet Protocol Flow Information Export (IPFIX) is investigated for a utilisation in the nowadays industry domain based on a conceptual case study with a wireless protocol. As a conclusion, an evaluation is performed in order to clarify the limits and the overall usability of IPFIX for the monitoring of industrial networks in order to support future network management systems.

View