Development and control of the multi-legged robot mantis

S Bartsch, M Manz, P Kampmann… - Proceedings of ISR …, 2016 - ieeexplore.ieee.org
This paper presents the multi-legged robot MANTIS which is developed within the project
LIMES at the DFKI RIC and the University of Bremen. In particular, we describe the …

Learning and generalizing behaviors for robots from human demonstration

A Fabisch - 2020 - media.suub.uni-bremen.de
Behavior learning is a promising alternative to planning and control for behavior generation
in robotics. The field is becoming more and more popular in applications where modeling …

Reconfigurable hardware-based acceleration for machine learning and signal processing

H Woehrle, F Kirchner - Formal Modeling and Verification of Cyber …, 2015 - Springer
Certain application areas of signal processing and machine learning, such as robotics,
impose technical limitations on the computing hardware, which make the use of generic …

BOLeRo: Behavior optimization and learning for robots

A Fabisch, M Langosz… - International Journal of …, 2020 - journals.sagepub.com
Reinforcement learning and behavior optimization are becoming more and more popular in
the field of robotics because algorithms are mature enough to tackle real problems in this …

Intelligenter Antrieb

R Bachmayer, P Kampmann, H Pleteit, M Busse… - KI-Technologie für …, 2023 - Springer
Frei schwimmende Unterwasserroboter können sich in allen sechs Freiheitsgraden
bewegen. Während aktives Nicken und Rollen in der Regel durch das Design, dh …

Intelligent Propulsion

R Bachmayer, P Kampmann, H Pleteit, M Busse… - AI Technology for …, 2020 - Springer
Free-floating underwater robotic vehicles are free to move in all six degrees of freedom.
While active pitch and roll is typically limited by design, ie hydrostatic stability, the robots …

[PDF][PDF] Heterogeneous Dataflow Hardware Accelerators for Machine Learning on Reconfigurable Hardware

H Woehrle, J Teiwes, MM Krell… - ECML …, 2014 - phdsession-ecmlpkdd2014.greyc.fr
The trend to develop increasingly more intelligent systems leads directly to a considerable
demand for more and more computational power. However, in certain application domains …