Semester Project

Main content

Semester Projects at IRIS

ETH Zürich is using SiROP to publish and search scientific projects. With your university login you get free access to internships, scientific projects, Bachelor’s and Master’s theses. For more information please visit sirop.org.

Jul 19, 2017

Robotic Endoscope for Laser Osteotomy

In this project, you will support our interdisciplinary team in stabilizing and controlling the end-effector of a robotic endoscope which is guided by a serial robot.

Read more 

Jul 19, 2017

Visual-inertial navigation on a quadruped robot using Google Tango

The goal of this project is to use Google Tango to enable teach and repeat applications on RSL’s highly agile quadruped ANYmal.

Read more 

Jul 17, 2017

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 fi ...

Read more 

Jul 16, 2017

Development of an intelligent single-leg testbench

Develop a intelligent single-leg testbench for validation of sensors and applied machine learning.

Read more 

Jul 16, 2017

Development of a new type of force sensor

In this project we are going to investigate how to integrate force sensing capability directly into structural elements of a legged robot.

Read more 

Jul 13, 2017

Monocular Initialization from Small Motion

The project aim to develop algorithms to initialize monocular visual odometry from small motion.

Read more 

Jul 13, 2017

Feature Tracking/Matching in Dynamic Scenes

The project aims to develop algorithms for robust feature tracking/matching in dynamic environments.

Read more 

Jul 10, 2017

Impact of High-Performance Imaging on SLAM

The goal of this work is to evaluate the influence of high resolution, high frame rate and/or multi view imaging on the accuracy of Simultaneous Localization and Mapping (SLAM) algorithms. A motion tracking system is used to measure the performance of our custom built visual-inertial hardware.

...

Read more 

Jul 10, 2017

Joystick actuation for remote control or force feedback

The student should develop a device that is capable of moving a regular joystick of an excavator such that the excavator could be remote controlled . This device could also be used to enable force feedback on such a joystick.

Read more 

Jul 6, 2017

Somnomat: an Actuated Bed to Improve Sleep

A good night’s sleep is one of the most important factors influencing health and wellbeing. Within the SOMNOMAT project we are developing actuated beds that improve the sleep Quality of their us.

Read more 

Jul 6, 2017

Effect of Vestibular Stimulation on Dreaming and Meta Awareness

In a sleep study we are investigating whether gentle rocking movements can promote sleep in elderly people. It is known that vestibular stimulation can influence our bodily awareness and perception of self. Your task will be to investigate whether vestibular stimulation influences dream content ...

Read more 

Jul 6, 2017

Data Analysis of Anti-Snoring Intervention Study

Within the SOMNOMAT project we are developing smart beds which acquire physiological signals and react to them by providing a suitable intervention, such as positional therapy for snorers. To test our beds a sleep study was carried out. We are looking for two students to help analyze the sound ...

Read more 

Jul 4, 2017

Evaluating the Performance of Communication Software for Real-Time Robotics Applications

The objective of this project is to design and implement a benchmark in order to evaluate and compare the performance of state-of-the-art software frameworks for Inter-Process Communication (IPC) which are widely used in the field of robotics.

Read more 

Jul 4, 2017

Design and actuation of bistable structures for medical applications

Bistable structures are structures that exhibit two different equilibrated configurations. Energy for their actuation is thus only required to switch from one configuration to the other, which make them more energy efficient than classical solutions. Our team is currently investigating the use of ...

Read more 

Jun 30, 2017

Large-scale Dense Scene Reconstruction from Multiple UAVs

The goal of this project is to develop a system that generates a dense 3D reconstruction of a scene from camera image streams from multiple Unmanned Aerial Vehicles (UAVs)

Read more 

Jun 30, 2017

Machine learning for multicopter based semantic mapping

This project looks at the integration of pixel and object wise semantic classification into an existing 3D dense mapping infrastructure. The system will run online onboard a multicopter as it explores an area.

Read more 

Jun 30, 2017

Collaborative Map Building and Localization using Multiple UAVs

The goal of this project is to develop a system that generates a 3D map out of data collected by multiple Unmanned Aerial Vehicles (UAVs), and subsequently allows multiple UAVs to localize in this pre-built map.

Read more 

Jun 29, 2017

Large Scale Stone Aggregation

This project is about autonomous object aggregation with a walking excavator. The goal is to explore, implement, and evaluate methods for discrete object assembly on a full scale construction machine.

Read more 

Jun 29, 2017

Modelling and Simulation of 3-Phase PMSM-Based Actuators

The objective of this project is to develop a model and tool for simulating the effects of electric motor dynamics on legged systems using actuators incorporating Permanent Magnet Synchronous Motors (PMSMs), a generalized version of common DC Brushless (BLDC) motors.

Read more 

Jun 29, 2017

Using Machine-Learning to Learn Models of 3-Phase PMSM Actuator Dynamics

The objective of this project is to apply Machine-Learning techniques to develop a data-driven approach for learning physical models of electric PMSM-based actuators. These models may then be used to advance the sensing and control capabilities of Series Elastic Actuators used on the robotic syst ...

Read more 

Jun 29, 2017

Exploitation of Series-Elastic Actuator Dynamics in Legged Robots using Reinforcement Learning

The objective of this project is to explore machine-learning techniques, specifically Reinforcement Learning, to allow legged robots incorporating elastic elements at the joints, to exploit these in order to increase locomotion performance and efficiency.

Read more 

Jun 28, 2017

Excavation planning for an autonomous walking excavator

The aim of the project is to create a planning tool to excavate large 3D areas using a Menzi Muck walking excavator.

Read more 

Jun 28, 2017

Excavator climbing on a truck with scripted motion plans

The aim of this project is to enable a highly customized 12ton Menzi Muck to do certain scripted motions or tasks like autonomously climbing on the back of a truck or walking sideways.

Read more 

Jun 28, 2017

Grasping with a Humanoid Hand

This project is about robust grasping with a self adaptive humanoid hand. The goal is to evaluate and implement methods for gripping reliably handles and rails but also objects for pick and place tasks.

Read more 

Jun 26, 2017

Adaptive Learning Control Concept with ARMin V

Evaluate possible learning control strategies for an implementation in ARMin. Implement the selected controller in ARMin. Conduct a technical study showing the accuracy and usability of the chosen learning controller.

Read more 

Jun 16, 2017

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.

Read more 

Jun 15, 2017

ANYmal on Rollerblades: Design, Simulation and Control of a Rollerblading Robot

This project explores novel design, simulation and locomotion principles to enable ANYmal to perform gaits that mimic those used by human rollerbladers, for example those that combine walking or running with skating motion.

Read more 

Jun 9, 2017

Design, Fabrication, and Testing of a Rake for the Beachbot Robot

The Beachbot is an autonomous mobile robot that draws designs in beach sand. The current rake de- sign is prone to damage. The goal of this project is to identify a more robust design for the rake and then do fabrication, integration with the rake’s control system, and testing.

Read more 

Jun 8, 2017

3D Anatomy Reconstruction using a Magnetic Endoscope

We wish to reconstruct 3D meshes of internal human anatomy using videos obtained from a magnetically controlled endoscope.

Read more 

Jun 8, 2017

Shifting the paradigm in sleep classification algorithms

During sleep studies there is a need to influence sleep patterns in real time. Constant visual inspection of physiological signals by expert clinical staff is too costly and ineffective. To achieve unsupervised sleep detection, an automatic algorithm is needed.

Read more 

Jun 6, 2017

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 pr ...

Read more 

Jun 5, 2017

Analysis of leg muscle activity during undisturbed and disturbed walking

A device called the ETH Knee Perturbator has been developed at the RELab. It can induce knee joint perturbations during walking. Measurements of muscle activity while wearing the device and during perturbations offers useful insight in muscle recruitment when gait is disturbed.

Read more 

May 30, 2017

Design and evaluation of a variable stiffness catheter for eye surgery

The student designs a novel catheter for eye surgery. By utilizing Low Melting Point Alloy (LMPA) technology, the stiffness of the catheter can be controlled. This allows us to move the catheter in a flexible state and do manipulations in a a stiff state.

Read more 

May 23, 2017

Interaction Forces in Climbing: How to assess them in an affordable manner?

Although contact forces between climber and hold have been emphasized as an important component in successful climbing, affordable instrumentation to measure these forces are not available, especially for measuring holds with arbitrary shapes. In this project, affordable instrumention is develope ...

Read more 

May 23, 2017

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.

Read more 

May 22, 2017

Game and GUI Development for the Rehabiliation Robot ARMin V

Upgrade our graphical user interface for therapists and develop an interesting game for stroke patients.

Read more 

May 20, 2017

Tethered Drone

In this project we aim to develop a system for deploying a tethered drone from a ground robot to provide additional situational awareness for operators.

Read more 

May 15, 2017

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.

Read more 

May 15, 2017

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.

...

Read more 

May 10, 2017

Perception for Drone Racing

In this project we aim to detect 3D objects in image data for use in within our autonomous drone racing system.

Read more 

May 2, 2017

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 unlocking the possibility of virtual reality applications. The tracking system shall use an a priori unknown pattern which will have to be learnt on-the-fly.

Read more 

Apr 26, 2017

Detection, Pose Estimation and Manipulation of Arbitrarily Shaped Objects

Depending on student's interest and background there are multiple available projects within the scope of mobile manipulation project described below.

Read more 

Apr 26, 2017

Deep Learning for Semantic SLAM

The goal of this project is to train a deep neural network to segment robot sensor data (vision / LiDAR) into semantic scenes. The segmentation is then used to facilitate the SLAM process.

Read more 

Apr 21, 2017

Deep Scale Learning for Visual Motion Estimation (MA/SA)

The goal of this project is to train a deep neural network to estimate scale for a purely visual motion estimation framework. This will enable robots to perform metric ego-motion estimation without use of additional information sources such as an IMU or wheel encoders.

Read more 

Apr 20, 2017

3D Object Registration

The goal of this project is implementing and evaluating an object detection algorithm that is capable of dealing with clutter.

Read more 

Apr 20, 2017

Learning Visual Object Descriptors

The goal of this project is developing and evaluating a machine learning based full-object descriptor algorithm for object retrieval

Read more 

Apr 12, 2017

Advanced lithographies for single-bacteria trapping

Single-cell analysis gives important insights into heterogeneity among cells and will be beneficial to cancer research, regenerative medicine and pharmaceutical development. A 3D-printer at the nanoscale will be used to produce micron-sized masters of wells for capturing single bacteria.

Read more 

Apr 3, 2017

Physical Threshold Detection

In human environments, windows and doors represent thresholds between spaces. This project deals with designing a system to robustly detect windows/doors/thresholds that a quadrotor could fly through, using cameras and range sensors.

Read more 

Apr 3, 2017

Automated Wound monitoring at home

In this study we aim to identify biomarkers on wound images in a clinical proof of concept study with diabetic foot ulcer patients

Read more 

Mar 30, 2017

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 to provide additional quantitative information during the rehabilitation of neurological patients.

Read more 

Mar 25, 2017

A real-time Event Camera Simulator

Event cameras such as the Dynamic Vision Sensor (DVS) are recent sensors with large potential for high-speed and high dynamic range robotic applications. The goal of this project is to extend and improve an existing event camera simulator developed in our lab.

Read more 

Mar 14, 2017

Design of a Casing for an Open-Source Activity Monitor

Design of a robust, comfortable and attractive casing for a commercial physical activity monitor, suitable for wearing on different locations on the body.

Read more 

Mar 3, 2017

Path planning for UAVs with Visual-Inertial SLAM

The goal of this project is to develop a path-planning algorithm for small, rotorcraft UAVs providing it with the ability to cope with an incrementally generated map without any prior information about the environment.

Read more 

Oct 24, 2016

Study the Motion Limit of Visual Odometry

Specific work will include the theoretical analysis of the visual odometry pipeline and validation by simulation/experiments. It is also possible to perform the study for different camera configurations.

Read more 

Oct 24, 2016

Robust and Adaptive Multi-Camera Visual Odometry

The project aims to develop a robust and adaptive multi-camera visual odometry pipeline based on the existing framework in our lab.

Read more 

Oct 24, 2016

Learning Depth from Images and IMU Measurements

In robotics, the inertial measurement unit (IMU) is a commonly used sensor and provides the motion information of the correct scale. This project aims to implement a deep learning algorithm that can estimate the scene depth from images and the IMU measurements.

Read more 

Oct 24, 2016

Smart Feature Selection In Visual Odometry

The student is expected to study how motion estimation is affected by feature selection (e.g., number of features, different feature locations). The ultimate goal will be to implement a smart feature selection mechanism in our visual odometry framework.

Read more 

Oct 24, 2016

Learning Motion from Blur

The goal of the project is to implement a Machine Learning algorithm that can recover the camera motion from a single blurry image.

Read more 

Aug 1, 2016

Novel tool to assess upper limb function in neurological patients

The Virtual Peg Insertion Test (VPIT) is a novel tool to measure upper limb function combining haptic feedback, virtual reality and an instrumented handle that records grasping force. The objective of this project is to establish and systematically evaluate performance metrics collected on the VP ...

Read more 

Feed source: www.siropglobal.org

 
 
Page URL: http://www.iris.ethz.ch/student-projects/semester-project.html
24.07.2017
© 2017 Eidgenössische Technische Hochschule Zürich