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

 -  13:00 Uhr
Kolloquium

Qualitative comparison between marker-based and video-based human pose estimation in the context of imitation learning

von: Max Lödige  (Universität Bremen)
The Master's thesis explores whether video-based 3D human pose estimation can serve as an effective alternative to marker-based motion capture for imitation learning from human demonstration. The data will be recorded through a study using multiple modalities, it will be conducted with a custom…
 -  13:00 Uhr
Kolloquium

Graph-based Projected Entangled-Pair State with GPU Acceleration

von: Alexander Krug  (Universität Bremen)
Quantum algorithms promise to provide speedups or even solutions to previously unfeasible problems. As quantum computing matures, benchmarks are needed as a standardized method to evaluate and compare different quantum computing platforms. Hamiltonian evolution serves as a well studied problem setti…
 -  13:00 Uhr
Exposé

Reinforcement Learning for Ground Force Prediction in Unstructured Environments

von: Adrain Danzglock  (Universität Bremen)
In robotic navigation, vision is essential for understanding unstructured environments and enabling effective locomotion. This presentation highlights the significance of vision-driven decision-making for footstep planning in both quadruped and biped robots. Existing methodologies are reviewed, focu…
 -  13:30 Uhr
Exposé

Adaptive Motion Control of Legged Robots via Predictive Force Modeling

von: Kabilan Tamilmani  (Hochschule Bonn-Rhein-Sieg (H-BRS))
Legged robots are well-suited for navigating complex and uneven terrains, but maintaining stable locomotion in such environments remains a critical challenge. Vision-based systems like cameras and LiDAR often face issues such as noise, occlusion, and latency, which can lead to misinterpretation of t…
 -  13:00 Uhr
Exposé

Framework for Diversity Auditing and its Application to Datasets in Human-Robot Interaction

von: Veli Ates  (Fachhochschule Dortmund)
The fairness and reliability of AI systems, particularly in Human-Robot Interaction (HRI), are critically dependent on the demographic diversity of their training data. However, many public datasets used to train these systems have significant, often unquantified, biases, which can lead to models th…
 -  13:00 Uhr
Kolloquium

Contact Implicit Control for the Vertical Hopper

von: Blanka Burchard  (Hochschule Bremen)
Legged robots bear significant potential for robotic applications that deal with diverse and challenging environments where wheeled robots may struggle to move effectively. Nonetheless, the promise of extended mobility comes at the cost of increased complexity due to the inherentlynonlinear dynamics…
 -  13:00 Uhr
Kolloquium

Do different Quantum Optimal Control algorithms have an influence on the fidelity of one-qubit and two-qubit gates on superconducting systems?

von: Adrian Mellentin  (Universität Bremen)
Today’s quantum processor architectures with more than 1000 superconducting qubits are getting closer to the goal of performing complicated calculations. However, the noisy intermediate-scale quantum (NISQ) devices that exist at this time are challenged by phenomena like leakage, cross talking betwe…
 -  14:00 Uhr
Exposé

Guidance and control of AUVs performing hydrobatic maneuvers

von: Lukas Skuras  (TU Dresden)
The recent field of Hydrobatics presents a set of formidable engineering challenges for autonomous underwater vehicles (UAVs). Previous work has shown quite small, high thrust AUVs, capable of performing various maneuvers with optimal control solutions. However, these AUVs are still unfit for tight …
 -  13:30 Uhr
Zwischenbericht

Qualitative comparison between marker-based and video-based human pose estimation in the context of imitation learning

von: Max Lödige  (Universität Bremen)
The Master's thesis explores whether video-based 3D human pose estimation can serve as an effective alternative to marker-based motion capture for imitation learning from human demonstration. The data will be recorded through a study using multiple modalities, it will be conducted with a custom…
 -  13:00 Uhr
Zwischenbericht

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…
© DFKI GmbH
zuletzt geändert am 06.09.2024