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
Zwischenbericht

Highly-Dynamic Movements of a Humanoid Robot Using Whole-Body Trajectory Optimization

von: Julian Eßer  (Universität Duisburg-Essen)
In order to further close the gap between robots and their natural counterparts, current research is driving towards exploiting the natural dynamics of robots. This requires a rethinking about the way we control robots for moving in a more dynamic, efficient and natural way. Dynamic bipedal locomoti…
 -  13:30 Uhr
Zwischenbericht

Development of an AUV calibration framework

von: Christophe Stilmant  (Universität Bremen)
In order to increase accuracy and robustness of their state and pose estimations, autonomous underwater vehicules (AUV) use a growing number of sensors. All these sensors must be calibrated before being used. This calibration step is essential in order to receive the most reliable data possible: Wit…
 -  13:00 Uhr
Exposé

Vectored Thrust Control of Autonomous Underwater Vehicles

von: Lukas Rust  (Universität Bremen)
Autonomous Underwater Vehicles (AUVs) have developed over the last decades into one of the most important technological research platforms for marine/ocean exploration. Increased advancements in this area have lead to more robust, precise and intelligent hardware and software solutions which AUVs ca…
 -  14:00 Uhr
Exposé

Applying heuristic search strategies to plan with re-configurable multi-robot systems

von: Rahul Babu Shrestha  (Jacobs University Bremen)
Reconfigurable robots can physically merge to create dynamic robotic systems, leading to additional degrees of freedom. Temporal Planning for Reconfigurable Multi-Robot Systems (TemPl) is a constrained-based mission planner for reconfigurable multi-robot systems which introduces a mission descriptio…
 -  13:00 Uhr
Zwischenbericht

Aufbau eines hydraulischen Tauchzellensystems zur dreidimensionalen Lageänderung eines tiefseefähigen Unterwasser-Fahrzeuges

von: Florian Schmeer  (Universität Bremen)
Das Projekt EurEx-SiLaNa (EurEx - Sichere Langzeitnavigation) des Deutschen Forschungszentrums für künstliche Intelligenz (DFKI) und des Deutschen Zentrums für Luft- und Raumfahrt (DLR) befasst sich mit der Erhöhung der Einsatzdauer autonomer Unterwasserfahrzeuge (engl. autonomus underwater vehicle …
 -  11:00 Uhr
Kolloquium

Visual Explanations in Deep Reinforcement Learning via Convolutional Neural Network Localization

von: Matthias Rosynski  (Universität Bremen)
Deep Reinforcement Learning (DRL) connects the classic Reinforcement Learning algorithms with Convolutional Neural Networks (CNN). A problem in DRL is that CNNs are black-boxes and it is not easy to understand the decision-making process of agents. In order to be able to use the programs in highly d…
 -  13:00 Uhr
Exposé

Highly-Dynamic Movements of a Humanoid Robot Using Whole-Body Trajectory Optimization

von: Julian Eßer  (Universität Duisburg-Essen)
In order to further close the gap between robots and their natural counterparts, current research is driving towards exploiting the natural dynamics of robots. This requires a rethinking about the way we design and control robots for moving in a more dynamic, efficient and natural way.Dynamic biped…
 -  13:00 Uhr
Kolloquium

Development and Comparison of Self-Righting Behaviors on a Four-Legged Walking Robot

von: Simon Teiwes  (Universität Bremen)
Mobile autonomous robots are increasingly conquering many fields of applications.
 The key feature of those systems is their autonomy due to their robustness against unpredictable changes of the environment or the mission goal, eliminating the need of intervention of a human operator.
 Legged robot…
 -  13:30 Uhr
Exposé
RH1 A 1.03

Abbildung von situationsabhängigen impliziten Bewertungen mittels Errorpotentials und dessen Verwendung beim Reinforcement Learning

von: Lukas Schloßmüller  (Universität Bremen)
Bei komplexen Reinforcement Learning Anwendungen stößt man auf das Problem eine Reward-Funktion zu definieren, da Reward-Funktionen umfangreiches Fachwissen erfordern oder zu unerwünschten Verhalten führen können. Um dieses Problem zu umgehen, werden Ansätze erforscht, welche den Menschen aktiv in d…
 -  13:00 Uhr
Kolloquium
RH1 A 1.03

Exploiting the SherpaTT Rover Active Suspension System to Enable Optimal Solar Array Orientation and Inclination for Long Traverses in Martian Environment

von: Georges Labrèche  (Luleå University of Technology)
The rover SherpaTT has been deployed in several field experiments where it was put under test within natural and unstructured Mars analogue terrain with respect to general morphology and geology. The rover displayed the ability to cope with natural terrain and to fulfill the task of being an explor…
© DFKI GmbH
zuletzt geändert am 06.09.2024