Category Archives: Projects

NOTOX

NOTOX is one of the building block projects of the European research initiative SEURAT (safety evaluation ultimately replacing animal testing) funded by EU-FP7 HEALTH programme and the European Cosmetics Association (Cosmetics Europe). The total funding for the cluster projects is 50 million €. This initiative with six projects as building blocks aims at the common strategy “towards the replacement of current repeated dose systemic toxicity testing in human safety assessment”.

Tomographic reconstruction of an electron tomography tilt series. Image from [1].

DFKI Participated in NOTOX by providing high performance implementations of iterative tomographic reconstruction algorithms for electron tomography using the Ettention software package.

[1] T. Dahmen et al., The Ettention software package, Ultramicroscopy 161 (2016) 110–118.

IMCL – Iterative Methods for Computed Laminography

Standard 3D Computed Tomography (3D-CT) is an established technique both in medicine and non-destructive industrial testing. However, some very important and safety-critical objects, like airplane wings, printed circuit boards or fiber-reinforced lighweight construction structures cannot be appropriately examined using 3D-CT.

Geometry of the CLARA Laminography device. Image from [1].

We are building a novel pipeline based on Computed Laminography(CL) to allow for a robust and reliable non-destructive testing of these objects, drawing on the excellence of our team in industrial engineering, mathematical algorithm development and highly-efficient parallel software implementations.

Laminographic reconstruction using different reconstruction settings. Image from [1].

[1] P. Trampert et al., Spherically symmetric volume elements as basis functions for image reconstructions in computed laminography, J. Xray. Sci. Technol. Preprint (2017) 1–14.

Team

 

Individualisierte Implantate und Prothesen für die Versorgung unterer Extremitäten (IIP-EXTREM)

Individualisierte Implantate und Prothesen für die Versorgung unterer Extremitäten (IIP-EXTREM)

Severe injuries of the lower leg require individual treatment and often require the treating doctors to make difficult decisions. The funded research project  IIP-EXTREM in the BMB+F program „Individualized Medical Technology“ aims to provide technical support for those decisions and make them more quantitative.

The project follows two strategies: the first strategy aims for reconstruction using individualized and standardized implants. Powerful simulations and visualizations based on clinical CT or MRT data will help to re-orient bone fragments, make decisions concerning the right choice of implant and finally generate individual implants. The fabrication of the implants will be performed using modern methods of additive metal fabrication.

The second strategy will come in place if a severe injury makes an amputation inevitable. In this case, simulation software  will help to create an exact fitting, high performance prothesis shaft.

Both subprojects aim to use efficient simulations and modern additive manufacturing methods to optimize the production chain and save expensive recurring treatments.

The clinical side of the consortium is represented by the Chair of Orthopedics of the Trauma Surgery of the university Witten/Herdecke. The simulation and its validation is developed jointly between the Chair of Applied Mechanics of Saarland University and the German Research Center for Artificial Intelligence (DFKI), that also creates the user interfaces. Individualized implants are developed and manufactured by Karl Leibinger Medizintechnik GmbH & Co. KG, the prothesis shafts are developed and manufactured by Ottobock HealthCare GmbH, who also coordinates the consortium.

Project duration: 01.06.2016 – ???

Contact: Dr Tim Dahmen

Team

INTERACT

INTERACT – Interactive Manual Assembly Operations for the Human-Centered Workplaces of the Future

In order to be competitive in a global scale, European factories should be operated by a highly skilled workforce supported by advanced automation and IT tools. The European research project INTERACT aims to utilize workers’ knowledge on executing manual assembly tasks and include it in the digital tools used to support design, verification, validation, modification and continuous improvement of human-centred, flexible assembly workplaces.

Continue reading INTERACT

HYSOCIATEA

Hybrid Social Teams for Long-Term Collaboration in Cyber-Physical Environments

HySociaTea is short for Hybrid SociaTeams for Long-Term Collaboration in Cyber-Physical Systems. In this project, funded by the German Ministry for Education and Research, the German Research Center for Artificial Intelligence (Deutsches Forschungszentrum für Künstliche Intelligenz – DFKI) investigates how teams of humans, robots and software agents (i.e. virtual characters and softbots) can work collaboratively in a production scenario.

Many large-scale real-world problems, such as effective disaster response, the careful dismantling of contaminated structures or the efficient manufacturing and construction of complex artifacts, require the coordination of such teams of humans, robots, and software agents to accomplish the collection of challenging tasks. It is well known that more can be achieved through teamwork in a shorter timeframe and at a higher quality than by individual performance. Our vision of effective hybrid social teams of humans, robots and software agents working together seamlessly in dynamic cyber-physical environments can only be achieved by combining the research excellence and experience of eight DFKI research departments located at the three main sites (Bremen, Kaiserslautern, Saarbrücken) in a joint effort. HySociaTea is thus a collaborative grand challenge project, which combines the diverse DFKI competencies in a wide spectrum of subfields of Artificial Intelligence to address a fundamental research goal in the area of intelligent interacting agents.

The envisioned characteristics of hybrid social teams of physical and virtual agents imply the following fundamental research challenges:

  1. Distributed problem analysis and task allocation based on skills, knowledge and experience
  2. Sharing goals, plans as well as intentions and coordinating plan execution
  3. Understanding all physical and communicative interactions of all team members
  4. Developing social group behavior and emotional coherence
  5. Building mutual trust and demonstrating accountability for the assigned subtasks
  6. Compensating weaknesses of individual team members by empathetic help

Project Homepage: http://hysociatea.dfki.de/

Contact: Ingo Zinnikus


Deutsche Version

Das vom Bundesministerium für Bildung und Forschung (BMBF) geförderte Projekt HySociaTea (Hybrid Social Teams for Long-Term Collaboration in Cyber-Physical Environments) realisiert und untersucht die Zusammenarbeit von technologisch unterstützten Menschen mit autonomen Robotern, virtuellen Avataren und Softbots, die zusammen in einem Team gemeinsame Aufgaben lösen sollen.

Im Zusammenhang mit dem Zukunftsprojekt Industrie 4.0 ermöglichen diese hybriden Teams z.B. eine flexible Produktion, in der auch auf ungeplante Ereignisse durch eigenständige Reorganisation des Teams reagiert werden kann. Neben der Erforschung der reinen technischen Grundlagen, liegt der Schwerpunkt auch auf der Entwicklung von robotischen Teamkompetenzen, sowie auf intelligentem Multi-Agenten-Verhalten, welche auch wichtige Aspekte in rein menschlichen Teams sind. Technische Systeme sollen hier vor allem als Assistenzsystem für den Menschen in der Produktion eingesetzt werden – die Roboter müssen also als Partner im Gesamtprozess wahrgenommen werden.

Der in HySociaTea entwickelte und untersuchte hybride Teamaufbau kann auf lange Sicht in unterschiedlichen realen Herausforderungen eingesetzt werden, z.B. bei modularen Produktionsanlagen in der Fabrik der Zukunft, als Rettungsteam bei Katastrophenszenarien, oder bei der notwendigen Arbeitsteilung zwischen Menschen und Maschinen beim sicheren Rückbau von Atomkraftwerken.

Zur Realisierung des Projekts bündeln verschiedene Fachbereiche aus allen DFKI-Standorten (Bremen, Kaiserslautern, Saarbrücken) ihre Kompetenzen:

  • RIC (Robotics Innovations Center, DFKI Bremen): autonome und kooperative Robotersysteme, mobile Manipulation
  • CPS (Cyber-Physical Systems, DFKI Bremen): sichere Mensch-Roboter Interaktion
  • EI (Embedded Intelligence, DFKI Kaiserslautern): technische Einbindung des Menschen, tragbare Sensorik
  • AV (Augmented Vision, DFKI Kaiserslautern): Perzeptionsmodule mittels Bildverarbeitung und Sensorfusion
  • KM (Knowledge Management, DFKI Kaiserslautern): blickgesteuerte Aufmerksamkeitserkennung, Realzeit-Objekterkennung
    IUI (Intelligent User Interfaces, DFKI Saarbrücken): emo-soziale virtuelle Charaktere, multimodale Dialogplattform
  • LT (Language Technology Lab, DFKI Saarbrücken): autonome Teamreorganisation, Sprachinteraktion
  • ASR (Agents and Simulated Reality, DFKI Saarbrücken): Kommunikations-Middleware, Dual Reality

HySociaTea wird gefördert durch das Bundesministerium für Bildung und Forschung (BMBF) unter Förderkennzeichen 01IW14001.

Project Homepage: http://hysociatea.dfki.de/

Ansprechpartner: Ingo Zinnikus

FI-Core

Future Internet – Core

Im Verbund mit insgesamt 31 Partnern aus 8 europäischen Ländern und Israel, startete am 01.09.2014 das zukunftsweisende Projekt „Future Internet – Core“. Das Projekt wird von der EU im Rahmen des Future Internet Public Private Partnership (FI-PPP) gefördert und schließt sich eng an die bereits laufenden Projekte FI-WARE und FI-Content2 an. Das auf 2 Jahre angelegte Projekt soll insbesondere die Basistechnologien für das Internet der Zukunft erforschen. Der Forschungsbereich ASR beschäftigt sich in seinem Workpackage mit “Advanced Web-based User Interfaces” – einem Forschungsthema bei dem hier schon umfassende Expertise durch frühere und laufende Projekte besteht.

Continue reading FI-Core

CREMA

Cloud-based Rapid Elastic Manufacturing

The European H2020 research project CREMA (Cloud-based Rapid Elastic Manufacturing) aims at the innovative combination of cloud computing and XaaS (Everything-as-a-Service) for highly flexible, resource-efficient coordination of service-based industrial manufacturing processes in distributed and dynamically changing environments.

Continue reading CREMA

Arvida

Angewandte Referenzarchitektur für virtuelle Dienste und Anwendungen

ARVIDA ist ein vom Bundesministerium für Bildung und Forschung (BMBF) gefördertes Verbundprojekt mit aktuell 23 Partnern aus Forschung und Industrie. Das Hauptziel des Projektes ist die Erstellung einer dienstorientierten Referenzarchitektur für Virtuelle Techniken (VT).

Continue reading Arvida