Nuremberg, Germany / June 21, 2022 - June 23, 2022
Fraunhofer at the embedded world
Hall 4 | booth 422 and 509
Hall 4 | booth 422 and 509
Self-Powered Wide-Area Network is a unique combination of the LPWAN standard mioty® with Energy Harvesting for massive IoT applications like smart city and Industrial Internet of Things (IIoT). The mioty® technology relies on telegram splitting dividing a compact telegram into multiple radio bursts, distributed over time and frequency. The energy harvesting technology makes use of smallest amounts of energy, like heat, light or vibration to power mioty® completely without cables or batteries.
Whether IoT or its industrial equivalent Industrial IOT - networked sensor technology is the supplier of the data. In this context, wireless sensor technology enables data acquisition at inaccessible measurement locations, with constantly changing measurement configurations, or simply when the effort required for a wired application is too great. Until now, the testing of such data required a high initialization effort until the first data arrived. Wireless sensor platforms offer users a quick start. From the integration of commercially available sensors to the web-based display and evaluation of data, the systems presented require only a few clicks. The platforms are tailored to the different needs of the users:
High Performance - highly integrated with the ability for powerful data pre-processing.
The energy-efficient RFicient® radio receiver technology with a current consumption less than 3 µA can receive radio telegrams in three license-free frequency bands simultaneously and independently of each other. This makes positioning systems for the localization of objects in warehouses possible, but also worldwide mobile applications, such as container tracking without manual frequency switching. RFicient® is also suitable for building automation, smart lighting, electronic shelf labels, remote maintenance and control, and wireless sensor networks in general. Years of maintenance-free operation is possible with very small batteries and solar cells or with energy harvesting. The particularly short response time in milliseconds also enables real-time applications. This new and efficient RF solution approach is therefore predestined for use in the Internet of Things.
Machine Learning applications in embedded devices are a strongly emerging trend. A large number of AI chips has been announced, the first products for embedded AI are on the market. Current neural network architectures like deep neural networks require high computational complexity and power consumption. Neuromorphic hardware in contrast relies on massive parallel processing and performs calculations, e.g. for Machine Learning, faster and with less power. Efficient architectures for neuromorphic hardware with respect to computational performance, power consumption and chip area are therefore a key element for a widespread deployment of neural networks in embedded devices. The Fraunhofer IIS presents different neuromorphic hardware architectures. Among them are novel approaches to bring the human neural network closer to the chip.
As one of the leading IC design facilities in Europe, we develop customized solutions to meet the constantly evolving requirements of industrial applications. Our work being independent of technology and manufacturer, we are able to provide our customers with optimum solutions. Our focus is on development of mixed-signal ASICs, intelligent integrated sensor systems as well as on design solutions for increasingly complex electronic systems.
Whether for industrial, communications, automotive or any other applications, we are your partner from the idea to the series production.
In contrast to digital circuits, analog components of mixed-signal systems are often still designed manually. According to the increasing miniaturization of electronics, this task is becoming even more complex and prone to errors. This results in long development cycles and high costs. By automation and systematic structuring of the integrated circuit design Intelligent IP (IIP) is able to counteract. Accordingly, IIP enables not only a faster and safer design but also a re-use of IPs.
New Innovative concepts are fundamental in order to meet the challenges for electronic systems owing to extended functionality and increasing miniaturization. Recent packaging-solutions not only have minimal space requirements but also allow a high data throughput with low energy-consumption. Fraunhofer IIS/EAS supports to master the complex design of packaging-solutions, exploiting degrees of freedom while considering the thermal, mechanical and electrical coupling.
Deep SiL testing of embedded systems enables an agile development process as used by the SW industry for years. By using virtual hardware models, deep software testing can start way before hardware is available. This allows to deep test your system from the application layer down to the hardware withouth modifying your software which will increase the coverage significantly and produce more robust systems.
Intelligent systems work particularly quickly, efficiently and reliably if the data is processed right in the place where it is generated: directly in the device and with the help of embedded artificial intelligence ("embedded AI"). Using the example of an autonomously driving robot that scans its environment with cameras, Fraunhofer IIS presents an edge AI solution approach that enables object recognition in offline operation. The robot analyzes its environment independently and can be controlled by gestures.
Hybrid radios automatically switch back and forth between analog VHF, digital radio and Internet streaming. By always looking for the best way to receive a radio program, they allow passengers to enjoy uninterrupted listening as they travel. This is possible through an integration of Fraunhofer software components. They guarantee the versatility to operate in various markets or vehicle categories and an uncompromising sound quality. Integrated data decoders offer additional information.
Tiny Machine Learning (TinyML) is a research area in the field of machine learning and describes the optimization as well as execution of AI-based processing chains on embedded systems. At Embedded World, we will demonstrate AI developments for small ultra-low power applications using noise detection as an example.