Recent work in legged robotics shows the promise of unified control strategies for whole-body control. Portela et al. (2024) demonstrated force control without force sensors, enabling compliant manipulation through body coordination. In another study, they achieved accurate end-effector tracking using whole-body RL with terrain-aware sampling. Fu et al. (2023) showed that unified policies can dynamically handle both movement and manipulation in quadruped robots by training with two critics: one for arms, and one for legs, and then gradually combining them.
In this project, you will investigate reinforcement learning for whole body control of a bimanual legged manipulator. You will implement a baseline single-critic whole body controller for the system. You will then investigate different multi-critic approaches and their effects on the training and final performance of the whole-body controller.
References:
Learning Force Control for Legged Manipulation, Portela et al., 2024
Whole-Body End-Effector Pose Tracking, Portela et al., 2024
Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion, Fu et al., 2023 - Robotics and Mechatronics
- Master Thesis, Semester Project
|
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 - Information, Computing and Communication Sciences
- Master Thesis, Semester Project
|
Recent advancements in AI, particularly with models like Claude 3.7 Sonnet, have showcased enhanced reasoning capabilities. This project aims to harness such models for excavation planning tasks, drawing parallels from complex automation scenarios in games like Factorio. We will explore the potential of these AI agents to plan and optimize excavation processes, transitioning from simulated environments to real-world applications with our excavator robot. - Engineering and Technology
- Master Thesis, Semester Project
|
Master thesis on novel devices and tools for both valve repair and replacement at Harvard Medical School - Engineering and Technology, Medical and Health Sciences
- Master Thesis
|
We are developing robotic catheters for heart valve repair and for treatment of arrythmias. - Engineering and Technology, Medical and Health Sciences
- Master Thesis
|
Three-dimensional medical imaging techniques such as Computed Tomography (CT) and MRI are indispensable in modern clinical workflows. CT utilizes X-rays acquired from multiple angles to reconstruct detailed volumetric patient anatomy data. Due to the harmful effects of ionizing radiation, especially in vulnerable populations such as infants, it is critical to minimize radiation exposure while maintaining diagnostic image quality.
Optimizing CT parameters requires systematic studies, yet direct experimentation on infants is ethically and medically unacceptable. This project aims to develop a novel infant head phantom that accurately replicates the radiological properties of an infant’s head. The phantom will serve as a testbed for CT imaging studies, enabling the optimization of scan parameters that balance minimal radiation exposure with high-quality image acquisition tailored for pediatric neuroimaging.
- Biomedical Engineering, Manufacturing Engineering, Materials Engineering, Mechanical and Industrial Engineering
- ETH Zurich (ETHZ), Master Thesis, Semester Project
|
Our project aims to enhance the ultrasound-assisted bioprinting process using real-time feedback and image processing. We have developed a transparent nozzle equipped with multiple cameras for real-time monitoring. The next steps involve integrating advanced image processing techniques, such as template matching, and implementing a feedback system to optimize the printing process. The system will be fully automated, featuring a function generator for wave creation and cooling elements. By analyzing the printing process and acoustic cell patterning with computer vision and leveraging real-time sensor feedback, we aim to dynamically optimize parameters such as frequency and amplitude for accurate and consistent pattern formation, crucial for bio applications. - Artificial Intelligence and Signal and Image Processing, Behavioural and Cognitive Sciences, Computation Theory and Mathematics, Computer Software, Engineering and Technology, Information Systems, Medical and Health Sciences
- Bachelor Thesis, Master Thesis
|
Enable Birds-Eye-View perception on autonomous mobile robots for human-like navigation. - Computer Vision, Intelligent Robotics, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Pattern Recognition, Photogrammetry and Remote Sensing
- ETH Zurich (ETHZ), Master Thesis
|
Elevate semantic scene graphs to a new level and perform semantically-guided navigation and interaction with real robots at The AI Institute. - Computer Vision, Engineering and Technology, Intelligent Robotics, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Pattern Recognition
- ETH Zurich (ETHZ), Master Thesis
|
Predicting the failure mechanisms of low-density cellular solids, from random fiber networks to periodic
architected materials (or metamaterials), remains a challenge for computational mechanics. One fundamental
distinction between beam-based architected materials and classical homogeneous solids lies in
the nature of their failure. Unlike classical materials, beam-based architected materials fail through the
discrete breaking of individual beams. This results in complex patterns of crack initiation and propagation,
that are significantly different from those observed in classical materials.
As computational models for large-scale, manufacturable metamaterials often involve millions or even
billions of unknowns, we are developing an open-source C++ library for scalable finite element simulations.
Currently, this library leverages distributed computing on CPUs via Open MPI, utilizing ETH
Zurich’s Euler cluster. The goal of this project is to improve simulation performance for predicting failure
in large-scale beam networks. A key focus will be integrating Nvidia’s GPU accelerators to achieve
significantly enhanced computational efficiency beyond what distributed CPU computing alone can provide.
Throughout this project, the student will contribute to an open-source project, conduct in-depth
performance studies, and utilize the developed software to predict fracture behavior in novel materials
with different (multi-)material properties, including both linear elastic and plastic regimes. - Mechanical Engineering, Numerical Analysis
- ETH Zurich (ETHZ), Master Thesis, Semester Project
|
