Disclaimer: If you want to propose any thesis topic that falls in the general area of the listed here, contact Prof. Chalvatzaki directly, and discuss a topic that suits your interests.
We offer the following current topics directly for Bachelor and Master students at TU Darmstadt.
Note that we cannot provide funding for any of these theses projects.
We highly recommend that you do robotics and machine learning lectures (Robot Learning, Statistical Machine Learning, Reinforcement Learning, Grundlagen der Robotik, Probabilistic Graphical Models, and/or Deep Learning) before applying for a thesis. Even more important to us is that you followed our Intelligent Robotic Manipulation Seminar and our Project Lab, or that you followed both Robot Learning: Integrated Project, Part 1 (Literature Review and Simulation Studies) and Part 2 (Evaluation and Submission to a Conference), before doing a thesis with us.
When you contact the advisor, it would be nice if you could mention (1) WHY you are interested in the topic (dreams, parts of the problem, etc.), and (2) WHAT makes you special for the projects (e.g., class work, project experience, special programming or math skills, prior work, etc.). Supplementary materials (CV, grades, etc.) are highly appreciated. Of course, such materials are not mandatory, but they help the advisor to see whether the topic is too easy, just about right, or too hard for you.
FOR FB16+FB18 STUDENTS: Students from other departments at TU Darmstadt (e.g., ME, EE, IST), you need an additional formal supervisor who officially issues the topic. Please do not try to arrange your home dept advisor by yourself but let the supervisor contact that person instead!
Offered Topics :
☑ Title: The Limits of SE(3)-Equivariant Imitation Learning for Robot Manipulation
Scope: Master Thesis
Start Date: ASAP
Advisors: Max Siebenborn, Georgia Chalvatzaki
Detailed Proposal: SE(3)-Equivariant Manipulation Thesis Call
Robot grasping differently rotated objects by jointly rotating end-effector. Task from [4]
Equivariant policies [1,2,3] are increasingly used in robot manipulation because they respect geometric structure. Equivariance means that if the input (observations) is transformed—like rotated or translated—the output (robot actions) changes in the same predictable way. However, in real robots, factors like joint limits, collisions, end-effector design, and task goals can break this symmetry. For example, in certain scenarios, rotating an object may require a different grasp rather than just rotating the hand. In this thesis, you will explore when SE(3)-equivariance is useful—and when it is not—by pushing the limits of equivariant policies!
Research Questions
- When is SE(3)-equivariance a valid prior for manipulation?
- What assumptions or constraints cause symmetry to break?
- How can we use equivariance as a prior when full equivariance is broken, e.g., via soft priors?
What You Will Do
- Study equivariant imitation learning and reproduce existing results.
- Implement tasks that stress manipulability, collisions, and kinematic limits. Analyze symmetry-breaking conditions.
- Optionally, test on a real Tiago++ robot or develop architectures for symmetry-breaking cases.
Requirements
- Background in robotics and robot learning
- Strong Python and PyTorch skills
- Bonus: robot simulation experience (MuJoCo), imitation learning
- Bonus: knowledge in equivariant learning / group theory / differential geometry
Opportunities
Equivariance is a powerful prior that can improve robot manipulation, yet is rarely applied in practice. Your thesis could help bridge this gap. You will be given the opportunity to work with real robots and publish your results.
Interested?
Send a short (informal) motivation, CV, and grade sheets to: max.siebenborn@tu-darmstadt.de
References
[1] Wang, Dian, et al. “Equivariant diffusion policy.” 8th Annual Conference on Robot Learning, 2024.
[2] Tie, Chenrui, et al. “Et-seed: Efficient trajectory-level se (3) equivariant diffusion policy.” arXiv preprint arXiv:2411.03990 (2024).
[3] Yang, Jingyun, et al. “Equibot: Sim (3)-equivariant diffusion policy for generalizable and data efficient learning.” 8th Annual Conference on Robot Learning, 2024.
[4] Mandlekar, Ajay, et al. “What matters in learning from offline human demonstrations for robot manipulation.” arXiv preprint arXiv:2108.03298 (2021).
☑ Title: Action Chunking Transformers for Bimanual Primitive Coordination
Scope: Master Thesis
Advisors: Kumar Manas
The Action Chunking Transformer (ACT) architecture, proven successful in the ALOHA bimanual manipulation system, represents a breakthrough in learning complex coordinated movements. This thesis extends ACT to operate at the primitive level rather than raw actions, creating a hierarchical framework that combines the expressiveness of modern imitation learning with the interpretability of skill-based robotics.
This thesis targets real-world scenarios such as: coordinating dual robot arms to
restock supermarket shelves and handle airport baggage efficiently and safely.
Research Goal & Expected Outcomes
Primary Objective: Adapt the ACT architecture to predict chunks of manipulation primitives instead of raw joint actions, enabling temporal abstraction while preserving bimanual coordination capabilities. The modified ACT will use a CVAE (Conditional VAE) latent space to capture multimodal coordination strategies: when both arms should move together vs. sequentially, which arm leads in asymmetric tasks, and how to recover from perturbations.
Idea: Primitive chunking naturally provides temporal abstraction, where each chunk represents a coherent manipulation phase (e.g., approach-grasp-lift sequence) rather than arbitrary action windows.
Requirements:
Essential: Python/PyTorch skills, familiarity with VAE/CVAE architectures, Transformer implementation experience, understanding of imitation learning.
Preferred / willingness: knowledge of behavior cloning methods, real robot experiments, ROS/ROS2
We Provide: Real bimanual robot system, demonstration dataset of operations, computational resources, mentorship, project collaboration and opportunity to publish in top tier conferences.
Further Details are available here.
Apply:
Write an email to kumar.manas[at]tu-darmstadt.de. Please shortly state your motivation and experience (courses, projects) and if available, transcript of records.
☑ Title: Transformer-based Primitive Sequencing for Bimanual Robot Manipulation
Scope: Master Thesis
Advisors: Kumar Manas
Bimanual robot manipulation represents one of the most challenging frontiers in robotics, enabling robots to perform complex tasks that require coordinated dual-arm movements. This thesis focuses on developing intelligent bimanual robots for real-world applications including supermarket shelf restocking and airport baggage handling.
key research question: Given a library of manipulation primitives (e.g. reach, grasp, lift, place, push), how can a robot learn WHEN to execute WHICH primitive with WHICH arm, and HOW to coordinate both arms from human demonstrations?
Research Goal & Expected Outcomes:
Primary Objective: Develop a Transformer-based sequence model that learns to predict and coordinate bimanual manipulation primitive sequences from human demonstration data collected in real supermarket environments. The framework will take current robot state and task context as input, and output: (1) next primitive ID for each arm, (2) primitive parameters (target poses, forces), (3) execution duration, and (4) inter-arm synchronization signals.
Key Ideas: Cross-attention mechanism between left and right arm token streams to implicitly learn coordination patterns without explicit programming.
Requirements:
Essential: Python programming, PyTorch experience, understanding of Transformer architectures, basics of robot kinematics
Preferred / willingness: Experience with imitation learning, ROS/ROS2, robot experiments, sequence modeling (NLP or time-series).
We Provide: Real bimanual robot system, demonstration dataset of operations, computational resources, mentorship, project collaboration and opportunity to publish in top tier conferences.
Further Details are available here.
Apply:
Write an email to kumar.manas[at]tu-darmstadt.de. Please shortly state your motivation and experience (courses, projects) and if available, transcript of records.
☑ Title: Active Physical and Visual Investigation for Robotic Manipulation using Foundation Models
Scope: Master Thesis
Advisors: Georgia Chalvatzaki, Xanthi Papageorgiou (external)
Keywords: Robotic Manipulation, Foundation Models, LLM, VLM, Active Perception, Physical Interaction, Uncertainty Resolution, Human-Robot Interaction
Topic: Recent advances in Vision and Language Models (VLMs) have enabled robots to understand high-level commands, but they often fail when faced with visual ambiguity. For example, is a bolt loose, or is that just a shadow? This project aims to move beyond simple “observe-then-act” pipelines by creating a robot that can actively investigate its environment to resolve such uncertainties.
The core idea is to develop a framework where the robot, when uncertain, can autonomously decide to take another look from a different angle or even perform a gentle physical “touch test” with its gripper. By fusing visual data with physical feedback, the system can build a more robust and reliable understanding of the world, making a more informed final decision. This project will be implemented on a Franka Emika robotic arm and will focus on a solar panel inspection task, directly contributing to the goals of the ARISE EU project.
Tasks: Your work will include the following tasks:
– Conduct a literature review on the latest developments in foundation models for robotic control and perception.
– Design and implement the proposed Investigative Robotic Agent Framework using Python and ROS.
– Develop a novel module to translate raw physical sensor data (e.g., force/torque) into concise natural language descriptions that an LLM can understand.
– Set up and calibrate the real-world hardware, including the Franka arm, a wrist-mounted camera, and the inspection mock-up.
– Rigorously evaluate the system’s performance against baseline model(s) that does not perform active investigation.
– Document your work and write your final Master’s thesis, and participate in a paper submission to a top-tier robotics conference.
Requirements:
– Strong programming skills in Python.
– Practical experience with robotics; familiarity with ROS is a significant plus.
– A good understanding of fundamental deep learning concepts; experience with frameworks like PyTorch is beneficial.
– A keen interest in working with real-world robotic hardware.
– Previous experience with LLM/VLM APIs is a bonus but not strictly required.
References:
– Ahn, M., Brohan, A., Brown, N., et al. (2022). Do As I Can, Not As I Say: Grounding Language in Robotic Affordances. arXiv preprint arXiv:2204.01691.
– Brohan, A., Brown, N., et al. (2023). RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control. arXiv preprint arXiv:2307.15818.
– Huang, W., et al. (2023). VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models. arXiv preprint arXiv:2307.05973.
Contact: Interested students are invited to apply by emailing (georgia.chalvatzaki@tu-darmstadt.de) with their motivation letter, CV, and transcripts (if available).
☑ Title: Bimanual Dexterous Manipulation Benchmark for Generalizable Robot Learning
Scope: Master Thesis
Advisors: Steven Li, Georgia Chalvatzaki 
Topic: Imagine needing to use a screwdriver to tighten a screw. Your hands effortlessly grasp the tool, align it with the screw, and apply precise pressure to secure it. This fine motor control, known as dexterous manipulation, is natural for humans but highly challenging for robots. Robotic dexterous manipulation requires controlling a high degrees-of-freedom (DoF) hand to manipulate objects through continuous fingertip forces. Challenges include frequent contact changes, real-time feedback, high-dimensional inputs, long-horizon tasks, and generalizing across various object dynamics and geometries. These difficulties intensify during dynamic manipulation.
In this thesis, we aim to build a dexterous manipulation benchmark, featuring tasks like grasping, reorienting objects, two-handed peg insertion, etc. The goal is to enable sim-to-real transfer of learned skills and evaluate state-of-the-art algorithms from imitation learning (IL) to reinforcement learning (RL), ultimately building a robotic foundation model in simulation.
Highly motivated students can apply by sending an e-mail expressing their interest to Steven Li (email: supersglzc@gmail.com), attaching your letter of motivation and possibly your CV.
Requirements: A passion for robotics is key to success in this project. Reinforcement Learning knowledge and Python programming skills are needed.
Starter code will be provided to help you get started.
References:
[1] Chen, Yuanpei, et al. “Towards human-level bimanual dexterous manipulation with reinforcement learning.” Advances in Neural Information Processing Systems 35 (2022): 5150-5163.
[2] Zhu, Yuke, et al. “robosuite: A modular simulation framework and benchmark for robot learning.” arXiv preprint arXiv:2009.12293 (2020).
[3] Makoviychuk, Viktor, et al. “Isaac gym: High performance gpu-based physics simulation for robot learning.” arXiv preprint arXiv:2108.10470 (2021).
[4] Mittal, Mayank, et al. “Orbit: A unified simulation framework for interactive robot learning environments.” IEEE Robotics and Automation Letters 8.6 (2023): 3740-3747.
☑ Title: Multisensory Exploration for Efficient Robot Reinforcement Learning
Scope: Master thesis
Advisor: Rickmer Krohn, Gabriele Tiboni
Topic (in detail): thesis_ms_exploration.pdf
Humans rely on multiple sensory modalities like vision, touch, and proprioception, to explore and interact with their environment, especially in contact-rich tasks such as object manipulation. In contrast, most current robot
learning systems still only rely on vision for exploration. This thesis aims to develop and analyze multisensory exploration strategies that leverage vision, force-torque sensing, tactile input, and proprioception to improve sample efficiency, representation learning objectives and task performance in reinforcement learning.
The research will be conducted in simulated contact-rich manipulation environments using IsaacLab. You will compare baseline methods such as Random Network Distillation (RND) with newly developed approaches that integrate multisensory information to guide exploration. A central goal is to characterize how different sensory modalities influence the agent’s data collection, behavior and downstream task performance. Outstanding Work will be submitted to a conference with a potential publication.
How to apply: Highly motivated students can apply by sending an e-mail expressing their interest to Rickmer Krohn (email: rickmer.krohn@tu-darmstadt.de), attaching your letter of motivation and possibly your CV.
Requirements: Enthusiasm, ambition, and a curious mind go a long way. There will be supervision provided to help the student understand basic and advanced concepts. However, experience in Reinforcement Learning, Robot Simulation and good (python) programming skills are needed to successfully work on this thesis. Prior knowledge of Curiosity/Exploration methods and Isaac Sim are a plus.