Diplomandenseminar

Die AG Robotik von der Universität Bremen bietet in Kooperation mit dem Robotics Innovation Center von der DFKI GmbH eine ganze Reihe von Seminaren und Vorträgen an. In dieser Reihe sind die Bachelor-, Master- und Diplomarbeiten enthalten. Die Termine werden hier regelmäßig aktualisiert. Externe können in vielen Fällen nach Rücksprache mit dem Sekretariat an den Vorträgen teilnehmen.

Vorträge

 -  14:00 Uhr
Exposé

Konzeptionelle Entwicklung eines Gefahrenerkennungs- und Vermeidungs-Systems für den lunaren Mikrorover im Projekt SAMLER-KI

von: Sireen Al Semadi  (Universität Bremen)
Der lunare Mikro-Rover im Projekt SAMLER-KI muss semiautonom in einer herausfordernden und potenziell riskanten Umgebung auf dem Mond agieren. Diese Arbeit konzentriert sich darauf, ein Gefahrenerkennungs- und -vermeidungssystem zu entwickeln, das dem Rover ermöglicht, auf der Mondoberfläche effizie…
 -  13:00 Uhr
Exposé

Konstruktion eines Mechanismus zur Ermöglichung der Bein-Rotation in Exoskeletten

von: Jan-Philipp Brettschneider  (Hochschule Bremen)
Eine wiederkehrende Herausforderung bei Exoskeletten ist die Übertragung von Kräften und Momenten entlang virtueller Achsen, welche sich im menschlichen Körper befinden. Ein Beispiel hierfür ist die Rotation des Beines um dessen Längsachse. Dieser Freiheitsgrad wird von vielen Exoskeletten nicht abg…
 -  13:00 Uhr
Kolloquium

Ambient Air Pollution Prediction

von: Hannes Gelbhardt  (Universität Bremen)
Accurately predicting air pollutant concentration remains challenging but essen- tial in preventing the public from being exposed to high concentrations that lead to several hundred thousand premature deaths across Europe yearly (European Environment Agency, 2023). This research focuses on enhanci…
 -  13:00 Uhr
Zwischenbericht

Adversary-driven Exploration in Coordinative Multi-Agent Deep Reinforcement Learning

von: Tim Schnauder  (Universität Bremen)
Multi-agent deep reinforcement learning (MADRL) is a powerful approach that enables agents to coordinate and collaborate to solve complex collaborative tasks. Applications of MADRL range from robotics to traffic control and resource allocation. However, the learning process can be slow, especially w…
 -  13:00 Uhr
Kolloquium

Cosserat Rod-based Kinetostatic Analysis of a 6-RUS Parallel Continuum Robot

von: Vinayvivian Pedrick Rodrigues  (RWTH Aachen)
Continuum manipulators have historically been considered serial devices, perhaps because they typically have a long slender form, and the dominant geometric modeling paradigm is constant curvature arc segments tangentially connected in series. However, as some researchers have noted, many continuum …
 -  13:00 Uhr
Kolloquium

Reinforcement Learning-based Control for Swing-up and Stabilization of an Underactuated Double Pendulum System

von: Chi Zhang  (Technische Universität München)
Nonlinear systems' control presents a significant challenge and has attracted considerable interest within the research community. In this study, reinforcement learning-based control is explored, a method that has shown promising results across various applications. The focus is placed on an underac…
 -  13:30 Uhr
Exposé

Model Complexity Adaptation of a Physical World Model for Learning Transferable Behaviors in Simulation for a Real-World Robotic System

von: Antonia Holsten  (Universität Bremen)
Learning robot behaviors in simulation has the advantages of being faster, safer and cheaper than learning on a real system. In exchange, the problem of Simulation Optimization Bias is introduced, which is caused by discrepancies between the model and the real system, commonly referred to as the Sim…
 -  13:00 Uhr
Exposé

Development of a highly backdrivable transmission for robotic applications

von: Mamdouh Abughonmi  (Jade University)
At DFKI there are several projects related to dynamic applications. The development of a robot that can operate effectively in dynamic environments is becoming increasingly important for several reasons such as demographic, environmental changes and ambitious space missions. Therefore, Much  re…
 -  14:00 Uhr
Zwischenbericht

Visual Voice Activity Detection with state-of-the-art video classifiers

von: Cedric Kränzle  (Universität Bremen)
Visual Voice Activity Detection (V-VAD) is the task to determine whether a person is speaking, based on images or video footage. It is a central point in Human Computer Interaction, as it is one of the first signals that can indicate that a human is interacting with a computer. Two new big datasets…
 -  13:30 Uhr
Exposé

Online Terrain Traversability Estimation for Wheel-Legged Rover Exploration

von: Yogeshkarna Govindaraj  (Hochschule Bonn-Rhein-Sieg)
In robotics, traversability, the ability of a robot to navigate challenging terrains, remains a significant challenge due to limitations in design, perception, and computation. The hybrid wheel-legged design, exemplified by the SherpaTT rover, offers enhanced mobility in unstructured terrain. Curren…
© DFKI GmbH
zuletzt geändert am 06.09.2024