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.
Propose Your Own Robotics Challenge
This project invites you to step into the role of an innovator, encouraging you to identify challenges you are passionate about within the field of robotics. Rather than working on predefined problems, you will have the freedom to propose your own project ideas, address real-world issues, or explore cutting-edge topics. This project allows you to define your own research journey.
Keywords
Robotics, Research
Labels
Semester Project , Bachelor Thesis , Master Thesis
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2025-01-28 , Earliest start: 2025-01-27
Organization Robotic Systems Lab
Hosts Schwarke Clemens , Bjelonic Filip , Klemm Victor
Topics Information, Computing and Communication Sciences
Data Driven Simulation for End-to-End Navigation
Investigate how neural rendering can become the backbone of comprehensive, next generation data-driven simulation
Keywords
Neural rendering, Simulation
Labels
Internship , Master Thesis
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2025-01-24 , Earliest start: 2025-01-27
Organization Robotic Systems Lab
Hosts Kneip Laurent
Topics Information, Computing and Communication Sciences , Engineering and Technology
Evolving Minds: Neuroevolution for Legged Locomotion
This project explores the use of neuroevolution for optimizing control policies in legged robots, moving away from classical gradient-based methods like PPO. Neuroevolution directly optimizes network parameters and structures, potentially offering advantages in environments with sparse rewards, while requiring fewer hyperparameters to tune. By leveraging genetic algorithms and evolutionary strategies, the project aims to develop efficient controllers for complex locomotion tasks. With computational capabilities doubling approximately every two years as predicted by Moore's Law, neuroevolution offers a promising approach for scaling intelligent control systems.
Keywords
Evolutionary Algorithms, Reinforcement Learning, Quadrupeds, Legged Locomotion
Labels
Master Thesis
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2025-01-22 , Earliest start: 2025-01-27
Organization Robotic Systems Lab
Hosts Bjelonic Filip , Schwarke Clemens
Topics Information, Computing and Communication Sciences
AI-Powered Clustering of Satellite Data for Global Navigation
Imagine a robot that can intelligently interpret the world from above—looking at its immediate surroundings and predict how the terrain extends beyond its sensors. If the ground beneath its feet is muddy, it might infer that the meadows ahead will have a similar challenge, adjusting its path accordingly. To enable this kind of intelligent decision-making, robots need to recognize how local conditions propagate globally. Machine learning techniques, particularly deep learning models, offer a way to automate this understanding by clustering satellite images based on visual and structural similarities.
Keywords
Learning, Deep Learning, Satellite Data, Global Planning, Robotics
Labels
Semester Project
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2025-01-22
Organization Robotic Systems Lab
Hosts Richter Julia
Topics Information, Computing and Communication Sciences
Design of a Compliant Mechanism for Human-Robot Collaborative Transportation with Non-Holonomic Robots
Human-robot collaboration is an attractive option in many industries for transporting long and heavy items with a single operator. In this project, we aim to enable HRC transportation with a non-holonomic robotic base platform by designing a compliant manipulation mechanism, inspired by systems like the Omnid Mocobots.
Keywords
Human-robot collaboration Collaborative transportation Non-holonomic robot Mobile manipulation
Labels
Master Thesis , ETH Zurich (ETHZ)
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2025-01-16 , Earliest start: 2024-07-08
Applications limited to ETH Zurich
Organization Robotic Systems Lab
Hosts Kindle Julien , Bray Francesca
Topics Information, Computing and Communication Sciences , Engineering and Technology
Perceptive Arm Motion Planning and Control for Heavy Construction Machine Tasks
In this work we would utilize reinforcement learning, neural network actuator modeling, and perception for the control and arm motion planning of a 40ton excavator with a free-swinging gripper. The project will be in collaboration with Gravis Robotics, ETH spinoff working on the automation of heavy machinery.
Keywords
reinforcement learning, perception, hydraulics, excavator, manipulation, industry
Labels
Semester Project , Collaboration , Master Thesis , ETH Zurich (ETHZ)
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2025-01-08 , Earliest start: 2025-02-03 , Latest end: 2025-08-31
Organization Robotic Systems Lab
Hosts Egli Pascal Arturo , Nan Fang , Spinelli Filippo
Topics Information, Computing and Communication Sciences , Engineering and Technology
Boosting Reinforcement Learning with High-Speed Gaussian Splatting
This project addresses the computational bottlenecks in model-free reinforcement learning (RL) with high-dimensional image inputs by optimizing Gaussian Splatting—a GPU-accelerated technique for photorealistic image generation from point clouds—for RL applications. By integrating pre-sorting methods, the project aims to enhance rendering speeds, enabling broader RL applications beyond geometric constraints or abstraction layers. Building on previous work involving risk annotations in Gaussian splats, the project seeks to develop generalizable RL policies that leverage real-world knowledge.
Keywords
Gaussian Splatting, Navigation, Reinforcement Learning
Labels
Semester Project , Master Thesis
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2025-01-08
Organization Robotic Systems Lab
Hosts Roth Pascal , Wilder-Smith Max
Topics Information, Computing and Communication Sciences
How to Touch: Exploring Tactile Representations for Reinforcement Learning
Developing and benchmarking tactile representations for dexterous manipulation tasks using reinforcement learning.
Keywords
Reinforcement Learning, Dexterous Manipulation, Tactile Sensing
Labels
Semester Project , Bachelor Thesis , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2025-01-08 , Earliest start: 2024-12-15 , Latest end: 2025-06-01
Applications limited to ETH Zurich
Organization Robotic Systems Lab
Hosts Bhardwaj Arjun , Zurbrügg René
Topics Information, Computing and Communication Sciences
Imitation Learning for Pedipulation
This project aims to enable our quadrupedal robot, ANYmal, to perform manipulation tasks with its foot. Particularly, we want to use imitation learning to learn high-level motion plans that can solve real-world tasks such as opening doors, pushing objects, and transporting payloads. This approach will allow solving simple manipulation tasks autonomously.
Keywords
legged robots, imitation learning, manipulation, pedipulation
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-19 , Earliest start: 2025-02-01 , Latest end: 2025-08-31
Organization Robotic Systems Lab
Hosts Arm Philip
Topics Information, Computing and Communication Sciences , Engineering and Technology
BEV meets Semantic traversability
Enable Birds-Eye-View perception on autonomous mobile robots for human-like navigation.
Keywords
Semantic Traversability, Birds-Eye-View, Localization, SLAM, Object Detection
Labels
Master Thesis , ETH Zurich (ETHZ)
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2024-12-18 , Earliest start: 2025-01-15 , Latest end: 2025-10-31
Organization Robotic Systems Lab
Hosts Gawel Abel
Topics Information, Computing and Communication Sciences , Engineering and Technology
Scene graphs for robot navigation and reasoning
Elevate semantic scene graphs to a new level and perform semantically-guided navigation and interaction with real robots at The AI Institute.
Keywords
Scene graphs, SLAM, Navigation, Spacial Reasoning, 3D reconstruction, Semantics
Labels
Master Thesis , ETH Zurich (ETHZ)
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2024-12-18 , Earliest start: 2025-01-15 , Latest end: 2025-10-31
Organization Robotic Systems Lab
Hosts Gawel Abel
Topics Information, Computing and Communication Sciences , Engineering and Technology
Global robot localization in mesh models
This project includes designing and implementing a particle filter for global robot localization in the environments represented by a mesh model. Particular interest lies in the applicability of such a technique for construction sites, which are considered highly dynamic and, hence, challenging for robot localization.
Keywords
* Global robot localization * Diffusion models * Particle Filter
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-17 , Earliest start: 2024-12-18
Organization Robotic Systems Lab
Hosts Vysotska Olga , Talbot William
Topics Engineering and Technology
Graph-based robot localization in BIM models
This project focuses on implementing and deploying a graph-based localization framework that allows to position a robot within BIM (Building information Models).
Keywords
Graph-based robot localization BIM models
Labels
Semester Project , Bachelor Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-17 , Earliest start: 2024-12-18
Organization Robotic Systems Lab
Hosts Vysotska Olga , Talbot William
Topics Engineering and Technology
Digital Twin for Spot's Home
MOTIVATION ⇾ Creating a digital twin of the robot's environment is crucial for several reasons: 1. Simulate Different Robots: Test various robots in a virtual environment, saving time and resources. 2. Accurate Evaluation: Precisely assess robot interactions and performance. 3. Enhanced Flexibility: Easily modify scenarios to develop robust systems. 4. Cost Efficiency: Reduce costs by identifying issues in virtual simulations. 5. Scalability: Replicate multiple environments for comprehensive testing. PROPOSAL We propose to create a digital twin of our Semantic environment, designed in your preferred graphics Platform to be able to simulate Reinforcement Learning agents in the digital environment, to create a unified evaluation platform for robotic tasks.
Keywords
Digital Twin, Robotics
Labels
Semester Project , Master Thesis
Contact Details
More information
Published since: 2024-12-17 , Earliest start: 2025-01-05
Applications limited to University of Zurich , ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne
Organization Computer Vision and Geometry Group
Hosts Blum Hermann , Portela Tifanny , Bauer Zuria, Dr. , Trisovic Jelena
Topics Information, Computing and Communication Sciences
KALLAX Benchmark: Evaluating Household Tasks
Motivation ⇾ There are three ways to evaluate robots for pick-and-place tasks at home: 1. Simulation setups: High reproducibility but hard to simulate real-world complexities and perception noise. 2. Competitions: Good for comparing overall systems but require significant effort and can't be done frequently. 3. Custom lab setups: Common but lead to overfitting and lack comparability between labs. Proposal ⇾ We propose using IKEA furniture to create standardized, randomized setups that researchers can easily replicate. E.g, a 4x4 KALLAX unit with varying door knobs and drawer positions, generating tasks like "move the cup from the upper right shelf into the black drawer." This prevents overfitting and allows for consistent evaluation across different labs.
Keywords
Benchmakr, Robotics, pick-and-place
Labels
Semester Project , Master Thesis
Contact Details
More information
Published since: 2024-12-17 , Earliest start: 2025-01-06
Applications limited to University of Zurich , ETH Zurich , Swiss National Science Foundation , EPFL - Ecole Polytechnique Fédérale de Lausanne
Organization Computer Vision and Geometry Group
Hosts Blum Hermann , Bauer Zuria, Dr. , Zurbrügg René
Topics Information, Computing and Communication Sciences
Adapting to Injuries for Dexterous In-Hand Manipulation
Develop a reinforcement learning-based method for training adaptive policies for dexterous in-hand manipulation systems to deal with actuator failure on the fly.
Keywords
Dexterous Manipulation, Reinforcement Learning, Adaptive Learning
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-12 , Earliest start: 2024-12-16 , Latest end: 2025-06-01
Applications limited to ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne
Organization Robotic Systems Lab
Hosts Bhardwaj Arjun , Ma Yuntao
Topics Information, Computing and Communication Sciences
Extending Functional Scene Graphs to Include Articulated Object States
While traditional [1] and functional [2] scene graphs are capable of capturing the spatial relationships and functional interactions between objects and spaces, they encode each object as static, with fixed geometry. In this project, we aim to enable the estimation of the state of articulated objects and include it in the functional scene graph.
Keywords
scene understanding, scene graph, exploration
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-11
Applications limited to ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne
Organization Computer Vision and Geometry Group
Hosts Bauer Zuria, Dr. , Trisovic Jelena , Zurbrügg René
Topics Information, Computing and Communication Sciences , Engineering and Technology
Offline LLM-Based Planning for Mobile Manipulation
Large Language Models have enormous potential to increase the generalization capability of robots. Specifically, they can allow mobile platforms to navigate successfully in unknown environments towards open-vocabulary goals. Current applications to mobile platforms are limited due to online models being both slow to query and requiring stable internet connection, which can not always be guaranteed. This project aims to explore the possibility of using a miniature LLM locally on the ALMA robot for navigation though unmapped space, with the goal of moving towards specifying objects using an open-vocabulary and interacting with them.
Keywords
Large Language Models, Mobile Manipulation, Robotics, Machine Learning, Planning
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-11 , Earliest start: 2025-02-01 , Latest end: 2025-12-31
Organization Robotic Systems Lab
Hosts Elanjimattathil Aravind , Scheidemann Carmen
Topics Engineering and Technology
Active Object Localization with Touch
Develop active exploration strategies for object identification and localization with tactile feedback.
Keywords
Dexterous Manipulation, Object Retrieval, Active Localization, Tactile Sensing
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-11 , Earliest start: 2024-12-15 , Latest end: 2025-06-01
Applications limited to ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne
Organization Robotic Systems Lab
Hosts Bhardwaj Arjun , Zurbrügg René
Topics Information, Computing and Communication Sciences
Learning-based object orientation prediction for handovers
Humans are exceptional at handovers. Besides timing and spatial precision, they also have a high-level understanding of how the other person wants to use the object that is handed over. This information is needed to hand over an object, such that it can be used directly for a specific task. While robots can reason about grasp affordances, the integration of this information with perception and control is missing.
Keywords
Robot-Human Handover, Human-Robot-Interaction, Mobile Manipulation, Robotics
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-10 , Earliest start: 2025-02-01 , Latest end: 2025-12-31
Organization Robotic Systems Lab
Hosts Scheidemann Carmen , Tulbure Andreea
Topics Information, Computing and Communication Sciences , Engineering and Technology
Evolve to Grasp: Learning Optimal Finger Configuration for a Dexterous Multifingered Hand
Use evolutionary algorithms with analytical force closure metrics to learn the optimal morphology of a dexterous hand.
Keywords
Evolutionary Algorithm, Machine Learning, Grasping, Robotics
Labels
Semester Project , Master Thesis
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2024-12-09 , Earliest start: 2024-12-09 , Latest end: 2025-10-31
Applications limited to ETH Zurich
Organization Robotic Systems Lab
Hosts Church Joseph , Zurbrügg René
Topics Information, Computing and Communication Sciences
Learn to Reach: Collision Aware End-Effector Path Planning & Tracking using Reinforcement Learning
Develop a method for collision aware reaching tasks using reinforcement learning and shape encodings of the environment
Keywords
Reinforcement Learning, Robotics, Perception, Machine Learning
Labels
Semester Project , Master Thesis , ETH Zurich (ETHZ)
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2024-12-09 , Earliest start: 2024-12-09 , Latest end: 2025-12-31
Applications limited to ETH Zurich
Organization Robotic Systems Lab
Hosts Zurbrügg René , Zurbrügg René , Portela Tifanny
Topics Information, Computing and Communication Sciences
Differential Particle Simulation for Robotics
This project focuses on applying differential particle-based simulation to address challenges in simulating real-world robotic tasks involving interactions with fluids, granular materials, and soft objects. Leveraging the differentiability of simulations, the project aims to enhance simulation accuracy with limited real-world data and explore learning robotic control using first-order gradient information.
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-09 , Earliest start: 2025-01-01 , Latest end: 2025-12-31
Applications limited to ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne
Organization Robotic Systems Lab
Hosts Nan Fang , Ma Hao
Topics Engineering and Technology
Conformal Prediction for Distribution Shift Detection in Online Learning
This project investigates the use of conformal prediction for detecting distribution shifts in online learning scenarios, with a focus on robotics applications. Distribution shifts, arising from deviations in task distributions or changes in robot dynamics, pose significant challenges to online learning systems by impacting learning efficiency and model performance. The project aims to develop a robust detection algorithm to address these shifts, classifying task distribution shifts as outliers while dynamically retraining models for characteristic shifts.
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-09 , Earliest start: 2025-01-01 , Latest end: 2025-12-31
Organization Robotic Systems Lab
Hosts Ma Hao , Nan Fang
Topics Information, Computing and Communication Sciences , Engineering and Technology
Visual Language Models for Long-Term Planning
This project uses Visual Language Models (VLMs) for high-level planning and supervision in construction tasks, enabling task prioritization, dynamic adaptation, and multi-robot collaboration for excavation and site management. prioritization, dynamic adaptation, and multi-robot collaboration for excavation and site management
Keywords
Visual Language Models, Long-term planning, Robotics
Labels
Semester Project , Master Thesis
Description
Work Packages
Contact Details
More information
Published since: 2024-12-06 , Earliest start: 2025-01-24 , Latest end: 2025-10-29
Organization Robotic Systems Lab
Hosts Terenzi Lorenzo
Topics Information, Computing and Communication Sciences
Learning Acrobatic Excavator Maneuvers
Gravis Robotics is an ETH spinoff from the Robotic Systems Lab (RSL) working on the automation of heavy machinery (https://gravisrobotics.com/). In this project you will be working with the Gravis team to develop an algorithm that allows a 25-ton excavator to perform an acrobatics maneuver, the jump turn.
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-06 , Earliest start: 2025-01-01 , Latest end: 2025-12-01
Organization Robotic Systems Lab
Hosts Egli Pascal Arturo , Zhang Weixuan
Topics Engineering and Technology
RL-Based Autonomous Excavation
Gravis Robotics is an ETH spinoff from the Robotic Systems Lab (RSL) working on the automation of heavy machinery (https://gravisrobotics.com/). In this project, you will be working with the Gravis team to develop a vision-based system to detect anomalies during the autonomous operation of the machine. You will conduct your project at Gravis under joint supervision from RSL.
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-06 , Earliest start: 2025-01-01 , Latest end: 2025-12-01
Organization Robotic Systems Lab
Hosts Zhang Weixuan , Egli Pascal Arturo
Topics Engineering and Technology
Data-Driven Joint Control
Gravis Robotics is an ETH spinoff from the Robotic Systems Lab (RSL) working on the automation of heavy machinery (https://gravisrobotics.com/). In this project, you will be working with the Gravis team to develop a perceptive navigation system for an autonomous CAT323 excavator. You will conduct your project at Gravis with joint supervision with RSL.
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-06 , Earliest start: 2025-01-01 , Latest end: 2026-01-01
Organization Robotic Systems Lab
Hosts Jelavic Edo , Egli Pascal Arturo
Topics Engineering and Technology
Taming the Invisible: Autonomous Gas Detection with ANYmal
Gas source localisation has many applications, such as responding to chemical accidents, detecting explosives, and identifying methane leaks from landfill sites. These tasks often take place in hazardous environments, posing significant risks to human operators. To mitigate these dangers, robotic systems are increasingly being developed to undertake these challenging missions. However, real-world gas localization presents a significant challenge: gas plumes are highly dynamic, exhibiting both temporal and spatial inconsistencies due to environmental factors such as wind, turbulence, and diffusion. Overcoming these complexities is essential for reliable robotic gas detection and localization.
Keywords
Navigation, Gas Sensing, Neural Network
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-06
Organization Robotic Systems Lab
Hosts Richter Julia
Topics Information, Computing and Communication Sciences
Perceptive Navigation
Gravis Robotics is an ETH spinoff from the Robotic Systems Lab (RSL) working on automation of heavy machinery (https://gravisrobotics.com/). In this project you will be working with the Gravis team to develop a perceptive navigation system for autonomous CAT323 excavator. You will conduct your project at Gravis with joint supervision with RSL.
Keywords
Perceptive Navigation, Autonomous Excavator
Labels
Internship , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-06 , Earliest start: 2025-01-01 , Latest end: 2026-01-01
Organization Robotic Systems Lab
Hosts Jelavic Edo , Egli Pascal Arturo , Strub Marlin , Cizek Petr
Topics Engineering and Technology
RL-Based Stockpile Management for Autonomous Excavators
Gravis Robotics is an ETH spinoff from the Robotic Systems Lab (RSL) working on the automation of heavy machinery (https://gravisrobotics.com/). In this project, you will be working with the Gravis team to develop an RL-based perceptive planning and control system for stockpile management for an autonomous excavator. You will conduct your project at Gravis under joint supervision from RSL.
Keywords
Reinforcement Learning, Autonomous Excavation
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-06 , Earliest start: 2025-01-01 , Latest end: 2026-01-01
Organization Robotic Systems Lab
Hosts Egli Pascal Arturo
Topics Engineering and Technology
Vision-Based Anomaly Detection for Autonomous Excavators
Gravis Robotics is an ETH spinoff from the Robotic Systems Lab (RSL) working on the automation of heavy machinery (https://gravisrobotics.com/). In this project, you will be working with the Gravis team to develop a vision-based system to detect anomalies during the autonomous operation of the machine. You will conduct your project at Gravis under joint supervision from RSL.
Keywords
Vision, Autonomous Excavator
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-12-06 , Earliest start: 2025-01-01 , Latest end: 2026-01-01
Organization Robotic Systems Lab
Hosts Zhang Weixuan , Egli Pascal Arturo
Topics Engineering and Technology
LLM-Driven Skill Acquisition for the ANYmal robot
The goal of this project is to apply LLMs to teach the ANYmal robot new low-level skills via Reinforcement Learning (RL) that the task planner identifies to be missing.
Keywords
Large Language Models, Reinforcement Learning, Robotics
Labels
Master Thesis
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2024-12-03
Applications limited to ETH Zurich
Organization Robotic Systems Lab
Hosts Roth Pascal , Portela Tifanny
Topics Information, Computing and Communication Sciences
Diffusion-based Shared Autonomy System for Telemanipulation
Robots may not be able to complete tasks fully autonomously in unstructured or unseen environments, however direct teleoperation from human operators may also be challenging due to the difficulty of providing full situational awareness to the operator as well as degradation in communication leading to the loss of control authority. This motivates the use of shared autonomy for assisting the operator thereby enhancing the performance during the task. In this project, we aim to develop a shared autonomy framework for teleoperation of manipulator arms, to assist non-expert users or in the presence of degraded communication. Imitation learning, such as diffusion models, have emerged as a popular and scalable approach for learning manipulation tasks [1, 2]. Additionally, recent works have combined this with partial diffusion to enable shared autonomy [3]. However, the tasks were restricted to simple 2D domains. In this project, we wish to extend previous work in the lab using diffusion-based imitation learning, to enable shared autonomy for non-expert users to complete unseen tasks or in degraded communication environments.
Keywords
Imitation learning, Robotics, Manipulation, Teleoperation
Labels
Semester Project , ETH Zurich (ETHZ)
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2024-12-02 , Earliest start: 2024-11-01 , Latest end: 2025-11-01
Applications limited to ETH Zurich , University of Zurich
Organization Robotic Systems Lab
Hosts Elanjimattathil Aravind
Topics Information, Computing and Communication Sciences , Engineering and Technology
DynaGELLO: A Low Cost "Puppet" Teleoperation System for the DynaArm
The GELLO system proposed in [1] is a low-cost “puppet” robot arm that is used to teleoperate a larger, main robot arm. This project aims to adapt this open source design to enable teleoperation of the DynaArm, which is a robot manipulator arm custom designed by the Robotic Systems Lab to be mounted on the ANYmal quadruped platform. Such a system provides a simplification over the existing DynaArm teleoperation interface consisting of a second identical DynaArm used purely as a human interface device [2], which may be an unnecessarily expensive and cumbersome solution. The system developed may have applications in remote teleoperation for industrial inspection or disaster response scenarios, as well as providing an interface for training imitation learning models, which may optionally be explored as time permits. [1] Wu, Philip et al. "GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators". arXiv preprint (2024) [2] Fuchioka, Yuni et al. AIRA Challenge: Teleoperated Mobile Manipulation for Industrial Inspection. Youtube Video. (2024)
Keywords
Robotics, Teleoperation, Manipulation, Imitation Learning
Labels
Semester Project , Bachelor Thesis , Master Thesis
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2024-11-27 , Earliest start: 2025-01-06 , Latest end: 2025-07-31
Applications limited to ETH Zurich
Organization Robotic Systems Lab
Hosts Fuchioka Yuni
Topics Information, Computing and Communication Sciences , Engineering and Technology
Periodic Motion Priors for General Quadruped Locomotion Learning
In recent years, advancements in reinforcement learning have achieved remarkable success in quadruped locomotion tasks. Despite their similar structural designs, quadruped robots often require uniquely tailored reward functions for effective motion pattern development, limiting the transferability of learned behaviors across different models. This project proposes to bridge this gap by developing a unified, continuous latent representation of quadruped motions applicable across various robotic platforms. By mapping these motions onto a shared latent space, the project aims to create a versatile foundation that can be adapted to downstream tasks for specific robot configurations.
Keywords
representation learning, periodic autoencoders, policy modulating trajectory generators
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization ETH Competence Center - ETH AI Center
Hosts Li Chenhao , Miki Takahiro
Topics Information, Computing and Communication Sciences , Engineering and Technology
Lifelike Agility on ANYmal by Learning from Animals
The remarkable agility of animals, characterized by their rapid, fluid movements and precise interaction with their environment, serves as an inspiration for advancements in legged robotics. Recent progress in the field has underscored the potential of learning-based methods for robot control. These methods streamline the development process by optimizing control mechanisms directly from sensory inputs to actuator outputs, often employing deep reinforcement learning (RL) algorithms. By training in simulated environments, these algorithms can develop locomotion skills that are subsequently transferred to physical robots. Although this approach has led to significant achievements in achieving robust locomotion, mimicking the wide range of agile capabilities observed in animals remains a significant challenge. Traditionally, manually crafted controllers have succeeded in replicating complex behaviors, but their development is labor-intensive and demands a high level of expertise in each specific skill. Reinforcement learning offers a promising alternative by potentially reducing the manual labor involved in controller development. However, crafting learning objectives that lead to the desired behaviors in robots also requires considerable expertise, specific to each skill.
Keywords
learning from demonstrations, imitation learning, reinforcement learning
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization ETH Competence Center - ETH AI Center
Hosts Li Chenhao , Li Chenhao , Klemm Victor
Topics Information, Computing and Communication Sciences
Pushing the Limit of Quadruped Running Speed with Autonomous Curriculum Learning
The project aims to explore curriculum learning techniques to push the limits of quadruped running speed using reinforcement learning. By systematically designing and implementing curricula that guide the learning process, the project seeks to develop a quadruped controller capable of achieving the fastest possible forward locomotion. This involves not only optimizing the learning process but also ensuring the robustness and adaptability of the learned policies across various running conditions.
Keywords
curriculum learning, fast locomotion
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization Robotic Systems Lab
Hosts Li Chenhao , Bagatella Marco , Li Chenhao , Li Chenhao , Li Chenhao
Topics Engineering and Technology
Leveraging Human Motion Data from Videos for Humanoid Robot Motion Learning
The advancement in humanoid robotics has reached a stage where mimicking complex human motions with high accuracy is crucial for tasks ranging from entertainment to human-robot interaction in dynamic environments. Traditional approaches in motion learning, particularly for humanoid robots, rely heavily on motion capture (MoCap) data. However, acquiring large amounts of high-quality MoCap data is both expensive and logistically challenging. In contrast, video footage of human activities, such as sports events or dance performances, is widely available and offers an abundant source of motion data. Building on recent advancements in extracting and utilizing human motion from videos, such as the method proposed in WHAM (refer to the paper "Learning Physically Simulated Tennis Skills from Broadcast Videos"), this project aims to develop a system that extracts human motion from videos and applies it to teach a humanoid robot how to perform similar actions. The primary focus will be on extracting dynamic and expressive motions from videos, such as soccer player celebrations, and using these extracted motions as reference data for reinforcement learning (RL) and imitation learning on a humanoid robot.
Labels
Master Thesis
Description
Goal
Contact Details
More information
Published since: 2024-11-26
Applications limited to ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne
Organization ETH Competence Center - ETH AI Center
Hosts Li Chenhao , Kaufmann Manuel , Li Chenhao , Li Chenhao , Kaufmann Manuel , Li Chenhao
Topics Engineering and Technology
Learning Real-time Human Motion Tracking on a Humanoid Robot
Humanoid robots, designed to mimic the structure and behavior of humans, have seen significant advancements in kinematics, dynamics, and control systems. Teleoperation of humanoid robots involves complex control strategies to manage bipedal locomotion, balance, and interaction with environments. Research in this area has focused on developing robots that can perform tasks in environments designed for humans, from simple object manipulation to navigating complex terrains. Reinforcement learning has emerged as a powerful method for enabling robots to learn from interactions with their environment, improving their performance over time without explicit programming for every possible scenario. In the context of humanoid robotics and teleoperation, RL can be used to optimize control policies, adapt to new tasks, and improve the efficiency and safety of human-robot interactions. Key challenges include the high dimensionality of the action space, the need for safe exploration, and the transfer of learned skills across different tasks and environments. Integrating human motion tracking with reinforcement learning on humanoid robots represents a cutting-edge area of research. This approach involves using human motion data as input to train RL models, enabling the robot to learn more natural and human-like movements. The goal is to develop systems that can not only replicate human actions in real-time but also adapt and improve their responses over time through learning. Challenges in this area include ensuring real-time performance, dealing with the variability of human motion, and maintaining stability and safety of the humanoid robot.
Keywords
real-time, humanoid, reinforcement learning, representation learning
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization ETH Competence Center - ETH AI Center
Hosts He Junzhe , Li Chenhao , Li Chenhao
Topics Information, Computing and Communication Sciences
Continuous Skill Learning with Fourier Latent Dynamics
In recent years, advancements in reinforcement learning have achieved remarkable success in teaching robots discrete motor skills. However, this process often involves intricate reward structuring and extensive hyperparameter adjustments for each new skill, making it a time-consuming and complex endeavor. This project proposes the development of a skill generator operating within a continuous latent space. This innovative approach contrasts with the discrete skill learning methods currently prevalent in the field. By leveraging a continuous latent space, the skill generator aims to produce a diverse range of skills without the need for individualized reward designs and hyperparameter configurations for each skill. This method not only simplifies the skill generation process but also promises to enhance the adaptability and efficiency of skill learning in robotics.
Keywords
representation learning, periodic autoencoders, learning from demonstrations, policy modulating trajectory generators
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization ETH Competence Center - ETH AI Center
Hosts Li Chenhao , Rudin Nikita
Topics Information, Computing and Communication Sciences , Engineering and Technology
Handstands with a quadruped robot
Doing handstands (one arm and two legs) with a quadrupedal robot equipped with an arm using reinforcement learning. After getting into a stable upright position the next step will also be locomoting in this tripod configuration.
Keywords
reinforcement learning agile control quadrupedal robots
Labels
Master Thesis
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2024-11-26 , Earliest start: 2024-12-01
Applications limited to ETH Zurich
Organization Robotic Systems Lab
Hosts Cramariuc Andrei
Topics Information, Computing and Communication Sciences , Engineering and Technology
Universal Humanoid Motion Representations for Expressive Learning-based Control
Recent advances in physically simulated humanoids have broadened their application spectrum, including animation, gaming, augmented and virtual reality (AR/VR), and robotics, showcasing significant enhancements in both performance and practicality. With the advent of motion capture (MoCap) technology and reinforcement learning (RL) techniques, these simulated humanoids are capable of replicating extensive human motion datasets, executing complex animations, and following intricate motion patterns using minimal sensor input. Nevertheless, generating such detailed and naturalistic motions requires meticulous motion data curation and the development of new physics-based policies from the ground up—a process that is not only labor-intensive but also fraught with challenges related to reward system design, dataset curation, and the learning algorithm, which can result in unnatural motions. To circumvent these challenges, researchers have explored the use of latent spaces or skill embeddings derived from pre-trained motion controllers, facilitating their application in hierarchical RL frameworks. This method involves training a low-level policy to generate a representation space from tasks like motion imitation or adversarial learning, which a high-level policy can then navigate to produce latent codes that represent specific motor actions. This approach promotes the reuse of learned motor skills and efficient action space sampling. However, the effectiveness of this strategy is often limited by the scope of the latent space, which is traditionally based on specialized and relatively narrow motion datasets, thus limiting the range of achievable behaviors. An alternative strategy involves employing a low-level controller as a motion imitator, using full-body kinematic motions as high-level control signals. This method is particularly prevalent in motion tracking applications, where supervised learning techniques are applied to paired input data, such as video and kinematic data. For generative tasks without paired data, RL becomes necessary, although kinematic motion presents challenges as a sampling space due to its high dimensionality and the absence of physical constraints. This necessitates the use of kinematic motion latent spaces for generative tasks and highlights the limitations of using purely kinematic signals for tasks requiring interaction with the environment or other agents, where understanding of interaction dynamics is crucial. We would like to extend the idea of creating a low-level controller as a motion imitator to full-body motions from real-time expressive kinematic targets.
Keywords
representation learning, periodic autoencoders
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization ETH Competence Center - ETH AI Center
Hosts Li Chenhao , Li Chenhao , Li Chenhao
Topics Information, Computing and Communication Sciences , Engineering and Technology
Humanoid Locomotion Learning and Finetuning from Human Feedback
In the burgeoning field of deep reinforcement learning (RL), agents autonomously develop complex behaviors through a process of trial and error. Yet, the application of RL across various domains faces notable hurdles, particularly in devising appropriate reward functions. Traditional approaches often resort to sparse rewards for simplicity, though these prove inadequate for training efficient agents. Consequently, real-world applications may necessitate elaborate setups, such as employing accelerometers for door interaction detection, thermal imaging for action recognition, or motion capture systems for precise object tracking. Despite these advanced solutions, crafting an ideal reward function remains challenging due to the propensity of RL algorithms to exploit the reward system in unforeseen ways. Agents might fulfill objectives in unexpected manners, highlighting the complexity of encoding desired behaviors, like adherence to social norms, into a reward function. An alternative strategy, imitation learning, circumvents the intricacies of reward engineering by having the agent learn through the emulation of expert behavior. However, acquiring a sufficient number of high-quality demonstrations for this purpose is often impractically costly. Humans, in contrast, learn with remarkable autonomy, benefiting from intermittent guidance from educators who provide tailored feedback based on the learner's progress. This interactive learning model holds promise for artificial agents, offering a customized learning trajectory that mitigates reward exploitation without extensive reward function engineering. The challenge lies in ensuring the feedback process is both manageable for humans and rich enough to be effective. Despite its potential, the implementation of human-in-the-loop (HiL) RL remains limited in practice. Our research endeavors to significantly lessen the human labor involved in HiL learning, leveraging both unsupervised pre-training and preference-based learning to enhance agent development with minimal human intervention.
Keywords
reinforcement learning from human feedback, preference learning
Labels
Master Thesis
Description
Goal
Contact Details
More information
Published since: 2024-11-26
Organization ETH Competence Center - ETH AI Center
Hosts Li Chenhao , Li Chenhao , Chen Xin , Li Chenhao
Topics Information, Computing and Communication Sciences , Engineering and Technology
Online Safe Locomotion Learning in the Wild
Reinforcement learning (RL) can potentially solve complex problems in a purely data-driven manner. Still, the state-of-the-art in applying RL in robotics, relies heavily on high-fidelity simulators. While learning in simulation allows to circumvent sample complexity challenges that are common in model-free RL, even slight distribution shift ("sim-to-real gap") between simulation and the real system can cause these algorithms to easily fail. Recent advances in model-based reinforcement learning have led to superior sample efficiency, enabling online learning without a simulator. Nonetheless, learning online cannot cause any damage and should adhere to safety requirements (for obvious reasons). The proposed project aims to demonstrate how existing safe model-based RL methods can be used to solve the foregoing challenges.
Keywords
safe mode-base RL, online learning, legged robotics
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization ETH Competence Center - ETH AI Center
Hosts Li Chenhao , Li Chenhao , Li Chenhao , Li Chenhao
Topics Engineering and Technology
Autonomous Curriculum Learning for Increasingly Challenging Tasks
While the history of machine learning so far largely encompasses a series of problems posed by researchers and algorithms that learn their solutions, an important question is whether the problems themselves can be generated by the algorithm at the same time as they are being solved. Such a process would in effect build its own diverse and expanding curricula, and the solutions to problems at various stages would become stepping stones towards solving even more challenging problems later in the process. Consider the realm of legged locomotion: Training a robot via reinforcement learning to track a velocity command illustrates this concept. Initially, tracking a low velocity is simpler due to algorithm initialization and environmental setup. By manually crafting a curriculum, we can start with low-velocity targets and incrementally increase them as the robot demonstrates competence. This method works well when the difficulty correlates clearly with the target, as with higher velocities or more challenging terrains. However, challenges arise when the relationship between task difficulty and control parameters is unclear. For instance, if a parameter dictates various human dance styles for the robot to mimic, it's not obvious whether jazz is easier than hip-hop. In such scenarios, the difficulty distribution does not align with the control parameter. How, then, can we devise an effective curriculum? In the conventional RSL training setting for locomotion over challenging terrains, there is also a handcrafted learning schedule dictating increasingly hard terrain levels but unified with multiple different types. With a smart autonomous curriculum learning algorithm, are we able to overcome separate terrain types asynchronously and thus achieve overall better performance or higher data efficiency?
Keywords
curriculum learning, open-ended learning, self-evolution, progressive task solving
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization Robotic Systems Lab
Hosts Li Chenhao , Li Chenhao , Li Chenhao , Bagatella Marco , Li Chenhao
Topics Engineering and Technology
Humanoid Locomotion Learning with Human Motion Priors
Humanoid robots, designed to replicate human structure and behavior, have made significant strides in kinematics, dynamics, and control systems. Research aims to develop robots capable of performing tasks in human-centric settings, from simple object manipulation to navigating complex terrains. Reinforcement learning (RL) has proven to be a powerful method for enabling robots to learn from their environment, enhancing their performance over time without explicit programming for every possible scenario. In the realm of humanoid robotics, RL is used to optimize control policies, adapt to new tasks, and improve the efficiency and safety of human-robot interactions. However, one of the primary challenges is the high dimensionality of the action space, where handcrafted reward functions fall short of generating natural, lifelike motions. Incorporating motion priors into the learning process of humanoid robots addresses these challenges effectively. Motion priors can significantly reduce the exploration space in RL, leading to faster convergence and reduced training time. They ensure that learned policies prioritize stability and safety, reducing the risk of unpredictable or hazardous actions. Additionally, motion priors guide the learning process towards more natural, human-like movements, improving the robot's ability to perform tasks intuitively and seamlessly in human environments. Therefore, motion priors are crucial for efficient, stable, and realistic humanoid locomotion learning, enabling robots to better navigate and interact with the world around them.
Keywords
motion priors, humanoid, reinforcement learning, representation learning
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization ETH Competence Center - ETH AI Center
Hosts Li Chenhao , Li Chenhao , Li Chenhao , Li Chenhao
Topics Information, Computing and Communication Sciences
Learning World Models for Legged Locomotion
Model-based reinforcement learning learns a world model from which an optimal control policy can be extracted. Understanding and predicting the forward dynamics of legged systems is crucial for effective control and planning. Forward dynamics involve predicting the next state of the robot given its current state and the applied actions. While traditional physics-based models can provide a baseline understanding, they often struggle with the complexities and non-linearities inherent in real-world scenarios, particularly due to the varying contact patterns of the robot's feet with the ground. The project aims to develop and evaluate neural network-based models for predicting the dynamics of legged environments, focusing on accounting for varying contact patterns and non-linearities. This involves collecting and preprocessing data from various simulation environment experiments, designing neural network architectures that incorporate necessary structures, and exploring hybrid models that combine physics-based predictions with neural network corrections. The models will be trained and evaluated on prediction autoregressive accuracy, with an emphasis on robustness and generalization capabilities across different noise perturbations. By the end of the project, the goal is to achieve an accurate, robust, and generalizable predictive model for the forward dynamics of legged systems.
Keywords
forward dynamics, non-smooth dynamics, neural networks, model-based reinforcement learning
Labels
Master Thesis
Description
Contact Details
More information
Published since: 2024-11-26
Organization Robotic Systems Lab
Hosts Li Chenhao , Li Chenhao , Li Chenhao , Klemm Victor , Li Chenhao
Topics Engineering and Technology
DigGPT: Large Language Models for Excavation Planning
Large language models (LLMs) have shown the first sparks of artificial general intelligence. We want to test if GPT 4.0 can solve excavation planning problems.
Keywords
GPT, Large Language Models, Robotics, Deep Learning, Reinforcement Learning
Labels
Semester Project , Master Thesis
Description
Work Packages
Requirements
Contact Details
More information
Published since: 2024-11-21 , Earliest start: 2025-01-01 , Latest end: 2025-08-31
Organization Robotic Systems Lab
Hosts Terenzi Lorenzo
Topics Engineering and Technology
VR in Habitat 3.0
Motivation: Explore the newly improved Habitat 3.0 simulator with a special focus on the Virtual Reality Features. This project is meant to be an exploration task on the Habitat 3.0 simulator, exploring all the newly introduced features focusing specifically on the implementation of virtual reality tools for scene navigation. The idea is to extend these features to self created environments in Unreal Engine that build uppon Habitat
Labels
Semester Project
Contact Details
More information
Published since: 2024-11-06 , Earliest start: 2024-01-08
Applications limited to University of Zurich , Swiss National Science Foundation , ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne
Organization Computer Vision and Geometry Group
Hosts Blum Hermann , Bauer Zuria, Dr. , Sun Boyang , Zurbrügg René
Topics Information, Computing and Communication Sciences
Generalist Excavator Transformer
We want to develop a generalist digging agent that is able to do multiple tasks, such as digging and moving loose soil, and/or control multiple excavators. We plan to use decision transformers, trained on offline data, to accomplish these tasks.
Keywords
Offline reinforcement learning, transformers, autonomous excavation
Labels
Semester Project , Master Thesis
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-10-11 , Earliest start: 2025-01-01 , Latest end: 2025-08-31
Organization Robotic Systems Lab
Hosts Werner Lennart , Egli Pascal Arturo , Terenzi Lorenzo , Nan Fang , Zhang Weixuan
Topics Information, Computing and Communication Sciences
Novel Winch Control for Robotic Climbing
While legged robots have demonstrated impressive locomotion performance in structured environments, challenges persist in navigating steep natural terrain and loose, granular soil. These challenges extend to extraterrestrial environments and are relevant to future lunar, martian, and asteroidal missions. In order to explore the most extreme terrains, a novel winch system has been developed for the ANYmal robot platform. The winch could potentially be used as a fail-safe device to prevent falls during unassisted traverses of steep terrain, as well as an added driven degree of freedom for assisted ascending and descending of terrain too steep for unassisted traversal. The goal of this project is to develop control policies that utilize this new hardware and enable further climbing robot research.
Keywords
Robot, Space, Climbing, Winch, Control
Labels
Semester Project , Master Thesis , ETH Zurich (ETHZ)
PLEASE LOG IN TO SEE DESCRIPTION
More information
Published since: 2024-09-27 , Earliest start: 2024-10-07
Organization Robotic Systems Lab
Hosts Vogel Dylan
Topics Information, Computing and Communication Sciences , Engineering and Technology
Student Theses in Industry
We have a large number of industry partners who search for excellent students to conduct their student theses at the company or at ETH but in close collaboration with them (joint supervision by industry and ETH).
Ammann Group (Switzerland)
The Ammann Group is a worldwide leader in the manufacture of mixing plants, machinery, and services in the construction industry, with core competence in road construction and landscaping as well as in the transport infrastructure.
We are collaborating with Ammann to automate construction equipment
Maxon (Switzerland)
Maxon develops and builds electric drive systems that are among the best in the world. Their drive systems can be found wherever extreme precision and the highest quality standards are indispensable – on Earth, and on Mars.
Shunk (Germany)
Legged Wheel Chair
This project aims at extending a dynamic simulation and locomotion controllers for a robotized wheelchair able to handle difficult terrains including stairs. This project will prepare the prototype phase coming next.
.
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