Theses and Projects
We offer several Master Theses, Bachelor Theses, as well as projects that can be done as practica (see Lectures). Please see the list below. Please directly contact the supervisor(s) if you are interested in a specific topic. Even if there is currently no open topic that seems to fit your interest, please have a look at the research topics of our potential supervisors (link). If you want to do a thesis in a specific area, directly contact the supervisors working on this topic.
Exceptional Bachelor students can also to apply for Master Thesis topics.
| Titel | Topic | Supervisor | Type | Link |
|---|---|---|---|---|
| Immersive Vision-Based Teleoperation System via Virtual Reality | Robotics, Computer Vision, Teleoperation | Master Thesis | ||
| Learning Diverse Behaviors: Diffusion Meets RL | Reinforcement Learning, Diffusion | Mayank Mittal (ETHZ/Nvidia), Xiaogang Jia, Aleksandar Taranovic |
Master Thesis | |
| Reinforcement Learning for Multiple-Embodiment Grasping | Reinforcement Learning, Diffusion, Grasping | Roman Freiberg(Bosch) |
Master Thesis | |
| Foundational Vision-Trajectory Transformer for Industrial Robot Skills | Foundation Models, Robotics | Master Thesis, Research Project | ||
| Amortized Variational Inference for Bayesian Meta-Learning using Langevin Diffusions | Variational Inference | Master Thesis | ||
| Datasets for Molecular Geometry Generation from Energy Potentials using Variational Inference | Variational Inference | Master Thesis | ||
| Diffusion Based Imitation Learning for Robot Manipulation Tasks | Imitation Learning | Master Thesis |
| Titel | Topic | Supervisor | Student | Typ | Link |
|---|---|---|---|---|---|
| Variational Learning Of Multi Time Scale World Models | Variational Inference, World Models | Simon Schönberger | Master Thesis | ||
| Long Range Time-series Forecasting With Sequence to Sequence Models | Time Series | Severin Mahler | Bachelor Thesis | ||
| Capturing Long-Range-Dependencies in sequence to sequence models | Sequence Modelling | Salem Gholam Zadeh, Vaisakh Shaj |
Jannik Bach | Bachelor Thesis | |
| Deep Reinforcement Learning with Sequenced Movement Primitives in Robot Manipulation tasks | Reinforcement learning | Ge Li, Hongyi Zhou |
Dong Tian | Master Thesis | |
| Combining Reinforcement Learning and Diffusions via Weighted Maximum Likelihood Estimation | Reinforcement Learning | Batın Muslu | Master Thesis | ||
| Learning Complex Manipulations of Cluttered Scenes with Deep RL | Reinforcement Learning | Hanna Ziesche, Vien Ngo, Gerhard Neumann |
Master Thesis | ||
| Model-based Reinforcement Learning of Diverse Skills | Reinforcement Learning | Onur Celik, Philipp Becker |
Erwin Müller | Master Thesis | |
| Multi-step Deep Reinforcement Learning in High-Dimensional Action Spaces | Reinforcement Learning | Hanna Ziesche |
Bachelor Thesis | ||
| Reinforcement Learning of Diverse Skills | Reinforcement Learning | Onur Celik |
Hussam Alafandi | Master Thesis | |
| Solving Real-World Robot Manipulation Tasks with Deep Reinforcement Learning | Reinforcement Learning | Hongyi Zhou, Ge Li |
Max Nagy | Master Thesis | |
| State Space Models vs Transformers for Continuous Control | Offline RL, Sequence Modeling | Enrico Krohmer | Praxis der Forschung | ||
| Distributed Multi-Agent RL for Routing Optimization | Multi-Agent Reinforcement Learning | Niklas Kaspareit | Master Thesis | ||
| Enhanced Probabilistic Dynamic Movement Primitives | Movement Primitives | Ge Li, Hongyi Zhou |
Weiran Liao | Master Thesis | |
| Imitation Learning for Soft Objects Manipulation | Imitation Learning, Soft Manipulation | Kuan Yang | Master Thesis | ||
| Multi-modal Imitation learning for Complex Robot Manipulation | Imitation Learning | Xiaogang Jia |
Pascal Siekiera | Bachelor Thesis | |
| Role of Hierarchy in World Models for Long-Term Prediction | Hierarchical Models, World Models | Shuheng Zhang | Master Thesis | ||
| Explainable Reinforcement Learning using Graph Neural Networks | Graph Neural Networks, Reinforcement Learning | Niklas Freymuth |
Andreas Maier | Master Thesis | |
| Swarm RL for Solving the Inventory Routing Problem in Cooperation with an AI-Startup | Graph Neural Networks, Reinforcement Learning | Philipp Andris | Master Thesis |
| Titel | Topic | Supervisor | Student | Type | Link |
|---|---|---|---|---|---|
| Improving the Rollout stability of Graph-Network-based Simulators | Graph Neural Networks, Dynamics Modeling | Rodi Düger | Bachelor Thesis | ||
| Domain Randomization in Simulated Contact Manipulation Tasks | Reinforcement Learning, Simulation | Tim Alexander Drozniak | Bachelor Thesis | ||
| Investigating the Amortization Gap in Variational Inference for State Space Models | Variational Inference | Philipp Becker |
Yasin Tatar | Master Thesis | |
| Model-Based RL for Challenging Manipulation Tasks | Model-Based Reinforcement Learning | Philipp Becker |
Sven Hillenkötter | Master Thesis | |
| Diffusion-based Imitation Learning for Contact Rich Manipulation | Imitation Learning | Ralf Herp | Bachelor Thesis | ||
| Adversarial Imitation Learning with Preferences and Movement Primitives | Imitation Learning, Movement Primitives | Aleksandar Taranovic, Hongyi Zhou |
Aaron Eisermann | Master Thesis | |
| Variational Swarm Reinforcement Learning for Predictive Models of Deformable Objects | Graph Neural Networks, Dynamics Modeling | Niklas Freymuth, Rika Antonova (Stanford) |
Simon Reisch | Master Thesis | |
| Spatial Credit Assignment for Swarm Reinforcement Learning | Multi-Agent Reinforcement Learning | Niklas Freymuth |
Tom Kaminski, Julian Vu | Praxis der Forschung | |
| Graph Diffusion for Adaptive Mesh Refinement | Graph Neural Networks, Diffusion | Niklas Freymuth, Philipp Dahlinger |
Le Yang | Master Thesis/Research Project | |
| Recurrent Kalman Graph Network Simulators | Graph Neural Networks, Dynamics Modeling | Niklas Freymuth, Philipp Dahlinger, Paul Scheikl (HERA) |
Cem Oezcan | MSc Thesis / Research Project | |
| Instructing Robots using Verbal Feedback | Imitation Learning, Interactive Learning | Aleksandar Taranovic |
Han Liu | Master Thesis | |
| Learning Adaptive Mesh Refinement Strategies from Human Feedback | Graph Neural Networks, Imitation Learning | Niklas Freymuth, Aleksandar Taranovic |
David Petri | Master Thesis | |
| Transformers for Time Series Prediction | Transformers, Time Series | Saleh Gholam Zadeh, Vaisakh Shaj |
Nicolas Braun | Bachelor Thesis | |
| Generation of Industrial Robot Programs Using Large Language Models | Large Language Models | Aleksandar Taranovic |
Urs Keßner | Bachelor Thesis | |
| Reinforcement Learning with Human Preferences | Preference Learning | Aleksandar Taranovic |
Jens Bosch | Bachelor Thesis | |
| All You Need is State-Dependent Deep Reinforcement Learning | Reinforcement Learning | Fabian Otto, Onur Celik |
Dominik Roth | Bachelor Thesis | |
| Reinforcement Learning for Robot Manipulation Tasks | Reinforcement Learning | Onur Celik |
Jan Küblbeck | Bachelor Thesis | |
| Hybrid Models for Inverse Dynamics Modeling | Dynamic Model Learning, Recurrent Neural Networks | Moritz Reuss |
Noah Petry | Bachelor Thesis | |
| Gradient-based Episodic RL using Differentiable Physics Simulators | Reinforcement Learning | Maximillian Hüttenreich |
Felix Köhler | Master Thesis | |
| Human-Robot Collaboration using Behavioral Cloning and Teleoperation | Reinforcement Learning | Philipp Dahlinger |
Simon Essig | MSc Thesis / BSc Thesis / Research Project | |
| 6-D Pose Estimation and Visualization in an Augmented Reality device | Object Detection | Nicolas Schreiber |
Niklas Baier | Bachelor Thesis | |
| Continual Deep Reinforcement Learning In Non Stationary Situations | Multi Task Reinforcement Learning | Vaisakh Shaj |
Stefan Geyer | Master Thesis | |
| Stable Optimization of Gaussian Likelihoods | Optimization | Fabian Otto, Michael Volpp |
Denis Megerle | Master Thesis | |
| End-to-End Differentiable Grasping Network | Grasping and Manipulation | Ngo Anh Vien |
Philipp Blättner | MSc Thesis / BSc Thesis / Research Project | |
| Geometry-based Robot Motion Learning | Reinforcement Learning | Gerhard Neumann, Hadi Beik-Mohammadi, Leonel Rozo |
Jiechao Zhang | Master Thesis | |
| Inverse Dynamics Learning for Pneumatic Muscular Robots | Dynamics Learning; Recurrent Networks | Vaisakh Shaj |
Rohit Sonker | Research Internship | |
| Grasp Adaptation for Robotic Manipulation | Grasping and Manipulation | Gerhard Neumann, Vien Ngo, Hanna Ziesche |
Jun Wang | MSc Thesis, Research Project | |
| Improving Uncertainty Estimation for Model-Based Reinforcement Learning | Model-Based Reinforcement Learning | Philipp Becker |
Aina Galofre | Master Thesis | |
| Robot Online Motion Planning with Episode-based Reinforcement Learning | Reinforcement Learning | Ge Li |
Hongyi Zhou | Master Thesis | |
| Autonomous Partitioning of Heterogeneous Swarm Systems | Multi-Agent Reinforcement Learning | Niklas Freymuth |
Thomas Mohr | Bachelor Thesis | |
| Reinforcement Learning for Deformable Objects | Reinforcement Learning | Niklas Freymuth, Onur Celik, Paul Scheikl (HERA) |
Alissa Müller | Master Thesis | |
| Swarm Reinforcement Learning in Limited Visibility with Graph Neural Networks | Reinforcement Learning | Niklas Freymuth, Maximilian Hüttenrauch |
Lyubomira Dimitrova | Master Thesis | |
| Episodic Versatile Imitation Learning via Geometric Features Matching | Imitation Learning | Nicolas Schreiber, Niklas Freymuth |
Felix Bächle | Bachelor Thesis | |
| Variational Bayesian Deep Learning for Model Predictive Control | Bayesian Deep Learning | Philipp Becker, Michael Volpp |
Florian Seligmann | MSc Thesis / BSc Thesis / Research Project | |
| Tackling Offline Reinforcement Learning by Model Learning | Offline Reinforcement Learning | Philipp Becker |
Stefan Krieg | Bachelor Thesis | |
| Self-Supervised Model-Based Reinforcement Learning under Partial Observability | Model-Based Reinforcement Learning | Philipp Becker |
Sebastian Markgraf | Master Thesis | |
| Physical Simulation from Observation using Graph Neural Networks | Graph Neural Networks | Niklas Freymuth, Paul Scheikl (HERA) |
Jonas Linkerhägner | Master Thesis | |
| Representation-Invariant Latent Spaces for Robot Video Learning | Meta-Learning | Niklas Freymuth |
Serge Thilges | Bachelor Thesis | |
| Information Theoretic Trust Regions for Gradient Descent | Imitation Learning, Trust-Region Optimization | Philipp Becker, Maximilian Hüttenrauch |
Philipp Dahlinger | Master Thesis | |
| Learning to Pick specific Objects in a Heap | Grasping and Manipulation | Gerhard Neumann, Vien Ngo, Hanna Ziesche |
Oussama Zenkri | Master Thesis | |
| Learning to Assemble using 6D Pose Estimation for Insertion Tasks | Grasping and Manipulation | Gerhard Neumann, Hanna Ziesche, Vien Ngo |
Artur Eckard | Master Thesis | |
| Long-Term Prediction for Pushing and Grasping with Deep Reinforcement Learning | Grasping and Manipulation | Gerhard Neumann, Hanna Ziesche, Vien Ngo |
Mohammed Abdalqader | Master Thesis | |
| Efficient Gradient-Based Variational Inference with GMMs | Variational Inference | Oleg Arenz |
Zihan Ye | Master Thesis | |
| Trajectory Segmentation for Robot Manipulation Datasets | Grasping and Manipulation | Ge Li |
Xin Tian | Bachelor Thesis | |
| Imitation Learning for Versatile Robot Manipulation | Imitation Learning | Philipp Becker, Onur Celik |
Maximilian Li | Master Thesis | |
| Sample Efficient Episodic Policy Search | Reinforcement Learning | Onur Celik |
Marcel Sandermann | Masterarbeit | |
| Neural Process For Player Classification in Computer Games | Meta Learning, Few Shot Classification | Vaisakh Shaj |
Martin Herault | Master Thesis (External) | |
| Probabilistic Forget Gates For Changing Dynamics | Time Series Modelling, Meta Learning | Vaisakh Shaj |
Christof Beck | Bachelor Thesis | |
| RippleNet: A remote message passing method for Graph Neural Networks | Deep Geometric Meshing | Niklas Freymuth |
Ruoheng Ma | Master Thesis | |
| Swarm Reinforcement Learning with Graph Neural Networks | Reinforcement Learning | Niklas Freymuth |
Christian Burmeister | Bachelor Thesis | |
| Improved Trust Regions for Adversarial Imitation Learning | Imitation Learning, Trust-Region Optimization | Philipp Becker, Fabian Otto, Hanna Ziesche |
Ahmed Agha | Master Thesis | |
| Bayesian Aggregation for Deep Reinforcement Learning in Swarms | Deep Reinforcement Learning/Multi-Agent Learning | Maximilian Hüttenrauch |
Robin Rüde | Master Thesis | |
| Data Augmentation for Neural Processes | Meta-Learning | Michael Volpp |
Anushka Vashishtha | External Master Thesis with Robert Bosch GmbH | |
| Kalman Mixture Networks | Time Series Modeling | Chen Qui, Maja Rudolf, Philipp Becker, Vaisakh Shaj |
Giao Nguyen Quynh | External Master Thesis with Robert Bosch GmbH | |
| Residual Model Learning using Action-Conditional Recurrent Kalman Networks | Dynamics Modeling | Niels van Duijkeren, Robert Krug, Vaisakh Shaj, Philipp Becker |
Moritz Reuss | External Master Thesis with Robert Bosch GmbH | |
| Contextual Policy Search for Robot Table Tennis | Reinforcement Learning | Ge Li |
Dongzhuoran Zhou | Master Thesis | |
| Intrinsically Motivated Deep Reinforcement Learning | Deep Reinforcement Learning, Dynamics Learning in latent space | Vaisakh Shaj |
Andreas Boltres | Master Thesis | |
| Recursive Surrogate-Modeling for Stochastic Search*DIPLOMARBEIT* | Stochastic Search / Regression | Maximilian Hüttenrauch |
Klaus Philipp Theyssen | Bachelor Thesis | |
| Actor-Critic Methods for Robotics | Reinforcement Learning | Philipp Becker, Onur Celik |
Roman Freiberg | Bachelor Thesis | |
| Deep Reinforcement Learning under Partial Observability using Kalman Filtering | Reinforcement Learning | Philipp Becker |
Carmen Eitel | Master Thesis | |
| Deep Reinforcement Learning of Versatile Behavior | Reinforcement Learning | Onur Celik |
Dhimiter Pikuli | Bachelor Thesis | |
| Inverse Reinforcement Learning for Highly-Versatile Behavior | Inverse Reinforcement Learning | Philipp Becker |
Niklas Freymuth | Master Thesis |