Synthetic data for environmental protection, AI methods for the resilient and crisis-resistant manufacturing industry, quantum computing, dynamic supply chains and secure data spaces, smart farming, and agricultural robotics - with this spectrum of key topics, DFKI 2023 will be represented in three halls at the Hannover Messe.
At the MWK Lower Saxony joint stand, Hall 2, Stand A40, the Saarland joint stand, Hall 2, B34, and at the Industrial Wireless Arena & 5G Networks in Hall 14, DFKI will show project results, technologies, and demonstrators from the Lower Saxony, Saarbrücken and Kaiserslautern sites.
In Hall 8, the SmartFactory_KL will demonstrate further development of its Production Level 4 concept with the _KUBA Modular Production Unit.
Synthetic data can be generated in large quantities faster and cheaper than their counterparts and are used in many applications in AI development. As training material for AI models, they provide the data basis for new experimental use cases. In the Agri-Gaia project, the working groups of the DFKI research areas, Plan-based Robot Control and Marine Perception, have developed a new approach for detecting plastic waste in the environment, especially in agricultural settings.
The SPAICER project aims to develop AI-based smart resilience services to generate comprehensible recommendations for action that enable decision-makers to initiate meaningful stabilization measures at an early stage. To increase resilience, smart services are offered on an open digital platform for companies - without them having to build up extensive AI expertise themselves or hand over their data sovereignty.
With the "Hidden Problem Detector," the Smart Service Engineering research department demonstrates a model for identifying hidden problems in supply chains from the PAIRS (Privacy-Aware, Intelligent and Resilient CrisiS Management) project. PAIRS pursues the development of a learning platform for crisis management that combines AI and human intelligence. The AI hybrid technologies are designed to anticipate both the initial crisis event and the reactions of various actors in cross-domain data space to generate targeted recommendations for action.
QUASIM is testing a quantum computing (QC) approach to accelerate simulations in manufacturing and make them more practical by reducing modeling efforts through quantum machine learning (QML). By comparing with previous methods, innovative solutions based on QC are designed, implemented, integrated into low-threshold Quantum Services (QS), and made available in distributed environments. In particular, hybrid models combining QC and machine learning (ML) are promising. This should enable manufacturing companies to access QS with limited simulation expertise.
The exhibit uses the example of machining and laser cutting to show how outsourcing simulations and training to QA support models from numerics and ML. In this way, simulations are accelerated, and innovative simulation models are transferred to industrial practice in the first place.
On the _KUBA modular production unit of the SmartFactory-KL, visitors can configure a model truck, the production of which starts immediately on-site. In parallel, the CO2 footprint, energy consumption, and material composition are tracked and displayed via the management shell. Many key technologies such as Digital Twins, Operational Safety Intelligence, 5G, Artificial Intelligence, Digital Product Passport, and Administrative Shell are visible at the SmartFactory-KL joint stand.
The aim of the Open6GHub is to contribute to a global 6G harmonization process and standard in the European context that takes into account Germany's interests in terms of societal priorities (sustainability, climate protection, data protection, resilience) while strengthening the competitiveness of companies, technological sovereignty and the position of Germany and Europe in the international competition for 6G.
The Open6GHub will contribute to the development of an overall 6G architecture, but also of end-to-end solutions in the following areas, among others: advanced network topologies with highly agile so-called organic networking, security and resilience, terahertz and photonic transmission methods, sensor functionalities in the networks and their intelligent use and further processing, and application-specific radio protocols.
Nature Robots develops autonomous robots for regenerative agriculture. Based on the self-built long-term autonomous monitoring robot Lero, the company creates temporally and spatially high-resolution, three-dimensional plant maps of crops and weeds, which are transferred into a monitoring interface for agronomists, farmers, and plant breeders. The AI and robotics systems allow use in natural and arbitrarily structured environments such as vegetable, fruit, and grape growing, as well as agroforestry, forestry, photovoltaic, and agro-photovoltaic environments. Nature Robots is a spin-off of DFKI and was founded in Osnabrück in January 2022.
Talk with Sven Lake, DFKI Plan-based Robot Control Research Department & Managing Director at Nature Robots GmbH
In order to achieve the ecological and economic advantages of diverse and perennial cultivation systems, the EXIST research transfer funded project PlantMap (Powerful Long-term Autonomous Navigation Towards Monitoring Agricultural Plants), coordinated by DFKI, is developing a temporally and spatially highly resolved three-dimensional plant map of individual plants as well as entire beds.
Based on the specially developed and built 3D long-term autonomous navigating monitoring robot, Lero, plant maps are generated and transferred into a monitoring user interface for agronomists, farmers, and plant breeders. The technologies allow for multiple applications in vegetable, fruit, and viticulture, as well as agroforestry, forestry, photovoltaic, and agro-photovoltaic environments.
Nature Robots is a spin-off of DFKI and was founded in Osnabrück in January 2022.
Panel discussion on AI & Machine Learning.
With Dr. Sebastian Pütz, DFKI Research Department Plan-based Robot Control & Managing Director Nature Robots GmbH