|
Since 1999, the I2S research team performs application-oriented research and development of intelligent information systems. Main focus is on the application of artificial intelligence (AI) for innovative means of intelligent service coordination and decision-making in smart information system.
Vision. Intelligent information systems in the future Internet including the Quantum Internet are envisioned to provide users with assisted real-time access to relevant data and services anywhere, anytime, on any device, safe and secure, and in an intelligent way. Agent technologies for individual or joint AI action planning and learning, inter-agent communication and coordination can be used to implement autonomous, proactive, rational, adaptive and collaborative behaviour of such systems with intelligent agents. Semantic technologies enable the semantic interoperation of distributed heterogeneous data, services, and processes in due course of their coordination (search, composition, negotiation, execution) by these agents for smart information systems in support of industry and business, as well as our private and social life.
Research. The research of the I2S team for intelligent information systems is within two major directions in AI, that are hybrid AI and quantum AI.
Hybrid AI (including neuro-symbolic AI) is concerned with the combination of different methods from one or different subfields of AI such as machine learning, automated planning, vision and multiagent systems. Our research in hybrid AI focuses on the development of scalable and efficient methods for hybrid learning, semantic reasoning and planning under uncertainty, optimization, agent behavior modeling, and action (service) coordination in multiagent systems for smart information systems.
Quantum AI (QAI) is concerned with the use of quantum computing for solving computationally hard problems in AI, and vice versa. Our research in QAI focuses on the development and investigation of the potential utility of direct quantum and hybrid quantum-classical algorithms for machine learning, planning and scheduling, vision, and action (service) coordination in multiagent systems in concrete use cases.
Applications. The research of the I2S team has been implemented in open-source and partly awarded AI tools and systems for various applications including (but not limited to):
- Satellite-based earth observation and mission planning
- Safe navigation by self-driving cars
- Smart assistance in health care, migration support, and social media
- Process optimisation in cloud manufacturing
- Machine condition monitoring and maintenance
- Adaptive business processes in smart retail environments
- Intelligent simulation of virtual production lines
- Decentralized power regulation in smart micro-grids
- Agricultural production planning and logistics
Some of our information system prototypes were demonstrated at the CEBIT fair, the Hannover Industry fair (HIM), and the international Consumer Electronics Show (CES). Current main application areas of our research are (but not limited to): Autonomous driving, aerospace, manufacturing, energy management.
Since 2008, the research team is part of the DFKI Agents and Simulated Reality department (formerly: DFKI Deduction and Multiagent Systems department) and successfully contributed to many funded R&D projects in its core research areas.
Contact: PD. Dr. Matthias Klusch, email: klusch@dfki,de, phone: +49-681-85775-5297, fax: +49-681-85775-2235, postal address: German Research Center for Artificial Intelligence (DFKI) GmbH, Stuhlsatzenhausweg 3, D-66123 Saarbruecken, Germany
|
