We are always searching for good students and have many good opportunities. However, we are also open to suggestions by students as long as they touch the topics relevant to intelligent systems. Click here for Offered Topics! Note that these Theses are only for TU Darmstadt students who can directly contact Team Members for more information. For exceptional external students, we offer Theses as well, these need to contact Jan Peters by
peters@ias.tu-darmstadt.de first. Here is the list of currently ongoing theses:
| Student | Advisor | Type | Topic |
|---|
| Jan Mackensen | Dorothea Koert | M.Sc. | A Human-Centered Approach for AI-Aided Anomaly Detection in Time Series |
| Marleen Sinsel | Dorothea Koert | B.Sc. | AI-Aided Pointing Gesture Detection for Human-Robot-Interaction |
| Sabin Grube | Snehal Jauhri | M.Sc. | Combining Deep Reinforcement Learning and 3D Vision for Dual-arm Robotic Tasks |
| Sebastian Müller | Kai Streiling (FB3), Max Stasica (FB3), Jan Peters | M.Sc. | Visual illusions in sensorimotor control – a reinforcement learning study |
| Janik Schöpper | Dorothea Koert | B.Sc. | Situational Adaptive Autonomy in a Shared Workspace |
| Zeyuan Sun | Rupert Mitchell, Jan Peters, Heinz Köppl | M.Sc. | Self Expanding Neural Networks for Reinforcement Learning |
| Marcel Mittenbühler | Ahmed Hendawy, Carlo D'Eramo, Georgia Chalvatzaki | M.Sc. | Lifelong Robot Learning with Pretrained Multimodal Models |
| Denis Andrić | An Thai Le, Georgia Chalvatzaki | M.Sc. | Learning Symplectic Manifold Of Dynamical Systems |
| Joshua Johannson | Oleg Arenz | M.Sc. | Bipedal Locomotion on Bolt |
| Hannah Wieland | Dorothea Koert | M.Sc. | Situational Autonomy Adaptation in Human Robot Interaction |
| Lu Liu | Michael Drolet from IAS, Oleg Arenz from IAS | M.Sc. | Learning Latent Embeddings for Locomotion |
| Lorenzo Tozzi | Davide Tateo, Carlo D'Eramo | M.Sc. | Dynamic Tiles for Deep Reinforcement Learning |
| Haoran Ding | Jan Peters and Leonel Rozo | M.Sc. | Safe Flow-based Robot Motion Policies |
| Philip Hirschle | Andras Gabor Kupcsik (BOSCH), Anh Vien Ngo (BOSCH), Jan Peters | Honor's Thesis | Scalable foundation model robot policy |
| Martin Steinborn | Suman Pal from IAS | M.Sc. | Multi-Person Pose Tracking Using Dynamically Gated Similarities |
| Florian Vogt | Daniel Palenicek | M.Sc. | Investigating bottlenecks of CrossQ's sample efficiency |
| Tim Henze | Jan Peters from IAS, Bastian Bischoff from Bosch | M.Sc. | Enhancng Multi-Modal Foundation Model Training via Image Captioning |
| Rolf Gattung | Tim Schneider from IAS, Kai Ploeger from IAS, Niklas Funk from IAS | M.Sc. | Tactile Pole Balancing |
| Bjarne Freund | Davide Tateo | B.Sc. | Isaac sim integration for Mushroom RL |
| Paolo Magliano | Davide Tateo from IAS, Raffaello Camoriano from PoliTo | M.Sc. | SafeLoco: Safe Reinforcement Learning for Robotic Locomotion |
| Zongwei Zhang | Michael Drolet from IAS, Firas Al-Hafez from IAS, Sebastian Hirt from TU Darmstadt, Oleg Arenz from IAS | M.Sc. | Reinforcement Learning for Exoskeleton Control |
| Marius Zöller | Kay Hansel and An Thai Le from IAS | M.Sc. | Enhancing Smoothness in Policy Blending with Gaussian Processes |
| Yi Li | Alexandre Chapin, Liming Chen, Emmanuel Dellandrea from LIRIS, Tim Schneider, Alap Kshirsagar | M.Sc. | Self-supervised learning of a visual object-centric representation for robotic manipulation |
| Jiahui Shi | Junning Huang | M.Sc. | Hybrid Force-Impedance Control for Robot Manipulators |
| Haris Cavkic | Suman Pal from IAS, Aiswarya Menon from IAS | M.Sc. | Flow Matching for Industrial Motion Planning: Learning Trajectory Distributions for Real-World Applications |
| Vojin Vlačić | Cristiana Mirandade Farias, Alap Kshirsagar, Tim Schneider | M.Sc. | Active Exploration for Bimanual Grasping |
| Khrystyna Rud | Alap Kshirsagar, Oliver Hahn | M.Sc. | Self-supervised Learning for Robotic Visuomotor Skills |
| Philipp Jahr | Joao Carvalho | M.Sc. | Residual SVF |
| Philip Hirschle | Jan Peters from IAS, Andras Kubcik from Bosch AI | M.Sc. | Scalable foundation model robot policy |
| Jonathan Lippert | Kai Ploeger, Alap Kshirsagar, Abir Chowdhury | M.Sc. | Human-Robot Partner Juggling |
| Tim Faust | TheoVincent from IAS | M.Sc. | Eau De Soft Actor-Critic: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning |
| Christian Scherer | Daniel Palenicek, Theo Gruner, Joe Watson from University of Oxford | B.Sc. | Coherent Soft Imitation Learning for Vision-Language Action Models |
| e.g., Sam Sample | e.g., Jan Peters from IAS, Tomas Dorf from ETIT | B.Sc. | e.g., Reinforcement Learning in Gold Fish Water Babbling |
| Sam Sample | e.g., Jan Peters from IAS, Tomas Dorf from ETIT | B.Sc. | e.g., Reinforcement Learning in Gold Fish Water Babbling |
| Henrik Metternich | Ahmed Hendawy | M.Sc. | Value-based Reinforcement Learning via Mode Connectivity |
| Magnus Dierking | An Thai Le, Joao Carvalho | M.Sc. | Model Tensor Planning |
| Topic | Students | Advisor |
|---|
| Robotic Knot Untangling | Tim Missal, Tom Roehner, Gina Leonie Wigginghaus | Berk Gueler from IAS |
| Long Horizon Shared Autonomy | Zhihao Han, Yuchao Wu, Ahmad Hamad | Berk Gueler from IAS |
| Controlling Humanoids by Natural Language | Ruixuan Ge, Khaled Sadeq | Claudius Kienle, Oleg Arenz |
| Motion Planning on Constraint Manifolds | Matej Zoltan Suvert, Philipp Schönfeld, Hangjian Qian | Cristiana Mirandade Farias, Kay Pompetzki |
| Hierarchical Semantic Segmentation of Human Demonstration Data | Daniel Neykov, David Lang , David Stebich, Paul Knaußt | Cristiana Mirandade Farias, Kay Pompetzki |
| Investigating neural network updates in Off-Policy Deep Reinforcement Learning | Habib Maraqten | Theo Vincent |
| Large-scale Procedural Robot Generation | Nurhak Yalcin, Lukas Müller | Nico Bohlinger |
