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

 -  13:30 Uhr
Exposé

Development of a vertical Launch and Recovery System for the AUV DeepLeng

von: Jonas Pollex  (Universität Bremen)
Exposé
 -  13:00 Uhr
Zwischenbericht

Robust Co-design for Underactuated Systems

von: Federico Girlanda  (University of Padua)
An approach to obtain an optimal behaviour of a system to achieve a specific task is via an interplay between trajectory optimization, stabilization and design optimization. To find a structured way to deal with this co-optimization is the main objective of the thesis work. The sim-to-real gap repre…
 -  13:00 Uhr
Kolloquium

Structural analysis and design of a micro-rover for lunar applications based on Coyote III

von: Leon Spies  (FH Aachen)
The aim of this thesis is to investigate the structural survivability of an existing Rover model (Coyote III) for use in space. A Rover experiences various structural loads throughout the course of the mission. These include the intense vibration experienced during the rocket launch, the lunar landi…
 -  13:00 Uhr
Kolloquium

Emotional regulation and coping in assistive/social robots

von: Janssen, Ayden  (Universität Bremen)
While a simple system modeling emotions can make a robot show believable emotions, it can also exhibit socially questionable or unacceptable emotions, like greeting a visitor while being visibly angry. Humans solve this problem by regulating their emotions with regard to the current situation and co…
 -  14:00 Uhr
Zwischenbericht

Adaptive Bewegungsunterstützung bei der Ausführung bekannter Bewegungsabläufe basierend auf der Echtzeitauswertung von Biosignalen

von: Tim Due  (Universität Bremen)
2. M.Sc. Vortrag
 -  13:30 Uhr
Exposé

Design of compliant robot leg using variable stiffness mechanism

von: Jung Min Lim  (RWTH Aachen)
The importance of legged robots is emphasized, as legged robot locomotion allows highly precise performance and wide spectrum of application, even in rough, unstructured terrain. However, the present challenges in legged robot locomotion are the trade-off between versatility and robustness, and the …
 -  13:00 Uhr
Zwischenbericht

Development and Analysis of a Fused Pose Estimator and a visual Odometry Component for a Robotic Rover

von: Felix Glinka  (Universität Bremen)
An accurate, up-to-date estimation of it's own pose is important for any mobile robot that should be able to navigate in and/or interact with the physical world. While there are many methods of pose estimation, they are often lacking in one or more specific aspects. In particular, they may be inaccu…
 -  13:00 Uhr
Kolloquium

Deviant Tone Detection in lnfants by P3a ERP Classification

von: Robin Kemmerich  (Universität Bremen)
The aim of this study was to implement a machine learning classifier for infant EEG data. Similar classifiers for adults are commonly utilized by brain-computer-interfaces. Three experiments were conducted to test our implementation, with the goal of classifying standard versus deviant/target stimul…
 -  13:00 Uhr
Kolloquium

Mechanical analysis of a motor test bench under consideration of alignment errors

von: Yaswanth Murali  (Hichschule Bochum)
DFKI is setting up a motor test bench to characterize the robotic drives developed in-house. The measurement can be influenced by torsional vibrations and alignment errors. Therefore, it is necessary to analyze the setup mechanically to minimize the measurement errors. For this purpose, the natural …
 -  10:30 Uhr
Kolloquium

Sim-to-Real Transfer in Deep Reinforcement Learning: Overcoming the „Simulation-Reality-Gap“ for Motion Control of an Unmanned Surface Vehicle

von: Tom Vincent Slawik  (Universität Hannover)
Unmanned surface vehicles (USVs) are boats that can navigate on the water surface without theneed for a human operator on board. Since there are many disturbances and nonlinear effects due tothe hydrodynamics of water, there is a need for robust motion control systems. Reinforcementlearning provides…
© DFKI GmbH
zuletzt geändert am 06.09.2024