Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Matthias Kerzel"'
Autor:
Ozan Özdemir, Matthias Kerzel, Cornelius Weber, Jae Hee Lee, Muhammad Burhan Hafez, Patrick Bruns, Stefan Wermter
Publikováno v:
Applied Artificial Intelligence, Vol 37, Iss 1 (2023)
Human infant learning happens during exploration of the environment, by interaction with objects, and by listening to and repeating utterances casually, which is analogous to unsupervised learning. Only occasionally, a learning infant would receive a
Externí odkaz:
https://doaj.org/article/fe16be4a2f8345afa750d580440cc6cd
Autor:
Matthias Kerzel, Philipp Allgeuer, Erik Strahl, Nicolas Frick, Jan-Gerrit Habekost, Manfred Eppe, Stefan Wermter
Publikováno v:
IEEE Access, Vol 11, Pp 123531-123542 (2023)
Robotic platforms that can efficiently collaborate with humans in physical tasks constitute a major goal in robotics. However, many existing robotic platforms are either designed for social interaction or industrial object manipulation tasks. The des
Externí odkaz:
https://doaj.org/article/7593ca94c7f244a096504a1f11f90da9
Publikováno v:
Frontiers in Robotics and AI, Vol 9 (2022)
We propose a neural learning approach for a humanoid exercise robot that can automatically analyze and correct physical exercises. Such an exercise robot should be able to train many different human partners over time and thus requires the ability fo
Externí odkaz:
https://doaj.org/article/d7add64c50bf45a68e02d883cce3ee87
Publikováno v:
Frontiers in Neurorobotics, Vol 15 (2021)
Long-term human-robot interaction requires the continuous acquisition of knowledge. This ability is referred to as lifelong learning (LL). LL is a long-standing challenge in machine learning due to catastrophic forgetting, which states that continuou
Externí odkaz:
https://doaj.org/article/bb8cd428f2d14cfb9888eba66546884b
Autor:
Focko L. Higgen, Philipp Ruppel, Michael Görner, Matthias Kerzel, Norman Hendrich, Jan Feldheim, Stefan Wermter, Jianwei Zhang, Christian Gerloff
Publikováno v:
Frontiers in Robotics and AI, Vol 7 (2020)
The quality of crossmodal perception hinges on two factors: The accuracy of the independent unimodal perception and the ability to integrate information from different sensory systems. In humans, the ability for cognitively demanding crossmodal perce
Externí odkaz:
https://doaj.org/article/68aa088544af4832b97a07f0c86c9950
Autor:
Stefan Heinrich, Yuan Yao, Tobias Hinz, Zhiyuan Liu, Thomas Hummel, Matthias Kerzel, Cornelius Weber, Stefan Wermter
Publikováno v:
Frontiers in Neurorobotics, Vol 14 (2020)
Human infants are able to acquire natural language seemingly easily at an early age. Their language learning seems to occur simultaneously with learning other cognitive functions as well as with playful interactions with the environment and caregiver
Externí odkaz:
https://doaj.org/article/59ff6bded6614cd3970dbeb66543eae6
Publikováno v:
Frontiers in Neurorobotics, Vol 14 (2020)
To overcome novel challenges in complex domestic environments, humanoid robots can learn from human teachers. We propose that the capability for social interaction should be a key factor in this teaching process and benefits both the subjective exper
Externí odkaz:
https://doaj.org/article/8c42fc0ec94b4059a88dbff81dbeaba2
Autor:
Di Fu, Cornelius Weber, Guochun Yang, Matthias Kerzel, Weizhi Nan, Pablo Barros, Haiyan Wu, Xun Liu, Stefan Wermter
Publikováno v:
Frontiers in Integrative Neuroscience, Vol 14 (2020)
Selective attention plays an essential role in information acquisition and utilization from the environment. In the past 50 years, research on selective attention has been a central topic in cognitive science. Compared with unimodal studies, crossmod
Externí odkaz:
https://doaj.org/article/806f53e9842d4bdb89967ce32cdaf5c1
Autor:
Matthias Kerzel, Jakob Ambsdorf, Dennis Becker, Wenhao Lu, Erik Strahl, Josua Spisak, Connor Gäde, Tom Weber, Stefan Wermter
Publikováno v:
KI - Künstliche Intelligenz. 36:237-254
Explainable AI has become an important field of research on neural machine learning models. However, most existing methods are designed as tools that provide expert users with additional insights into their models. In contrast, in human-robot interac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ebd139f1eaad4476ffb32ff748007e1a
https://doi.org/10.1007/s13218-022-00772-8
https://doi.org/10.1007/s13218-022-00772-8
Autor:
Di Fu, Fares Abawi, Hugo Carneiro, Matthias Kerzel, Ziwei Chen, Erik Strahl, Xun Liu, Stefan Wermter
Publikováno v:
International Journal of Social Robotics.
To enhance human-robot social interaction, it is essential for robots to process multiple social cues in a complex real-world environment. However, incongruency of input information across modalities is inevitable and could be challenging for robots
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd1aa79239226750a3fa9b499cd13af2
https://doi.org/10.1007/s12369-023-00993-3
https://doi.org/10.1007/s12369-023-00993-3