| Both sides previous revisionPrevious revisionNext revision | Previous revisionNext revisionBoth sides next revision |
| research [2023/08/14 13:41] – [Collaborative Projects] cstoess | research [2023/11/20 07:18] – dkastens |
|---|
| |
| |< 100% 33% 66%>| | |< 100% 33% 66%>| |
| | ^ {{:team:fame_logo.jpg?nolink&200|}} ^<WRAP> **FAME**: In the ERC Advanced Grant project “FAME“ (//Future-oriented cognitive Action Modelling Engine//) we will investigate how autonomous robots can understand everyday manipulation tasks and develop the skills to accomplish them successfully. The realization of computational models for performing everyday manipulation tasks for any object and any purpose would be a disruptive breakthrough in the creation of versatile, general-purpose robot agents, and it is still a grand challenge for AI and robotics.\\ |
| | \\ |
| | FAME wants to lay the groundwork for robots that achieve the competence level of humans. Humans can typically accomplish such tasks on the first try, despite uncertain physical conditions and novel objects. This requires comprehensive reasoning about the possible consequences of the intended behavior before physically interacting with the real world.\\ |
| | \\ |
| | In pursuit of these goals, FAME will investigate the hypothesis that a knowledge representation and reasoning (KR&R) framework based on explicitly represented and machine-interpretable inner-world models can enable robots to contextualize underdetermined manipulation task requests at the first attempt. The robots will gain their knowledge and understanding autonomously from sources such as written instructions and how-to videos provided by websites like WikiHow.</WRAP> ^ |
| | ^ {{:team:logo_eurobin193x54px.png?nolink&200|}} ^ **[[https://www.eurobin-project.eu//|euROBIN]]**: euROBIN is the Network of Excellence that brings together European expertise on Robotics and Artificial Intelligence (AI). It will establish a unified pan-European platform for research and development. For the first time, a large number of distinguished research labs across Europe are jointly researching AI-Based Robotics. As the lead beneficiary of the work package "Know", the Institute of Artificial Intelligence at the University of Bremen will provide, consolidate, combine, and advance the knowledge representation and reasoning (KR&R) capabilities of the euROBIN network. ^ |
| | ^ {{:tmp:ai4hri_logo.png?nolink&200|}} ^ **AI4HRI** (Artificial Intelligence for Human-Robot Interaction): Europe and Japan both face problems of shrinking and aging population, and using social robots is seen as a possible way of alleviating demographic issues. Robots need to be able to interact with people and this is studied in the field of Human-Robot Interaction (HRI). But dealing with humans is difficult, and HRI is still not making enough use of AI technologies. The goal of the AI4HRI project is to both develop and integrate several AI methods which will allow social robots to appropriately deal with humans around them. This includes 3 abilities that are currently missing in HRI: knowledge management and reasoning, learning of social skills, and planning and executing joint human-robot actions. AI4HRI brings together three teams who have very complementary approaches to solving the issues addressed by the project. IAI has extensive expertise on knowledge management and reasoning, Kyoto University, Japan has large know-how in learning for social interactions, and LAAS-CNRS, France adds to that strong expertise in human-aware design and in joint action planning and execution. The project will benefit from their synergy. Importantly, the above abilities will be combined into a single open-source architecture and shared with other researchers. ^ |
| ^ {{:logo-ease-2019.png?nolink&200|}} ^**[[http://www.ease-crc.org|EASE]]** (SFB 1320) is a collaborative research center. EASE will investigate the design, realization, and analysis of information processing models that enable robotic agents (and humans) to master complex human-scale manipulation tasks that are mundane and routine. EASE not only investigates action selection and control but also the methods needed to acquire the knowledge, skills, and competence required for flexible, reliable, and efficient mastery of these activities.^ | ^ {{:logo-ease-2019.png?nolink&200|}} ^**[[http://www.ease-crc.org|EASE]]** (SFB 1320) is a collaborative research center. EASE will investigate the design, realization, and analysis of information processing models that enable robotic agents (and humans) to master complex human-scale manipulation tasks that are mundane and routine. EASE not only investigates action selection and control but also the methods needed to acquire the knowledge, skills, and competence required for flexible, reliable, and efficient mastery of these activities.^ |
| ^ [[https://intel4coro.ai.uni-bremen.de|{{:kinect2_raw_nocalib.png?200|}}]] ^**[[https://intel4coro.ai.uni-bremen.de|IntEL4CoRo]]** designs and develops an immersive learning environment for Cognitive Robotics and AI. Based on the AVIVA model and a conceptual framework, coherent learning opportunities and materials will be developed.^ | ^ [[https://intel4coro.ai.uni-bremen.de|{{:kinect2_raw_nocalib.png?200|}}]] ^**[[https://intel4coro.ai.uni-bremen.de|IntEL4CoRo]]** designs and develops an immersive learning environment for Cognitive Robotics and AI. Based on the AVIVA model and a conceptual framework, coherent learning opportunities and materials will be developed.^ |
| ^ {{:projects:remaro.png?nolink&200|}} ^The REMARO project addresses the challenge of the development of a reliable AI system that can act on new underwater activities. The goal is to design brains for robots that enable robots to act safely while allowing them to improve by self-learning. Three project partners are from Bremen: DFKI, ROSEN Group, and the Institute of Artificial Intelligence at the University of Bremen.^ | ^ {{:projects:remaro.png?nolink&200|}} ^The **[[https://remaro.eu/|REMARO]]** project addresses the challenge of the development of a reliable AI system that can act on new underwater activities. The goal is to design brains for robots that enable robots to act safely while allowing them to improve by self-learning. Three project partners are from Bremen: DFKI, ROSEN Group, and the Institute of Artificial Intelligence at the University of Bremen.^ |
| ^ {{:projects:ki-campus_logo_mitimprover_blau.png?nolink&200|}} ^**[[http://improver.uni-bremen.de/|IMPROVER]]** develops a MOOC covering the most important aspects and techniques for designing and implementing cognition-enabled robot agents. ^ | ^ {{:projects:ki-campus_logo_mitimprover_blau.png?nolink&200|}} ^**[[http://improver.uni-bremen.de/|IMPROVER]]** develops a MOOC covering the most important aspects and techniques for designing and implementing cognition-enabled robot agents. ^ |
| ^ {{:research:logo_sfbfz.png?200|}} ^ The initiative **[[https://www.uni-bremen.de/farbige-zustaende.html|Farbige Zustände]]** aims at the development of a novel experimental method for developing metallic structural materials. The goal is the efficient and targeted identification of compositions and process chains that lead to a specific performance profile of the material. Conventional material developments are based on costly experimental investigations of chemical, mechanical, or technological material properties. The IAI uses AI and machine learning methods to predict material properties based on relationships extracted from experimental data and semantic knowledge. ^ | ^ {{:research:logo_sfbfz.png?200|}} ^ The initiative **[[https://www.uni-bremen.de/farbige-zustaende.html|Farbige Zustände]]** aims at the development of a novel experimental method for developing metallic structural materials. The goal is the efficient and targeted identification of compositions and process chains that lead to a specific performance profile of the material. Conventional material developments are based on costly experimental investigations of chemical, mechanical, or technological material properties. The IAI uses AI and machine learning methods to predict material properties based on relationships extracted from experimental data and semantic knowledge. ^ |
| ^ {{:projects:k4r_logo_rgb_rz.png?nolink&200}} ^ Der stationäre Einzelhandel befindet sich im Umbruch und sucht derzeit nach neuen Lösungen, um im Wettbewerb mit Onlinehändlern bestehen zu können. In **[[https://knowledge4retail.org/|Knowledge4Retail (K4R)]]** soll eine Plattform entstehen, die die Entwicklung und Nutzung von KI und den Einsatz von Servicerobotern im Einzelhandel voranbringt. Dabei sollen sogenannte „semantische digitale Zwillinge“ (semdZ) von Filialen als Grundlage für filial- und kundenindividuelle Lösungen in Einzelhandelsfilialen dienen. So kann mit semdZ die Logistik für jede Filiale individuell abgestimmt werden und vor Ort der Warenfluss nach exakter Platzierung der Produkte angepasst werden. Die Sortimentszusammenstellung kann sich filialindividuellen Besonderheiten dynamisch anpassen, und technische Hilfsmittel interagieren mit der K4R-Plattform, um die Mitarbeiter in der Filiale zu unterstützen.^ | ^ {{:projects:k4r_logo_rgb_rz.png?nolink&200}} ^ Brick-and-mortar retail is undergoing major changes and is looking for new solutions to compete with online retailers. **[[https://knowledge4retail.org/|Knowledge4Retail (K4R)]]** aims to create a platform that supports the development and use of AI and service robots in retail. So-called “semantic digital twins” of retail stores are intended to serve as the foundation for industry- and customer-specific solutions. Semantic digital twins can help coordinate logistics for each store and the flow of goods on site can be adjusted according to the exact placement of the products. The placement of the products dynamically adapts to store-specific features and technical aids interact with the K4R platform to support store employees.^ |
| ^ {{:projects:ilias.png?nolink&200|}} ^The ILIAS project develops methods to build robot systems, based on virtual reality (VR) and deep imitation learning, that can competently assist people with dementia on doing shopping and homework. ^ | ^ {{:projects:ilias.png?nolink&200|}} ^The **[[https://innolab.artiminds.com/ilias/|ILIAS]]** project develops methods to build robot systems, based on virtual reality (VR) and deep imitation learning, that can competently assist people with dementia on doing shopping and homework. ^ |
| ^ {{:projects:robohow.png?nolink&200}} ^**[[research:Robohow.Cog]]** enables robots to competently perform everyday human-scale manipulation activities - in both human working and living environments.^ | ^ {{:projects:robohow.png?nolink&200}} ^**[[research:Robohow.Cog]]** enables robots to competently perform everyday human-scale manipulation activities - in both human working and living environments.^ |
| ^ {{:projects:saphari.png?nolink&200}} ^**[[research:saphari]]** investigates Safe and Autonomous Physical Human-Aware Robot Interaction| | ^ {{:projects:saphari.png?nolink&200}} ^**[[research:saphari]]** investigates Safe and Autonomous Physical Human-Aware Robot Interaction| |
| ^ {{:projects:acat.png?nolink&200}} ^ **[[research:acat]]** enables robots to use information sources made for humans by learning and executing Action Categories^ | ^ {{:projects:acat.png?nolink&200}} ^ **[[research:acat]]** enables robots to use information sources made for humans by learning and executing Action Categories^ |
| ^ {{:rs_logo_text.png?nolink&200}} ^ **[[http://www.robosherlock.org|RoboSherlock]]** poses perception as a question-and-answer problem and uses the unstructured information management paradigm to create a framework for the perception of everyday objects^ | ^ {{:rs_logo_text.png?nolink&200}} ^ **[[http://www.robosherlock.org|RoboSherlock]]** poses perception as a question-and-answer problem and uses the unstructured information management paradigm to create a framework for the perception of everyday objects^ |
| ^ {{:projects:baycogrob.png?nolink&200}} ^ **[[research:BayCogRob]]** - Autonomous learning for Bayesian cognitive robotics (Schwerpunktprogramm Autonomes Lernen - DFG)^ | ^ {{:projects:baycogrob.png?nolink&200}} ^ **[[research:BayCogRob]]** - Autonomous learning for Bayesian cognitive robotics (DFG Priority Program on Autonomous Learning)^ |
| ^ {{:projects:memoman.png?nolink&200}} ^ **[[research:MeMoMan2]]** investigates Methods for real-time accurate Model-based Measurement of HuMan Motion^ | ^ {{:projects:memoman.png?nolink&200}} ^ **[[research:MeMoMan2]]** investigates methods for real-time accurate model-based measurement of human motion^ |
| |
| |
| ====== Internal Research Projects ====== | ====== Internal Research Projects ====== |
| |
| |< 100% 33% 66%>| | |
| ^ {{:logo_openease_2019.png?nolink&200|}} ^ **[[http://www.open-ease.org/|openEASE]]**: Web-based Knowledge Processing Service for Robots and Robotics/AI Researchers^ | ^ {{:logo_openease_2019.png?nolink&200|}} ^ **[[http://www.open-ease.org/|openEASE]]**: Web-based Knowledge Processing Service for Robots and Robotics/AI Researchers^ |
| ^ {{:projects:cram2.png?nolink&200}} ^ **[[:research:cram]]**: Cognitive Robot Abstract Machine^ | ^ {{:projects:cram2.png?nolink&200}} ^ **[[:research:cram]]**: Cognitive Robot Abstract Machine^ |
| ^ {{:projects:knowrob.png?nolink&200}} ^ **[[:research:knowrob]]**: Knowledge processing for autonomous robots^ | ^ {{:projects:knowrob.png?nolink&200}} ^ **[[:research:knowrob]]**: Knowledge processing for autonomous robots^ |
| ^ {{:research:software:pracmln-darkonbright-transp.png?nolink&200}} ^ **[[http://www.pracmln.org/|pracmln]]**: Markov logic networks in Python^ | ^ {{:research:software:pracmln-darkonbright-transp.png?nolink&200}} ^ **[[https://www.pracmln.org/|pracmln]]**: Markov logic networks in Python^ |
| ^ {{:research:software:prac-darkonbright-transp.png?nolink&200}} ^ **[[http://www.actioncores.org/|PRAC]]**: Probabilistic Action Cores -- Natural-language understanding for intelligent robots^ | ^ {{:research:software:prac-darkonbright-transp.png?nolink&200}} ^ **[[http://www.actioncores.org/|PRAC]]**: Probabilistic Action Cores -- Natural-language understanding for intelligent robots^ |
| ^ {{:projects:physics.png?nolink&200}} ^ **[[:research:naive-physics]]**: Simulation-based reasoning about physical effects^ | ^ {{:projects:physics.png?nolink&200}} ^ **[[:research:naive-physics]]**: Simulation-based reasoning about physical effects^ |
| |
