The scientist from DFKI research department Agents and Simulated Reality receives the award for her master's thesis in the "Artificial Intelligence" category. In her proof-of-concept study, Noshaba Cheema presents a procedure that simulates human fatigue when operating devices with outstretched arms. The method works on the basis of virtual agents and gets by without human data.
If the arm is constantly stretched out, for example, to interact with a control panel or touch screen, but also during assembly or handcraft work, it will lead to muscular overload or signs of wear and tear. To avoid this phenomenon, also known as 'gorilla arm,' interaction concepts and user interface design of devices – even in virtual reality – must carefully consider ergonomics.
Noshaba Cheema's master's thesis investigates how fatigue can be predicted and prevented through user interactions in which the arms are held outstretched forwards without real users. Instead, the movements are simulated, and the software agents are trained using Reinforcement Learning (RL), a machine learning method. These virtual (in silico) user test methods can predict real human fatigue data without the need to collect human motion data. This opens the possibility to easily explore new environments for which no data is available, e.g., fatigue effects on the moon, or situations where many movements have to be performed under time pressure.
The thesis shows how AI agent simulations can be used to understand virtual user testing and how a biomechanical motion model can help to generate more natural movements. The method presented reproduces the subjective effort very accurately, without simulating the muscles and their energy expenditure, and thereby arrives at more accurate predictions than previous approaches.
The results were developed in cooperation with Prof. Laura Frey-Law (University of Iowa Healthcare), Prof. Perttu Hämäläinen, Prof.Jaakko Lehtinen, Kourosh Naderi (all Aalto University Finland), and Prof. Philipp Slusallek (DFKI and Saarland University). The paper "Predicting Mid-Air Interaction Movements and Fatigue Using Deep Reinforcement Learning" was published at the Conference on Human Factors in Computing Systems (CHI) 2020.
"I firmly believe that artificial intelligence and technology, in general, will make people's lives better and easier. I therefore very much hope that women, in particular, will be interested in programming, technology, and IT. The fields of application are diverse and range from animation, art, games, to simulation, bioinformatics, or business," said Noshaba Cheema at the virtual awards ceremony.
About the Deutsche Telekom Women’s STEM Award:
Deutsche Telekom, the student magazine "audimax Medien," and the "MINT Zukunft schaffen" initiative have been presenting the award since 2014. Female STEM graduates from all over the world can submit their theses on strategic growth fields. In 2020 the focus is on: Artificial Intelligence, Cloud, Cyber Security, Internet of Things and Networks of the Future. The best thesis will be awarded 3,000 euros, with an additional 500 euros per strategic growth area. The patron is Claudia Nemat, Board Member Deutsche Telekom AG, responsible for Technology and Innovation.
Phone: +49 681 85775 3834
Criteria of this press release:
Journalists, Scientists and scholars
Information technology, Medicine, Nutrition / healthcare / nursing
Contests / awards, Scientific Publications
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).