In the future, robots will support people with physical disabilities in their own homes. To assess and expand the suitability of robots for everyday activities, the Institute for Artificial Intelligence at the University of Bremen equipped a new research laboratory with a kitchen and furniture. There is also an exact digital image of this lab, known as a “digital twin.” This enables the international research community to develop and test robotic technologies remotely.
Carrying out everyday tasks like a human being – this is the long-term goal of robotics research at the University of Bremen. After all, robots should one day, ideally as soon as possible, be able to help people with physical disabilities. However, tasks that are very simple for humans – setting and clearing the table, spreading butter on bread, stocking the fridge, or washing the dishes – are extremely complex processes for robots; a painstaking amount of effort goes into the robot’s development so that they can carry out these activities flawlessly. The University of Bremen now has a new research laboratory for its work on suitability for everyday activities; the lab largely resembles a normal apartment with a kitchen, places to sit, and other furniture.
“Setting up this laboratory, which broadly resembles an everyday setting, is a major step toward increasing our focus on artificial intelligence and AI-based robotics in particular,” says Professor Jutta Günther, the University of Bremen’s President. “The work made possible by the lab’s ‘digital twin’ also brings us into even closer contact with the international research community. The university aside, this will enhance the entire city of Bremen’s reputation as being the place for AI.”
Professor Michael Beetz, one of the world’s leading researchers in the artificial intelligence field, is keen to stress the importance of the true-to-life research laboratory. “We must not adapt the environment to the robots, as is the case in factories or logistics centers. Instead, we have to develop the robots in such a way that they can navigate the human environment and provide effective help there,” says Professor Beetz.
Spotlight on “Digital Twin”
In Professor Beetz’s view, the highlight of the new lab is not what you see on-site at the Institute for Artificial Intelligence, but something you don’t see at first. “We developed an exact digital image of this lab, known as a digital twin. We make this available to the international research community so that scientists in far-flung countries can also work on these topics under the same conditions as we do on-site,” says Professor Beetz. “The challenges in this area are so large that they require the cooperation of the research community to bring about major developments quickly. A single working group can only make progress in sub-areas – and this happens at a slow pace.”
As a result, the laboratory itself and the digital twin are dependent on each other. The Bremen facility and its furnishings are necessary for putting the robots to use in the desired scenarios in a real-life environment and conducting practical experiments. The laboratory apartment also allows the findings recorded by research groups around the world with the digital twin to be tested in a real-life setting in Bremen. “Does what was conceived and developed in India actually work in a real environment?” says Michael Beetz. Bremen could reap further benefits from the laboratory, as the international research community may meet more often to test the latest developments on-site and exchange ideas about them.
“Working Together to Develop and Share Research Knowledge”
The laboratory apartment is equipped in accordance with the latest research standards, providing a solid foundation for research in AI-based robotics at the University of Bremen. Over the years, this has included work involving the Institute for Artificial Intelligence with the Collaborative Research Center EASE (Everyday Activity Science and Engineering), the Center for Computing Technologies, as well as various projects and start-ups. “Providing our high-performance robot control systems developed in Bremen, as well as the research data and results, and offering the possibility to test our robots in our laboratory is a logical continuation of the ‘open data – open science – open research’ approach,” says Professor Beetz. Given the complexity and scope of the research tasks involved in AI-based robotics, computer scientists are keen to work together in developing and sharing their research knowledge in order to achieve swifter progress.
In addition to the new laboratory apartment, the Bremen-based robot researchers led by Professor Beetz have set up further very realistic laboratories, such as a small drugstore. “Robots set the table in the apartment, clear it, or prepare simple meals. At the drugstore, they perform stock checks, show where products are, and put them on the shelves,” says Professor Beetz. “The labs are measured with high precision and implemented as machine-interpretable models that enable experiments to be automatically evaluated and high-quality research data generated. As digital twins, they can be downloaded to your own computer like a computer game. Researchers can then carry out their research “from home” around the world. The underlying idea of open exchange within the entire research community always has a valuable role throughout.
The new laboratory apartment was partly financed by the University of Bremen, while third-party research projects provided most of the funds for the furnishings. The establishment of the facility has created new positions for researchers, which are currently being consolidated by further research projects and partnership agreements with companies.
Further Information:
www.ai.uni-bremen.de
www.ease-crc.org
www.uni-bremen.de/en/tzi/
www.uni-bremen.de/en
Contact:
Professor Michael Beetz
Institute for Artificial Intelligence / Collaborative Research Centre EASE
University of Bremen
Tel.: +49 421 218-64005
Email: beetz@cs.uni-bremen.de
Professor Michael Beetz
Institute for Artificial Intelligence / Collaborative Research Centre EASE
University of Bremen
Tel.: +49 421 218-64005
Email: beetz@cs.uni-bremen.de
A robot helps out in the kitchen: a scene from the new robotics lab at the University of Bremen.
Dominic Kastens
Dominic Kastens / University of Bremen
Criteria of this press release:
Business and commerce, Journalists, Scientists and scholars, Students, Teachers and pupils, all interested persons
Information technology, Nutrition / healthcare / nursing, Social studies
transregional, national
Research projects, Research results
English
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).