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

 -  15:30 Uhr
Kolloquium

Learning State Transition Functions of a Hydraulic Excavator using Data Driven Deep Learning

von: Jayanth Somashekaraiah  (Universität Bremen)
In this thesis, a neural network model is trained to learn the state transition function of a hydraulic excavator arm or a crane using data driven approach. The excavator arm or crane exhibits highly non linear behaviour due to hydraulic coupling between its actuators, non linearities in valves, par…
 -  13:00 Uhr
Kolloquium

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

Enhancement and Evaluation of an AUV's Docking Station Detection with Deep-Learning Based Object-Detection

von: Faraz Ahmad  (Constructor University)
Autonomous docking for underwater vehicles, especially locating the docking station, presents significant challenges for deploying sub-sea resident AUVs in exploration and monitoring tasks. To extend a fiducial marker-based docking station detection,  use of the state-of-the-art object detectio…
 -  14:00 Uhr
Exposé

Meta-Reinforcement Learning for Enhanced Generalization in Robotics

von: Lennart Heinbokel  (Universität Bremen)
This thesis aims to investigate the use of meta-reinforcement learning (meta-RL) to enhance sample efficiency in robotic systems, enabling agents to adapt to unseen tasks with fewer interactions. By employing contextual Markov Decision Processes (cMDPs) to formalize task variability, the study offer…
 -  13:00 Uhr
Kolloquium

Performance Evaluation of Quadratic Programming Solvers for Legged Robots on different Computer Architectures

von: Jakob Middelberg  (Universität Bremen)
In the past decade, the development of dynamic legged robots has gained significant traction and has produced remarkable results. Modern bipeds and quadrupeds are able to traverse difficult terrain while using various gaits and movements like walking, trotting, or jumping. Controlling those robotic …
 -  14:00 Uhr
Kolloquium

Adaptive Footstep Planning for Model Predictive Control of a Quadruped Robot

von: Hannah Isermann  (Universität Bielefeld)
Colloquium
 -  13:00 Uhr
Kolloquium

Real-time Dynamic Gesture Recognition for Human-Robot Collaboration

von: Shefali Dewangan  (Universität Bremen)
The primary goal of the thesis is to enhance human-robot collaboration by addressing the challenge of real-time dynamic gesture recognition. This initiative is a significant part of the ROMATRIS project, funded by THW at the DFKI, and the focus of the thesis is on the identification and real-time in…
 -  14:00 Uhr
Kolloquium

Examining the Potential of VVAD-LRS3: A Comprehensive Cross-Comparison throughout State-of-the-Art VVAD Data Sets

von: Karim Zanaty  (Rushford Business School)
Reliable recognition of people's gestures and mimics is crucial to a natural and intuitive interaction between robots (machines) and humans. Voice Activity Detection (VAD) may play a major role in this context. VAD algorithms detect if the person of interest is currently speaking or not. This can be…
 -  11:15 Uhr
Kolloquium

Data driven modeling and optimal manipulator control

von: Adriano del Río Fernandez  (École Centrale de Nantes)
In the field of optimal control linear systems are generally desirable. In the case of model predictive control the benefit of a linear system representation is significant, as it implies convexity of the optimization problem and global optimality for every solution. In this context very interesting…
 -  13:00 Uhr
Kolloquium

Robot state estimation using synthetic RGB images

von: Vasantakumaar, Naren  (Universität Bremen)
This thesis investigates the state estimation of a multi-joint object such as an excavator, by predicting the joint angles using synthetic RGB images as input. The research is to use RGB camera as an economical alternative to expensive retrofitting sensors for state estimation task of a manipulator.…
© DFKI GmbH
zuletzt geändert am 06.09.2024