Student Projects

Currently, the following student projects are available. Please contact the responsible supervisor and apply with your CV and transcripts.

In case you have project ideas related to any of these projects, take the opportunity and propose your own project!

We also offer Master Thesis and or exchange semesters at reknown universities around the world. Please contact us in case of interest!

Studies on Mechatronics

We offer students also to conduct their Studies on Mechatronics at our lab. In general, we recommend to do the Studies on Mechatronics in combination with the Bachelor Thesis, either as prepartory work the semester beofre or as extended study in parallel. If you want to do it independently, yiou can find prroposed projets also in the list below. Please directly apply with corresponsponding supervisor.

Emergent Acoustic Communication in Robot Groups

Can robots develop their own communication system through sound? We are looking for motivated students to join an interdisciplinary research project at the intersection of robotics, AI, acoustic signaling, and collective behavior.

Keywords

Emergent acoustic communication, Robot Learning, multi-agent communication.

Labels

Semester Project , Master Thesis

Description

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-05-16 , Earliest start: 2026-05-15

Organization Robotic Systems Lab

Hosts An Tianxu , Wang Shengzhi

Topics Information, Computing and Communication Sciences , Engineering and Technology

Hybrid Triangle and Gaussian Splatting

Photorealistic simulation and high-speed rendering are the basis of many modern robotics projects, but we are currently trapped in a binary: the rigid, memory-efficient world of triangle meshes versus the high-fidelity, computationally expensive world of neural representations. We propose a Hybrid Geometry Engine that abandons this "one-size-fits-all" approach. By representing static, flat architectural surfaces as optimized triangle meshes and complex 3D objects or volumetrics as 3D Gaussians, this project seeks to unlock a new paradigm for large-scale digital twins and robotic simulation.

Keywords

Computer Graphics 3D Gaussian Splatting Rendering

Labels

Master Thesis

PLEASE LOG IN TO SEE DESCRIPTION

More information

Open this project...

Published since: 2026-05-14 , Earliest start: 2026-05-18

Applications limited to ETH Zurich

Organization Robotic Systems Lab

Hosts Wilder-Smith Max

Topics Information, Computing and Communication Sciences

3D Scene Completion in Gaussian Splatting

Robots rarely get the luxury of a perfect map. During exploration, they are constantly fighting against "unknowables" such as occlusions, shadows, and unvisited corners that leave gaps in their understanding of the world. This project aims to address this by implementing 3D Gaussian Scene Completion, where the system proactively fills unobserved regions with learned geometric priors.

Keywords

3D Gaussian Splatting Scene reconstruction Scene completion 3D Graphics

Labels

Master Thesis

PLEASE LOG IN TO SEE DESCRIPTION

More information

Open this project...

Published since: 2026-05-14 , Earliest start: 2026-05-18

Applications limited to ETH Zurich

Organization Robotic Systems Lab

Hosts Wilder-Smith Max

Topics Information, Computing and Communication Sciences

Fine-Tuning Multimodal Reasoning Models for Affordance and Manipulativity Prediction in Robotic Manipulation

This project investigates whether reasoning-oriented multimodal models such as Gemma 4 can be fine-tuned to predict task-relevant affordances and manipulability for robotic manipulation. Given visual observations and high-level instructions, the model will identify actionable object parts, infer their functional suitability, and estimate how effectively a robot can interact with them using its own embodiment. Predictions may include affordance classes, contact regions, or manipulability scores learned from demonstrations, simulation, or robot execution data. These outputs will support interaction selection directly or guide downstream planners and control policies. The approach will be evaluated in simulation and on real robotic platforms to improve task-aware manipulation success in unstructured environments.

Keywords

affordance prediction; robotic manipulation; manipulability; multimodal reasoning; vision-language models; task-aware interaction; object part affordances; embodied AI; contact region prediction; motion planning; robot learning; high-level instruction understanding

Labels

Master Thesis

PLEASE LOG IN TO SEE DESCRIPTION

More information

Open this project...

Published since: 2026-05-10 , Earliest start: 2026-05-06 , Latest end: 2027-04-08

Applications limited to ETH Zurich , University of Zurich

Organization Robotic Systems Lab

Hosts Zurbrügg René , Werner Lennart

Topics Engineering and Technology

Automated calibration of body-scale contact sensors

Goal: Create a repeatable, precise, and high-throughput robotic experimental setup for characterizing a custom contact sensor. This project is part of a broader effort to enable robots to better perceive whole-body contact and execute dynamic, contact-rich tasks.

Keywords

Robotics, Tactile Sensing, Machine Learning, Automated Calibration, RL, AI, Mechanical Engineering, Manipulation

Labels

Semester Project

PLEASE LOG IN TO SEE DESCRIPTION

More information

Open this project...

Published since: 2026-05-07 , Earliest start: 2026-05-11 , Latest end: 2026-12-31

Applications limited to ETH Zurich

Organization Robotic Systems Lab

Hosts Baines Robert , Cramariuc Andrei

Topics Information, Computing and Communication Sciences , Engineering and Technology

AI-Driven Rock Reshaping Simulation and Control

This project develops an intelligent system for controlling rock fracture by combining finite element analysis (FEM) with machine learning. FEM simulations train a graph neural network (GNN) to predict fracture patterns. A reinforcement learning (RL) agent then uses this predictive GNN to learn optimal actions for guiding fractures towards a desired rock geometry, enabling precise and goal-oriented control.

Keywords

machine learning, deep learning, reinforcement learning, graph neural networks, construction robotics, space robotics

Labels

Semester Project , Master Thesis

Description

This project addresses a novel approach for simulating and controlling rock fracture processes using a combination of finite element analysis (FEM), supervised learning, and reinforcement learning (RL). The goal is to develop an intelligent system capable of predicting fracture patterns and actively guiding the fracturing process towards a desired rock geometry. The pipeline begins with a fracture simulation based on FEM, which models the physical stresses and crack propagation given the original rock geometry [1]. The data generated from various of these simulations is then used to train a graph neural network (GNN) via supervised learning. This GNN learns to predict the fracture behavior and resulting rock shape based on initial conditions and applied forces, and generalizes across geometries and materials [2]. Concurrently, an RL agent is developed. This agent's objective is to determine the optimal actions (e.g., applied forces or drilling patterns) to achieve a desired rock geometry. The RL agent learns through interaction with a training environment which leverages the pre-trained GNN to rapidly simulate the outcomes of the agent's actions on the rock geometry. By integrating FEM-based simulation with advanced machine learning techniques, this approach aims to create a powerful tool for understanding and controlling rock fracturing, with potential applications in fields such as mining, demolition and large scale construction robotics [3]. The GNN enables accurate and fast prediction of fracture mechanics on any geometries, while the RL agent provides intelligent, goal-oriented control over the fracturing process. [1] Li, J., Dai, L., Wang, S., Liu, Y., Sun, Y., Wang, J. and Zhang, A., 2024. Theoretical and numerical analysis of the rock breaking process by impact hammer. Powder Technology, 448, p.120254. [2] Mousavi, S., Wen, S., Lingsch, L., Herde, M., Raonić, B. and Mishra, S., 2025. RIGNO: A Graph-based framework for robust and accurate operator learning for PDEs on arbitrary domains. arXiv preprint arXiv:2501.19205. [3] Ryan Luke Johns et al. ,A framework for robotic excavation and dry stone construction using on-site materials.Sci. Robot.8,eabp9758(2023).DOI:10.1126/scirobotics.abp9758

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-04-19 , Earliest start: 2025-07-07

Organization Robotic Systems Lab

Hosts Spinelli Filippo , Gouveia Marina , Spinelli Filippo , Canales Claudio

Topics Information, Computing and Communication Sciences , Engineering and Technology

Scene graphs meet implicit representations

Explore novel, hierarchical spatial memory representations for flexible robot autonomy

Keywords

Hierarchical scene graphs, implicit representations, RL

Labels

Master Thesis

Description

When it comes to the input of low-level locomotion and navigation policies, learnings from the bitter lesson push researchers to slowly move away from explicit, world-centric representations towards implicit, egocentric representations. The belief is that this imposes the least bias on the representation, and thus leads to best performance. In order to make robots more capable, we then give them a memory or history of such embeddings as an augmented input. However, in many cases these embeddings are not spatially or temporally indexed, they are just a sequence of recent egocentric observations that turn out to be very local by design and express context only at a single level of abstraction. The goal of the present project would be to explore: • Spatial indexing of embedded representations in order to improve the ability to localize embeddings in space • Spatial pooling / compression of embeddings to generate novel implicit representations expressing contexts at higher levels of abstraction. The proposed idea is aiming for a marriage between scene graphs and implicit representations. The idea is to index/retrieve embeddings not just as a local history, but in space by projecting and averaging implicit representations in 3D. The hierarchy aspect would be an extension of this idea, and acknowledge the fact that different tasks benefit from different granularities of context representation. The challenge would be to find a meaningful pooling/averaging strategy that produces embeddings at a higher level of abstraction. In general, this would enable 1) more powerful memories that enable indexing in space (and possibly also time), and 2) more powerful policies that are informed about relevant context at multiple, different levels of abstraction. The thesis would be conducted at the RAI Institute, a relatively young, top-notch robotics research institute with representation in Zurich. It would be conducted under a collaboration framework between RAI and ETH Zurich. Strong engineering support and a best-in-class robotics research laboratory make this opportunity second to none. For an example of the recent achievements of the institute, please consider our online video channel. Selection is highly competitive. Potential candidates are invited to submit their CV and grade sheet, after which students will be invited to an on-site interview.

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-03-19 , Earliest start: 2026-03-23

Organization Robotic Systems Lab

Hosts Kneip Laurent

Topics Information, Computing and Communication Sciences , Engineering and Technology

LLM-based scene graph construction and navigation

Use LLM priors for efficient scene graph construction and navigation in urban environments

Keywords

Open vocabulary scene graphs, urban navigation, planning

Labels

Master Thesis

Description

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-03-19 , Earliest start: 2026-03-23

Organization Robotic Systems Lab

Hosts Kneip Laurent

Topics Information, Computing and Communication Sciences , Engineering and Technology

Learning-based robot state estimation

Achieve high-quality state estimation on any platform via conditioned neural representations

Keywords

Learning-based state estimation

Labels

Master Thesis

Description

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-03-19 , Earliest start: 2026-03-23

Organization Robotic Systems Lab

Hosts Kneip Laurent

Topics Information, Computing and Communication Sciences , Engineering and Technology

Enhancing Long-Range Navigation with VLMs

This project aims to enhance the WildOS [1] navigation framework by integrating a Vision-Language Model (VLM) [2,3] to perform semantic reasoning over a sparse topological graph. While standard WildOS excels at geometric navigation and open-vocabulary object search, it often lacks the high-level context needed to navigate "semantic traps" like dead-ends or complex roadblocks. By storing VLM-generated node summaries and image captions within the graph, the robot can transition from simple pattern matching to logical spatial querying. This allows the agent to interpret the environment's affordances—such as identifying if a path is "blocked by a gate" versus "temporarily obstructed by a person"—to make more informed recovery decisions.

Keywords

Foundation Models, Computer Vision, Navigation, Perception, Vision-Language Models, VLMs, Robotics, ROS, Field Robotics, Machine Learning,

Labels

Master Thesis

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-03-09 , Earliest start: 2026-03-09 , Latest end: 2026-10-31

Applications limited to ETH Zurich

Organization Robotic Systems Lab

Hosts Patil Vaishakh , Patel Manthan

Topics Information, Computing and Communication Sciences , Engineering and Technology

3D reconstruction with open-vocabulary reconstruction priors

Push the limits of arbitrary online video reconstruction by combining the most recent, prior-supported real-time Simultaneous Localization And Mapping (SLAM) methods with automatic backend regularization techniques.

Keywords

Structure from Motion Visual SLAM

Labels

Master Thesis , ETH Zurich (ETHZ)

Description

In recent years, the advent of learning-based methods has led to interesting novel structure from motion modules that provide end-to-end 3D structure, camera pose, and camera intrinsics estimation from arbitrary image sets [1,2]. While it is reasonable to assume that these representation implicitly impose geometric priors onto regularly encountered scene elements (e.g. chairs, tables, etc.), the imposition of these priors gets lost during the typical global back-end optimization step [3,4]. The imposition of geometric priors in back-end optimization is a topic with long-standing history, and nowadays encompasses both classical techniques such as piece-wise planarity or Manhattan world assumptions, as well as modern learning-based representations such as neural shape priors [5]. While certainly interesting, these approaches suffer from two important limitations: • Classical approaches are limited to a small set of pre-defined regularities that may be encountered in a certain class of environments (typically man-made). It is furthermore difficult to decide without further cues which parts of an environment should be regularized. • More modern approaches such as deep shape priors are typically trained on specific classes of objects, only, and are thus limited to certain object-level application. The goal of the present thesis is to investigate the following topics: • Flexible discovery of regularities (surface regularities, repetitive scene elements) in large scale outdoor reconstruction scenarios using LLM/VLMs • Extraction of geometric surface properties from grounded open-set features • Automatic formulation of regularization priors using LLMs • Inclusion into back-end reconstruction for improved global reconstruction results The proposed thesis will be conducted at the Robotics and AI (RAI) Institute, a new top-notch partner institute of Boston Dynamics pushing the boundaries of control and perception in robotics. For an example of the recent achievements of the institute, please consider our online video channel: Stunting with Reinforcement Learning The down-stream task of the present project will be the creation of geometric models with high fidelity surfaces for inclusion into simulation environments. Selection will be highly selective. Potential candidates are invited to submit their CV and grade sheet, after which students will be invited to an on-site interview. References [1] Grounding image matching in 3D with Mast3r, Vincent Leroy, Yohann Cabon, and Jerome Revaud [2] VGGT: Visual Geoemtry Grounded Transformer, Wang, Chen, Karaev, Vedaldi, Rupprecht, Novotny [3] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors, Murai, Dexheimer, Davison [4] VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold, Dominic Maggio, Hyungtae Lim, Luca Carlone [5] DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation, Park, Florence, Straub, Newcombe, Lovegrove

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-03-01 , Earliest start: 2025-07-01

Organization Robotic Systems Lab

Hosts Kneip Laurent

Topics Engineering and Technology

Event-based feature detection for highly dynamic tracking

Event cameras are an exciting new technology enabling sensing of highly dynamic content over a broad range of illumination conditions. The present thesis explores novel, sparse, event-driven paradigms for detecting structure and motion patterns in raw event streams.

Keywords

Event camera, neuromorphic sensing, feature detection, computer vision

Labels

Master Thesis

Description

Event cameras are a relatively new, vision-based exteroceptive sensor relying on standard CMOS technology. Unlike normal cameras, event cameras do not measure absolute brightness in a frame-by-frame manner, but relative changes of the pixel-level brightness. Essentially, every pixel of an event camera independently observes the local brightness pattern, and when the latter experiences a relative change of minimum amount with respect to a previous value, a measurement is triggered in the form of a time-stamped event indicating the image location as well as the polarity of the change (brighter or darker) [2]. The pixels act asynchronously and can potentially fire events at a very high rate. Owing to their design, event cameras do not suffer from the same artifacts as regular cameras, but continue to perform well under high dynamics or challenging illumination conditions. Event cameras currently enjoy growing popularity and they represent a new, interesting alternative for exteroceptive sensing in robotics when facing scenarios with high dynamics and/or challenging conditions. The focus of the present thesis lies on 3D motion estimation with event cameras, and in particular aims at event-driven, computationally efficient methods that can trigger motion hypotheses from sparse raw events. Initial theoretical advances in this direction have been presented in recent literature [3,4,5], though these methods are still limited in terms of the assumptions that they make. The present thesis will push the boundaries by proposing novel both geometry and learning-based representations. The proposed thesis will be conducted at the Robotics and AI Institute, a new top-notch partner institute of Boston Dynamics pushing the boundaries of control and perception in robotics. Selection is highly competitive. Potential candidates are invited to submit their CV and grade sheet, after which students will be invited to an on-site interview. [1] Event-Based, 6-DOF Camera Tracking from Photometric Depth Maps, TPAMI 40(10):2402-2412, 2017 [2] The Silicon Retina, 264(5): 76-83, 1991 [3] A 5-Point Minimal Solver for Event Camera Relative Motion Estimation. In Proceedings of the International Conference on Computer Vision (ICCV), 2023 [4] An n-point linear solver for line and motion estimation with event cameras. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [5] Full-DoF Egomotion Estimation for Event Cameras Using Geometric Solvers, Arxiv: https://arxiv.org/html/2503.03307v1

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-03-01 , Earliest start: 2025-03-17

Organization Robotic Systems Lab

Hosts Kneip Laurent

Topics Engineering and Technology

Soft object reconstruction

This project consists of reconstructing soft object along with their appearance, geometry, and physical properties from image data for inclusion in reinforcement learning frameworks for manipulation tasks.

Keywords

Computer Vision, Structure from Motion, Image-based Reconstruction, Physics-based Reconstruction

Labels

Master Thesis

Description

As 3D reconstruction [2,3], real-time data-driven rendering [4,5], and learning-based control technologies [6,7] are becoming more mature, recent efforts in reinforcement learning are moving towards end-to-end policies that directly consume images in order to generate control commands [8]. However, many of the simulated environments are limited to a composition of rigid objects. In recent years, the inclusion of differentiable particle-based simulation borrowed from computer graphics has enabled the inclusion of non-rigid or even fluid elements. Ideally, we can generate such representations from real world data in order to extend data-driven world simulators to arbitrary new objects with complex physical behavior. The present thesis focuses on this problem and aims at reconstructing soft objects in terms of their geometry, appearance, and physical behavior. The goal is to make use of the Material Point Method (MPM) in combination with vision-based cues and physical priors in order to reconstruct accurate 3D models of soft objects. The developed models will finally be included into an RL learning environment such as Isaac-Gym in order to train novel manipulation policies for soft objects. The proposed thesis will be conducted at the Robotics and AI Institute, a new top-notch partner institute of Boston Dynamics pushing the boundaries of control and perception in robotics. Selection is highly competitive. Potential candidates are invited to submit their CV and grade sheet, after which students will be invited to an on-site interview. [1] Modeling of Deformable Objects for Robotic Manipulation: A Tutorial and Review, Front. Robot. AI, 7, 2020 [2] Global Structure-from-Motion Revisited, ECCV 2024 [3] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors, CVPR 2025 [4] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, CVPR 2020 [5] 3D Gaussian Splatting for Real-Time Radiance Field Rendering, SIGGRAPH 2023 [6] Learning to walk in minutes using massively parallel deep reinforcement learning, CoRL 2022 [7] Champion-Level Drone Racing Using Deep Reinforcement Learning, Nature, 2023 [8] π0: A Vision-Language-Action Flow Model for General Robot Control, Arxiv: https://arxiv.org/abs/2410.24164

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-03-01 , Earliest start: 2025-03-17

Organization Robotic Systems Lab

Hosts Kneip Laurent

Topics Engineering and Technology

Generalist policies for robotic bike racing

This project addresses the problem of overfitting in autonomous robotic racing by developing generalist reinforcement learning (RL) policies. Conducted in collaboration between the RAI Institute and ETH Zurich, the research focuses on creating robust track embeddings for complex terrains. These embeddings will condition policies for a bike-like ultra-mobile vehicle (UMV), enabling it to autonomously race on previously unknown mountain-bike trails. The ultimate goal is to deploy these policies on physical hardware to achieve competitive, real-world performance via zero-shot transfer or minimal simulation refinement.

Labels

Master Thesis

PLEASE LOG IN TO SEE DESCRIPTION

More information

Open this project...

Published since: 2026-03-01

Organization Robotic Systems Lab

Hosts Jenelten Fabian, Dr.

Topics Engineering and Technology

Exploring Exotic Wheels For Wheeled-Legged Robots

Wheeled-legged robots combine the advantages of wheels, i.e., efficient high-speed locomotion, with obstacle negotiation and rough terrain capabilities of legs. In this study, different exotic wheel concepts should be researched, evaluated, and possibly implemented on a real robot to potentially boost efficiency, manipulation, and functionality.

Keywords

Wheeled-Legged Robots, Wheels, Robotics, Mechanical and Hardware Design, Manipulation, Tires

Labels

Semester Project , Bachelor Thesis , Master Thesis

PLEASE LOG IN TO SEE DESCRIPTION

More information

Open this project...

Published since: 2026-02-18

Organization Robotic Systems Lab

Hosts Klemm Victor

Topics Information, Computing and Communication Sciences , Engineering and Technology

Hierarchical Reasoning Models (HRM) for Robotics

How to properly deal with long-horizon tasks is still an unsolved problem in robot learning. Recent advances in reasoning models present Hierarchical Reasoning Models (HRM), inspired by the hierarchical and multi-timescale processing in the human brain. This fairly open project should implement and test state of the art solutions for long horizon planning that require reasoning in the context of robotics, especially robotics motion control.

Keywords

Robot learning, hierarchical reasoning, machine intelligence, long-horizon planning

Labels

Semester Project , Bachelor Thesis , Master Thesis

Description

Work Packages

Requirements

Contact Details

More information

Open this project...

Published since: 2026-02-18

Organization Robotic Systems Lab

Hosts Klemm Victor

Topics Information, Computing and Communication Sciences , Engineering and Technology

Student Theses at RAI

The Robotic Systems Lab offers a number of student projects at RAI or in collaboration with RAI. Please check the individual projects and directly apply to the supervisors.

Note on plagiarism

We would like to suggest every student, irrespective of the type of project (Bachelor, Semester, Master, ...), to make himself/herself familiar with ETH rules regarding plagiarism