Ongoing Theses

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 first. Here is the list of currently ongoing theses:

Benedikt HahnerJoe WatsonM.Sc.Sim2GP: Bayesian Dynamics Models via Differentiable Physics
Jan MackensenDorothea KoertM.Sc.A Human-Centered Approach for AI-Aided Anomaly Detection in Time Series
Zhiyuan HuJoe Watson, Oleg ArenzM.Sc.An Inference-based Approach to Reinforcement and Imitation Learning with Diverse Demonstration Data
Marleen SinselDorothea KoertB.Sc.AI-Aided Pointing Gesture Detection for Human-Robot-Interaction
Ruiyong PiVignesh Prasad, Sven SchultzeM.Sc.Mapless Social Robot Navigation
Sabin GrubeSnehal JauhriM.Sc.Combining Deep Reinforcement Learning and 3D Vision for Dual-arm Robotic Tasks
Han GaoGeorgia ChalvatzakiM.Sc.AffordanceParts: Learning Explainable Object Parts with Invertible Neural Networks
Fabian HahneVignesh PrasadB.Sc.Learning Human-Robot Interaction with Gaussian Processes HSMMs
Felix NonnengießerAlap Kshirsagar, Boris Belousov, Prof. Gemma RoigM.Sc.Visuotactile Sensing for In-Hand Object Pose Tracking
Arne BacksteinVignesh PrasadB.Sc.Temporal Latent Space Modelling using Hidden Markov Models
Sebastian MüllerKai Streiling (FB3), Max Stasica (FB3), Jan PetersM.Sc.Visual illusions in sensorimotor control – a reinforcement learning study
Janik SchöpperDorothea KoertB.Sc.Situational Adaptive Autonomy in a Shared Workspace
Zeyuan SunRupert Mitchell, Jan Peters, Heinz KöpplM.Sc.Self Expanding Neural Networks for Reinforcement Learning
Dominik HorstkötterTim Schneider, Boris Belousov, Alap KshirsagarB.Sc.Learning to Assemble SL-Block Structures from Vision and Touch
Hannes MittwollenSuman Pal, Jan HämmelmannB.Sc.Detection and 6D-pose estimation of objects using their CAD-Models
Marcel MittenbühlerAhmed Hendawy, Carlo D'Eramo, Georgia ChalvatzakiM.Sc.Lifelong Robot Learning with Pretrained Multimodal Models
Noah FarrDavide Tateo, Georgia ChalvatzakiB.Sc.Designing reward functions for robotic tasks
Philipp Vincent EbertKai PloegerB.Sc.Learning Latent Dynamics for Control
Denis AndrićAn Thai Le, Georgia ChalvatzakiM.Sc.Learning Symplectic Manifold Of Dynamical Systems
Julian RauNiklas FunkM.Sc.Scaling learned, graph-based assembly policies
Joshua JohannsonOleg ArenzM.Sc.Bipedal Locomotion on Bolt
Duc Huy NguyenTim Schneider, Boris Belousov, Alap KshirsagarB.Sc.Simulation of Vision-Based Tactile Sensors
Marius GlaserPaul Jansonnie, Oleg ArenzB.Sc.Real2Sim for Play-Doh Manipulation
Jonas RingdorfDavid Rother from IASM.Sc.Mixed-Motive Multi-Agent Reinforcement Learning
Hannah WielandDorothea KoertM.Sc.Situational Autonomy Adaptation in Human Robot Interaction
Frederik HellerGuillaume Duret, Tim Schneider, Alap KshirsagarB.Sc.Reinforcement Learning for Deformable Object Manipulation
Yasemin GoeksuAlap Kshirsagar, Oliver HahnM.Sc.Self-supervised Learning for Robotic Visuomotor Skills
Cheng QianJulenUrainDeJesusM.Sc.Learning Dexterous Manipulation from Videos
Marc SaghirFelix KaiserB.Sc.Ensemble Methods for Visual Anomaly Detection in Manufacturing Settings
Qiao SunJoao Carvalho from IAS, An Thai Le from IASM.Sc.Geometry-Aware Diffusion Models for Robotics
Lu LiuMichael Drolet from IAS, Oleg Arenz from IASM.Sc.Learning Latent Embeddings for Locomotion
Patrick SiebkeAditya Bhatt and Maximilian TölleM.Sc.Analysis of Quasimetric Reinforcement Learning
Esteban CosseratTim Schneider from IAS, Kay Hansel from IAS, Guillaume Duret from ECLM.Sc.Refining 6D pose with tactile sensor
Lorenzo TozziDavide Tateo, Carlo D'EramoM.Sc.Dynamic Tiles for Deep Reinforcement Learning
Tristan TischAryaman Reddi from LiteRLM.Sc.The Power of Friendship: Dynamic Multi-Agent Reward Sharing
Daniel DennertDaniel PalenicekB.Sc.Diminishing Return of Value Expansion Methods in Offline Model-Based Reinforcement Learning
Faran AhmadDaniel PalenicekB.Sc.Diminishing Return of Value Expansion Methods in Discrete Model-Based Reinforcement Learning
Jonathan KinzelNico Bohlinger, Daniel PalenicekM.Sc.On-robot Deep Reinforcement Learning for Quadruped Locomotion
Fabian DamkenExternal Thesis at Vector InstituteM.Sc.Learning Admissible and Monotone Heuristics for A*
Haoran DingJan Peters and Leonel RozoM.Sc.Safe Flow-based Robot Motion Policies
Philip HirschleAndras Gabor Kupcsik (BOSCH), Anh Vien Ngo (BOSCH), Jan PetersHonor's ThesisScalable foundation model robot policy
Junyi ChenAlap KshirsagarB.Sc.Object Hardness Classification Using a Vision-Based Tactile Sensor
Martin SteinbornSuman Pal from IASM.Sc.Multi-Person Pose Tracking Using Dynamically Gated Similarities
Max SiebenbornAditya Bhatt, Maximilian Tölle and Boris BelousovM.Sc.Distilling Motor Skills To A Humanoid Robot Through Imitation Learning
Florian VogtDaniel PalenicekM.Sc.Investigating bottlenecks of CrossQ's sample efficiency
Tim HenzeJan Peters from IAS, Bastian Bischoff from BoschM.Sc.Enhancng Multi-Modal Foundation Model Training via Image Captioning

Ongoing IP Projects

Visuotactile Shear Force EstimationErik Helmut, Luca DziarskiNiklas Funk, Boris Belousov
AI Olympics with RealAIGymTim Faust, Erfan Aghadavoodi, Habib MaraqtenBoris Belousov
Solving Insertion Tasks with RL in the Real WorldNick Striebel,Adriaan MulderJoao Carvalho
Hands-on ControlErik Gattung, Noah BeckerTim Schneider, Kay Hansel
Student-Teacher Learning for simulated QuadrupedsKeagan Holmes, Oliver Griess, Oliver GreinNico Bohlinger
Reinforcement Learning for Contact Rich ManipulationDustin GoreckiAiswarya Menon, Arjun Datta, Suman Pal
Autonomous Gearbox Assembly by Assembly by DisassemblyJonas Chaselon, Julius ThorwarthAiswarya Menon, Felix Kaiser, Arjun Datta
Learning to Assemble from Instruction ManualErik Rothenbacker, Leon De Andrade, Simon SchmalfussAiswarya Menon,Vignesh Prasad,Felix Kaiser,Arjun Datta
Black-box System Identification of the Air Hockey TableShihao Li, Yu WangTheo Gruner, Puze Liu
Unveiling the Unseen: Tactile Perception and Reinforcement Learning in the Real WorldAlina Böhm, Inga Pfenning, Janis LenzDaniel Palenicek, Theo Gruner, Tim Schneider
XXX: eXploring X-Embodiment with RT-XDaniel Dennert, Christian Scherer, Faran AhmadDaniel Palenicek, Theo Gruner, Tim Schneider, Maximilian Tölle
Kinodynamic Neural Planner for Robot Air HockeyNiclas MertenPuze Liu
XXX: eXploring X-Embodiment with RT-XTristan JacobsDaniel Palenicek, Theo Gruner, Tim Schneider, Maximilian Tölle
Reactive Human-to-Robot HandoversFabian HahneVignesh Prasad, Alap Kshirsagar
Analysis of multimodal goal prompts for robot controlMax SiebenbornAditya Bhatt, Maximilian Tölle
Q-Ensembles as a Multi-Armed BanditHenrik MetternichAhmed Hendawy, Carlo D'Eramo
Control Barrier Functions for Assistive TeleoperationYihui Huang,Yuanzheng SunBerk Gueler, Kay Hansel
Hands-on Control: Tactile Feedback for Remote Robot AssemblyNoah Becker,Chunyao Zhu,Kyrylo SovailoTim Schneider and Kay Hansel from IAS
Learning Torque Control for QuadrupedsDaniel Schmidt, Lina GaumannNico Bohlinger
Robot Learning for Dynamic Motor SkillsMarcus Kornamann, Qimeng HeKai Ploeger, Alap Kshirsagar