How can intelligent and teachable robots be evaluated? How do we know whether robots are good at what they’re doing? CAVECORE, a new Marie Skłodowska Curie Doctoral Network that is coordinated at the University of Bremen, is seeking to answer these questions.
Starting September 1, a total of 15 doctoral researchers will participate in CAVECORE over four years, working with cognitive robots that assess their surroundings with sensors, process information, and often interact with humans. CAVECORE is particularly interested in robots used in industrial, maritime, and service settings, such as care robots in private households. It is difficult to evaluate how well robots perform their tasks in such complex and open environments. Since behavior depends largely on context, there are no exact rules or clear criteria.
Determining how well a robot reacts to a situation requires first understanding why it makes certain decisions or acts a certain way, and can only be achieved once the robot is given the ability to disclose information about its behavior. This requires combining new methods from robotics, artificial intelligence, and software engineering, since these are necessary for making reliable statements about how safely and dependably robots perform tasks. How well these robots are received and integrated into various application settings largely depends on such skills.
CAVEVORE Connects Nine Partners from Six Countries
Marie Skłodowska-Curie Doctoral Networks are transnational doctoral programs with several academic and non-academic participating institutions and are formed with the intention of enhancing the researchers’ career development through international, interdisciplinary, and intersectoral mobility while strengthening the transfer of knowledge between the institutions. The networks are financed by the European Union as part of the Horizon Europe program. The application process is particularly demanding, and this year only 9.8 percent of the proposals were approved.
The University of Bremen project coordinator is Nico Hochgeschwender; Bettina von Helversen is also involved. Three of the fifteen doctoral researchers will work directly at the University of Bremen, while two additional doctoral researchers will be employed by industrial partners in Bremen.
Network partners include PAL Robotics (Spain), Cellumation (Bremen), EIVA (Denmark), the IT University of Copenhagen, Bielefeld University, the University of York, the Cyprus University of Technology, and LNE (Laboratoire national de métrologie et d’essais, the French counterpart to the German National Metrology Institute (PTB)).
Prof. Dr. Nico Hochgeschwender, Faculty of Mathematics / Computer Science, University of Bremen, Phone: +49 421 218-64330, Email: nico.hochgeschwender@uni-bremen.de
A robot navigates a virtual environment. Its movements are reflected in real time on a treadmill tha ...
Source: Philippe Stroppa
Copyright: Philippe Stroppa
Criteria of this press release:
Journalists
Information technology
regional
Research projects
English
A robot navigates a virtual environment. Its movements are reflected in real time on a treadmill tha ...
Source: Philippe Stroppa
Copyright: Philippe Stroppa
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).