Multi-Contact Motion Planning
The goal of this project is to develop a motion-planning algorithm for our quadruped ANYmal. Our robot should be able to use multiple contact points on the feet, knees, and belly for locomotion. To find effective motions plans in such scenarios,we want to combine our planner with a physics simulator
Development of a computational model of the human pelvic plexus nerves to design a neural interface for bioelectronic device treating erectile dysfunction
Nearly 30% of erectile dysfunction patients do not respond to drug treatments and to achieve erection, these patients mostly rely on intra-penile injections. We propose the development of a subcutaneously implantable bidirectional neurostimulation system to restore erectile functions.
Acoustophoretic particle manipulation for cell secretome analysis
High throughput analysis of cell secretome using mass spectrometry is a major goal in microbiology. In this project, steps towards reaching this goal using acoustophoretic devices are investigated.
Improving the resolution of metal 3D printing by means of acoustophoresis
Metal 3D-printing is limited in minimal feature size. In this project, acoustofluidic is utilized to make a huge step in improving the minimal feature size of laser powder deposition 3D printing.
Conducting Rehabilitation Studies with ARMin V
Recrute and supervise a designed therapist-orientated study to further increase usability of the robotic rehabilitation device ARMin V. The study will contain ca. 15 physiotherapists and the measurements will be taking place at the Balgrist Campus and Clinic Lengg.
Crystallization fouling and rational design of intrinsically scale-phobic surfaces
Crystallization fouling due to mineral scale formation on industrial devices is associated with equipment failures and increased energy consumption. We will attempt to understand the fundamentals of scale nucleation on nanoengineered substrates with advanced experimental methods.
Post-Doc in Wearable and Embedded Systems (IoT)
Our interdisciplinary team seeks a post-doctoral fellow for strengthening our efforts in developing wearable biomedical devices.
Project in mobile health systems
Develop and test personalized and efficient methods, devices and systems that can be used by anyone at the point-of-care to increase our ability to diagnose, monitor, prevent and treat major global health issues.
Real-Time Epileptic Seizure Detection by Deep Learning on EEG Data
In this master thesis you will develop machine learning algorithms to automatically detect and predict epileptic seizures in real-time.
Design of a tendon-based robotic device for locomotion training
The proposed project aims at designing a novel tendon-based parallel robotic device for locomotion training that can guide or resist the patients’ movements during training.
Fingertip 6-axis force sensor for robotic grasping and manipulation
Grasping and Manipulation of unknown objects in robotics requires forces to be detected in a precise and robust way. Goal of this project is to design state of the art solution for contact detection in such applications.
A Perfusion System for Vascularized In-Vitro Skin Models
This interdisciplinary project focuses on the development of a perfusion system for vascularized in-vitro skin models.
An Automated System for Skin Model Production
This interdisciplinary project focuses on the development of an automated system for skin model production.
Multi-Sensor Continuous-Time SLAM for UAVs
The goal of this project is a continuous-time incremental trajectory estimation and mapping formulation for multiple sensors on-board of fixed-wing or rotary-wing UAVs
Development of a microspine gripper for ANYmal
The goal of this project is to investigate the feasibility of a microspine based gripper. The basic gripping principle will be implemented in a gripper, foot for ANYmal or custom climbing robot.
Design and development of prehensile feet for ANYmal
The goal of this project is to prototype a prehensile foot that will be used on ANYmal. The final goal is to allow ANYmal to manipulate objects using the same actuation usually dedicated to locomotion.
Real-time Dynamic Scene Reconstruction
Autonomous interaction in real-world environments requires robots to build an internal representation of the observed scene and the objects therein. The goal of this project is to integrate efficient tracking of multiple (potentially) moving objects into an existing scene reconstruction framework.
Line Clustering and Description for Place Recognition
The goal of this project is to develop a place recognition pipeline using RGB-D or stereo cameras, by extracting line clusters.
Fabrication and testing of composite sandwich structures with load-tailored lattice cores
Motivated by the potential to increase the performance of composite lattice core (CLC) sandwich structures through load-tailored core topologies, the goal of this thesis is to fabricate and experimentally characterize optimized CLC sandwich structures for multi-axial load cases.
Mechatronic Design of a Wheel Electrode Sensor for Robotic Inspection
The goal of this project is to design, build, and integrate a light-weight wheeled electrochemical sensor on a flying robot, and test its ability to evaluate the state of concrete infrastructure
Learning to paint with an autonomous spray painting UAV
PaintCopter [1] is an autonomous UAV capable of spray painting on complex 3D surfaces. Currently the system is capable of painting basic elements such as lines, gradients and area-fill with a color of choice (see Fig.b). The motivation for this project is to find a way to decompose a provided textur
Evaluation of an Industrial Exoskeleton
Workers in industries such as construction and logistics execute physically demanding jobs every day. Over time, these tasks put workers at a high risk of injury. To mitigate these risks, we are developing wearable assistive exoskeletons that support and protect workers.
Development of a mechanical exoskeleton for construction workers.
Workers in industries such as construction are executing physically demanding jobs every day. Over time, these tasks put workers at a high risk of injury. To mitigate these risks, we are developing wearable assistive exoskeletons that support and protect workers.
Development of a sensor-based workload assessment for an industrial exoskeleton.
Workers in industries such as construction and logistics are executing physically demanding jobs every day. Over time, these tasks put workers at a high risk of injury. To assess this risk, you will develop a wearable, sensor-based workload assessment tool.
Clean room fabrication process optimization for small structures
Special acoustofluidic devices demand for small strucutres. In this project the used clean room processes are optimized to achieve an improvement in minimal feature size.
Deep learning enhanced trinocular depth optimization for obstacle avoidance onboard of a fixed-wing UAV
The goal of this project is to combine classical geometric with deep learning based depth estimation for binocular and trinocular camera setups
Smoking Lung Prototype for Cell Culture
Interdisciplinary project for the development of an automated smoking machine for biological cell tests
Numerical Investigations of Stent Folding and Deployment for Fetal Membrane Repair
The aim is to develop an efficient finite element (FE) based numerical model of a Nitinol stent which will be used for fetal membrane repair after surgery. More info in the PDF file.
Control Algorithm Development for a Series Elastic Actuated Exoskeleton
Robot-assisted therapy of stroke patients is a promising approach to improve the therapy outcome and to tackle the challenges of demographic ageing. Using a novel 6 DoF exoskeleton prototype, we want to investigate/develop new control strategies for the next generation of these robots.
Redesign of a Robotic Articulated Endoscope with Series Elastic Actuation
In this project you will redesign and extend an existing articulated endoscope. The focus lies on integrating series elastic elements in the actuation and implementing stable force control.
Werde Teil eines Bildungsprojekts für nachhaltige Entwicklung!
Werde Teil von “WeltFAIRsteher”, dem Bildungsprojekt für nachhaltige Entwicklung, das deine Ideen in den Schulalltag bringt.
Collaborative Virtual/Mixed Reality using Hololens/ARKit/ARCore
The goal is to develop an interface to easily extract mapping data from Hololens to be used in the open source mapping framework maplab. The project will then look into novel techniques to improve pose-estimation, 3D reconstruction or co-localization between devices.
Adding Illusions to Surgical Training Simulators
Pilots have been using simulators for years in order to get practical experience in a safe and repeatable way. Doctors have begun using simulators instead of practicing on patients. You will use Human Factors, System Design, and Statistics to test and verify the effect of haptic illusions in sims.
Design automation of flow structures for additive manufacturing
Additive manufacturing allows to fabricate structures with complex geometries. This project focuses on the automated design generation of mixers and extruders. Based on an existing framework the goal is to implement and test further features.
The influence of curing parameters on the cured shape of thermally stressed ultra-thin prepreg material
This work shall investigate the effect of curing parameters on the cured shape of ultra-thin CFRP laminates.
Artifact Detection in Challenging Conditions
Detecting artifacts in challenging environments using a multimodal sensor setup. The goal is to design robust artifact detection deep neural networks that can operate in challenging conditions with respect to illumination and other noise sources such as dust and smoke.
Developing of Adaptable Compliant Mechanism with Additive Manufacturing
Additive Manufacturing, Prostheses, Compliant Mechanism, Biomechanical Engineering
Simulation Validation and Redesign of a Die Casting Mold
A local control of the heat balance in die casting tools enables robust processing, faster cycle times as well as longer die lifetimes. With new manufacturing capabilities such as Additive Manufacturing (AM), engineers have almost unlimited possibilities to design cooling structures. To facilitate a
Additive Manufacturing: Towards feature recognition algorithms
This work will focusing on pre-processing possibilities to better adapt the SLM process to the geometry being manufactured. By developing feature recognition algorithm, the student will be able to divide the part in several volumes and scan them with different scanning strategies. See pdf attached.
Physiological pressures and interdependencies in different body compartments
- Interdisciplinary research in biomedical engineering - Analytical investigation of the interdependencies of the various body compartments - Collaboration between the Institute of Physiology at the University of Zurich and the Product Development Group Zurich at ETH Zurich
Mass Transport Across Atomically-Thin Nanoporous Membranes
Selective transport across nanopores is present in fields ranging from ion channels in biological cells to industrial scale water desalination and gas separation. We study nanofluidic transport across nanopores at the limit of membrane thinness with the single-atom-thin membrane material graphene.
Development and testing of a SLM manufactured component for the next generation of superconducting particle accelerator
Two famous international research organizations are working on the next generation of a superconducting particle accelerator. This thesis focuses on a specia lcompone of the particle accelerator. Currently, this element is manufactured using milling. However, due its complex geometry, it is desirabl
Plasmonic materials for photothermal therapy of cancer
A promising strategy to fight cancer is to locally heat up tumor tissue with the use of light-absorbing nanoparticles, also called photothermal therapy. Here, novel cost-effective plasmonic materials are developed, optimized and tested.
Development of new fluorescent nanoparticles for bioimaging
Fluorescent nanomaterials can be used for non-invasive imaging of biological tissue. However, the currently available materials do not yet meet the requirements for deep-tissue imaging. Therefore, this projects aims to develop novel luminescent nanoparticles operating in the near-infrared region.
Developing force sensitive climbing foot for ANYmal robot
Development of fully integrated force sensitive sensors that comply with the common real-time communication protocols used in robotics. These sensors gives robots the ability to sense and interact safer with the environment and humans enabling them to perform human-like tasks (surgical,collaborative
High-speed Augmented Realty with Event-based Cameras
The goal of this project is to achieve high-speed camera pose tracking of a single event-based camera to enable their application in virtual reality. The event-camera will detect and track features that are discovered on-the-fly from a a priori unknown scene.
Optimization of Large-Scale Visual Map
Visual localization in the UP-Drive project requires curating large visual maps of several square kilometers. These maps have several millions of landmarks and require large time and memory resources to optimize. This thesis addresses this scalability problem by converting landmark - pose constraint
Bubble-powered soft acoustomagnetic microrobots
The newly designed microrobot consists of a cavity at the center of its body and superparamagnetic particles within the polymer matrix. The microcavity supports an air-bubble trap, which enables propulsion in an acoustic field, and the magnetic particles allow controlled motion in a magnetic fiel
The acoustic nanoswimmer
We develop a new class of nanoswimmer, which propels through aqueous solution by small-amplitude undulation of flexible tail in a predominant travelling acoustic waves.
Autonomous, Information-Based Radiation Mapping using a UAV
The goal of this problem is to develop and implement a exploration and mapping strategy for autonomous radiation mapping using a small Unmanned Aerial vehicle (UAV), equipped with visual, inertial and radiation sensors onboard.
Optical Flow Estimation with an Event Camera
The goal of this project is to use event cameras to compute the optical flow in the image plane induced by either a moving camera in a scene or by moving objects with respect to a static event camera.
Visual Bundle Adjustment with an Event Camera
The goal of this project is to improve an existing visual odometry pipeline using an event camera by designing and integrating a visual bundle adjustment module in order to reduce the drift in the odometry pipeline.
Event Camera Characterization
Event cameras such as the Dynamic and Active Pixel Vision Sensor (DAVIS) are recent sensors with large potential for high-speed and high dynamic range robotic applications.
Building a high-speed camera! Learning Image reconstruction with an Event Camera
The goal of this project is to turn an event camera into a high-speed camera, by designing an algorithm to recover images from the compressed event stream.
A Visual-Inertial Odometry System for Event-based Vision Sensor
The goal of this project is to develop visual-inertial pipeline for the Dynamic and Active Vision Sensor (DAVIS). The system will estimate the pose of the DAVIS using the event stream and IMU measurements delivered by the sensor.
Wide-Baseline Place Recognition for SLAM
The goal of this project is to integrate an existing place recognition system that was already proven to work well for images captured from very wide baselines (e.g. air-ground images) into a state-of-the-art keyframe-based visual-inertial odometry system to effectively correct the effects of drift
Data-driven design of metamaterials with tunable properties
This project focuses on the computational design of a new class of cellular metamaterials using data-driven techniques and machine learning.
Decoding leg and foot motor intentions from amputee’s sciatic nerve recordings for neuroprosthesis application
Advanced neuroprosthesis provide a sensory feedback, increasing substantially the efficiency of the system; combining this with a complex motor-control decoding will generate a more natural and efficient control of the artificial limb.
Characterization of two-phase granular systems using Magnetic Resonance Imaging
The primary objective of this PhD project is to apply ultra-fast Magnetic Resonance Imaging to single- and two-phase granular systems (e.g. suspension or fluidized beds) to elucidate the underlying physics of a number of poorly understood phenomena.
Autonomous Radiation Mapping using mutliple UAVs
The goal of this project is to extend and further develop a tool for autonomous radiation mapping using multiple small Unmanned Aerial Vehicles (UAVs), equipped with visual, inertial and radiation sensors onboard, as well as GPS.
Biomechanical analysis and signal processing of data from transfemoral amputees with a sensorized bionic leg
Sensory feedback from the lower limbs is essential for the correct balance and symmetry during the walking. Lower limb amputees suffer the complete lack of sensory feedback from current available prostheses which excludes central nervous system from the correct sensory-motor integration.
Magnetic Resonance Imaging of CO2 capture reactors
Carbon capture and storage is anticipated to play a central role in curbing carbon dioxide emission to the atmosphere and counteracting climate change. Here you will design and build several model reactors for the next generation carbon capture technology.
Incorporating on-line measurements into deep neural network predictions for estimating wind near terrain with a fixed-wing UAV
This project will develop methods for predicting wind near terrain during flight with a fixed-wing UAV. In particular, this work will focus on incorporating wind measurements from the UAV into the prediction model in-flight. This will require exploring new methods and architectures for deep learning
Characterization of a chromatographic separation as a unit of an integrated continuous process
The main goal of the project is to investigate the SMB separation and to assess its performance, by characterizing the adsorption behavior of the desired compound on the chosen stationary phase and by defining the operating conditions for the separation by means of the triangle theory.
Real-Time Deep Semantic SLAM
The goal of this project is to develop an object-level semantic SLAM system. The student will combine approaches from both SLAM and deep learning to develop a semantically-meaningful SLAM system.
Development of a miniaturized actuation system for pulsatile Ventricular Assist Devices (pVADs)
Miniaturization of the actuation system is of major importance in order to allow pulsatile VADs being fully implanted into the human body. In this project novel actuation systems will be explored aiming to an actuator of reduced size and power consumption.
Tool-changing Laparoscope for Reducing the Surgery Duration
Time is an important factor for patient health in surgery. The required duration of anaesthesia administration represents a burden for the patient’s health and is directly correlated to the patient’s recovery time. In this context, development of surgical tools that reduce required surgery time woul
Design and Evaluation of a Measurement Probe for Contact-Forces in Minimally Invasive Knee Surgery
One of the main challenges when developing robotic tools for minimally invasive surgery are unknown mechanical requirements. Your task will be to develop a measurement probe which can measure the contact forces between the surgical instrument and the surrounding tissue in the knee.
Technology based assessment of upper limb function during the rehabilitation of neurological patients
The Virtual Peg Insertion Test (VPIT) is a novel tool to measure upper limb function. It can provide quantitative information during the rehabilitation of neurological patients that can help to better understand the motor recovery process or the effect of therapeutic interventions.
Locomotion in small tunnels
The aim of this student project is to extend our locomotion framework to enable ANYmal, a quadruped robot, passing through a small tunnel.
Model Identification and Control for Near- and/or Post-stall Maneuvering with Fixed-wing UAVs
Understanding the boundaries and characteristics of the stall regime is critical for small fixed-wing UAVs. This project aims to identify a near/post-stall model for an ASL test aircraft and subsequently design a controller either preventing or exploiting the stall regime for short-field landings.
How does perturbing the knee modify kinematic variability and dynamic stability during walking?
Although humans are very good at maintaining balance while walking, how it is achieved is poorly understood. Our goal is to better understand dynamic balance control by describing responses to perturbations to the gait pattern, for example, by locking the knee joint during swing phase. In this project, you will assess the effects of knee locking on kinematic variability as well as dynamic stability during walking.
Experimental Human Knee Joint Impedance Estimation
Variable impedance actuators are used in many gait assistive devices. However, the unimpaired human knee joint impedance is unknown. This project will use an existing actuated knee brace to estimate the joint's impedance throughout the gait cycle in unimpaired human subjects.
Topological studies in realistic microvascular networks
The cortical vasculature is at the basis of nutrient supply in the brain. Nonetheless, our knowledge of the topological structure of realistic microvascular networks is still limited. The aim of this project is to improve our understanding of differences in vascular densities.
A new device for investigating thermal properties of additive manufacturing materials
Please refer to description/attached file
Investigating multiple force patches applied on the heart's epicardium
External ventricular assist devices might be the number one treatment for patients suffering from heart failure in the future. We are using both numerical methods and experiments to investigate open questions and to improve our prototype‘s design. Student projects are conceivable in different fields
Hand-Eye Calibration Toolbox
Hand-Eye calibration is a paramount pre-processing stage of many robotic and augmented reality applications. The goal of this project is to develop a user-friendly hand-eye calibration toolbox integrated with our robotic system.
Integrated Multi-Camera Calibration Toolbox
Camera calibration is a paramount pre-processing stage of many robotic vision applications such as 3D reconstruction, obstacle avoidance and ego-motion estimation. The goal of this project is to develop a user-friendly, single and multi-camera calibration toolbox adapted to our robotic system.
Visual-Inertial Multi-Robot Relative Pose Estimation
The goal of this project is to experiment and improve our recent multi-robot pose estimation algorithm. The student will be able to develop innovative ways for robots collaboratively perform tasks such as manipulation and inspection.
Structural coloration with resonant plasmonic nanoparticles generated via ultra-short pulsed LASER ablation
A ultra-short pulsed laser system will be used to generated nano-particle with different sizes. This gives the opportunity to color metallic surfaces only by changing the laser parameters.
Path-Planning for Autonomous Robot Navigation in Construction Sites
The goal of this project is to implement an optimization-based path planner for different robots in order to perform autonomous navigation and obstacle avoidance in construction sites.
Meta-study on Laser induced periodic Surface Structures (LIPSS)
see pdf announcement
Robustify Decision Boundaries in Deep Learning
Deep learning is part of more and more solutions in modern robotics. However, neural networks are not at all robust to conditions not seen during their training. This project explores ways to robustly use learning systems on robots in unfamiliar environments and with failing sensors.
Learning Control for a Soft Pneumatic Arm
Exploring model-based learning control approaches to achieve accurate position control with a pneumatically actuated soft robotic arm.
Construction robotics
Many tasks in the construction industry are repetitive and can be dangerous for human workers. We plan to develop robotic systems that can safely navigate and collaborate in these environments.
Numerical Investigation of Interface Failure in Thermoplastic Composite Lattice Core Sandwich Structures
The objective of this thesis is to develop numerical models capable of predicting the post-failure response of ultra-lightweight composite lattice core sandwich structures with thermoplastically welded core-to-facesheet interfaces.
Load-tailored Placement of Additively Manufactured Facesheet Stringers for Enhanced Performance of Composite Lattice Core Sandwich Structures
The objective of this thesis is to investigated the attainable performance increase of composite lattice core sandwich structures under multi-axial load cases through the load-tailored placement of additively manufactured facesheet reinforcements.
Piezoelectric scaffold using 3D stereolithography
Tissue engineering is a growing field of research aiming at the manufacture and repair of tissue. We are investigating the culture of bone cells in piezoelectric 3D scaffolds, manufactured with stereolithography printing technology.
Development of new preheating and impregnation techniques for the thermoplastic pultrusion process.
The objective of this thesis is to investigate new concepts how to effectively preheat thermoplastic composites and improve their impregnation quality during the thermoplastic pultrusion process. To validate the concept, a demonstrator preheating and impregnation stage will be designed and built.
Experimental investigation and numerical simulation of residual stresses in pultruded high performance composites.
The objective of this thesis is to investigate the formation of residual stresses in high performance thermoplastic composites and their influence on the material performance. The experimental approach and results will be validated through material testing and a thermomechanical FEM model.
Hybrid microrobots for biomedical applications
Development of hybrid microrobots, composed of magnetic nanoparticle composites incorporated in hydrogels, for active agents and biomolecules delivery in vitro.
Low-Latency Quadrotor Control for High-Speed, Agile Flight
Perception latency often represents a limitation for the achievable agility of an autonomous robot. Faster sensors and low-latency processing would allow to obtain more agile robots. The goal of this project is to explore low-latency, event-based cameras for closed-loop, high-speed quadrotor control
Evaluating the reliability and validity of a sensor-based assessment of upper limb function
The objective of this project is to quantitatively evaluate, in healthy subjects, the reliability and validity of sensor-based assessments of upper limb function implemented on the ArmeoSenso system.

Powered by  SiROP - the academic career network