Student Projects


How to apply

To apply, please send your CV, your Ms and Bs transcripts by email to all the contacts indicated below the project description. Do not apply on SiROP . Since Prof. Davide Scaramuzza is affiliated with ETH, there is no organizational overhead for ETH students. Custom projects are occasionally available. If you would like to do a project with us but could not find an advertized project that suits you, please contact Prof. Davide Scaramuzza directly to ask for a tailored project (sdavide at ifi.uzh.ch).


Upon successful completion of a project in our lab, students may also have the opportunity to get an internship at one of our numerous industrial and academic partners worldwide (e.g., NASA/JPL, University of Pennsylvania, UCLA, MIT, Stanford, ...).



Deep object pose estimation - Available

Description: Estimating the pose of objects from a single image has many applications, ranging from autonomous driving over manipulation to multi-robot SLAM. Based on some recent work, we would like to investigate a novel approach to this that could potentially be very powerful.

Goal: Develop a method that, given a training set of images of a certain object, are able to reliably detect the pose of that object in previously unseen images. We will provide some guidance based on our experience, but you will also be able to bring in your creativity. The optimal outcome is a publication (CVPR/RSS).

Contact Details: Titus Cieslewski ( titus at ifi.uzh.ch ), ATTACH CV AND TRANSCRIPT (also Bachelor)! Preferred skills: Linux, Python, some Computer Vision background, TensorFlow/PyTorch or equivalent. This project will be co-supervised by Elia Kaufmann.

Thesis Type: Master Thesis

See project on SiROP

Pushing hard cases in tag detection with a CNN - Available

Description: Visual Tags such as April or Aruco tags are nowadays detected with a handcrafted algorithm. This algorithm has its limitations in special cases, such as when the tag is far away from the camera, when the tag is partially occluded or when a camera with high distortion is used.

Goal: In this project, you will train a CNN to handle these special cases. We will first brainstorm a meaningful architecture that will allow a CNN to complement classical tag detection in the most effective way. You will then figure out the most effective way to create meaningful training data (hybrid of synthetic and real data?). Finally, you will use that data to train the desired detector.

Contact Details: Titus Cieslewski ( titus at ifi.uzh.ch ), ATTACH CV AND TRANSCRIPT! Required skills: Linux, Python, ability to read C++ code. Desirable skill: Tensorflow or similar.

Thesis Type: Semester Project / Bachelor Thesis / Master Thesis

See project on SiROP

Learning Robust Visual Place Recognition Combining Appearance, Sequence and Structure - Available

Description: Recognizing a previously visited place is challenging when the place is subject to changes in appearance due to for example wheather, time-of-day or seasonal changes. Many previous works tackle the problem based on appearance, sequence or structure.

Goal: In this project, you will attempt to unify these approaches, while using machine learning techniques to your advantage. You will evaluate your work on a publicly available dataset that has been recorded on the same trajectory across the span of a year.

Contact Details: Titus Cieslewski ( titus at ifi.uzh.ch ), ATTACH CV AND TRANSCRIPT! Required skills: Linux, Python, ability to read C++ code. Desirable skill: Tensorflow or similar.

Thesis Type: Master Thesis

See project on SiROP

Teach and Aggressive Repeat - Available

Description: When we think of robot path planning, we often think of fitting optimal trajectories into dense 3D maps. This requires high quality 3D maps in the first place, which are often hard to obtain. An alternative approach, called Teach and Repeat, is to retrace previously traversed paths. Teach and Repeat maps are easier to create, as no globally consistent pose estimate is required. They can also be very compact, as the environment only needs to be sampled at sparse, visually salient locations. In this project, you will do T&R with a twist: Try to fly the repeat as fast as possible.

Goal: Start by building a basic teach and repeat based on existing components. Then, start increasing the repeat speed. Find out what the limitations are. Perceptual limitations like motion blur? If so, can this be solved with event cameras ( https://goo.gl/itzpJN ) ? Or is it avoiding collisions, as potentially tight maneuvers from the slow teach phase cannot be repeated at high velocities? You will most likely start with deployment on a real quadrotor very soon.

Contact Details: Titus Cieslewski ( titus at ifi.uzh.ch ), ATTACH CV AND TRANSCRIPT (also Bachelor)! Required skills: Linux, C++, ROS. Students who took the Vision Algorithms for Mobile Robots class are at an advantage.

Thesis Type: Master Thesis

See project on SiROP

Learn Depth from Multiple Input Modalities - Available

Description: Depth sensing has become pervasive in applications as diverse as autonomous driving, augmented reality, and scene reconstruction. Mobile robots often feature sensors that provide depth information (LiDARs, RGB-D cameras, ToF cameras). The data from these sensors is typically sparse. Furthermore, depending on the sensing principle, these sensors fail when exposed to shiny, bright, transparent, distant, and low-texture surfaces. Learning-based approaches to infer depth from single images have already shown promising results. This project aims to combine both input modalities (RGB frames + sparse depth information) in a learned way to predict a dense depth image.

Goal: Combine both RGB and (sparse) depth data from an RGBD sensor to regress a high-quality dense depth image.

Contact Details: Elia Kaufmann (ekaufmann@ifi.uzh.ch)

Thesis Type: Semester Project / Master Thesis

See project on SiROP

Analyzing The Role of Perception Latency in High Speed Sense and Avoid - Available

Description: To prevent a collision with an obstacle or an incoming object, a robot needs to detect them as fast as possible and execute a safe maneuver to avoid them. The higher the relative speed between the robot and the object, the more critical the role of perception latency becomes. The goal of this project is to extend our previous work (http://rpg.ifi.uzh.ch/docs/RAL19_Falanga.pdf) on the analysis of the role of perception latency in high speed sense and avoid, in order to consider different robot dynamics and multiple scenarios, such as cases including dynamic obstacles.

Contact Details: Davide Falanga (falanga AT ifi DOT uzh DOT ch). Attach CV and Transcripts.

Thesis Type: Master Thesis

See project on SiROP

Performance analysis and characterization of a morphing quadrotor - Available

Description: The goal of this project is to study the impact of the morphology assumed by a quadrotor able to change its shape in-flight on the performance of its propulsion system. More specifically, it aims at characterizing the behaviour of the thrust produced by each propeller when (i) there is overlap among propellers and (ii) any of the propellers overlaps with the main body. Additionally, the project includes the implementation of a compensation scheme based on the results of such characterization.

Contact Details: Davide Falanga (falanga AT ifi DOT uzh DOT ch). Please attach CV and transcripts.

Thesis Type: Semester Project

See project on SiROP

Learning minimal representations of places - Available

Description: Place recognition and 6DoF localization has a wide range of applications, whether in robot autonomy, VR/AR or navigation interfaces. Given sensor readings (we focus on images), the goal is to establish position and orientation of a robot/device with respect to a previously recorded map. Recently, this is generally solved with a mixture of machine learning and geometry (NetVLAD, SuperPoint, LF-NET, PoseNet). Our focus in particular will be to solve this problem with a minimal representation.

Goal: Given query agent A and map agent B, have B establish a pose of A within its map, with minimal data transmission from A to B. We have a couple of ideas on how to solve this (see our most recent publication on this: https://arxiv.org/abs/1811.10681 ), but you are encouraged to bring your own ideas to the table.

Contact Details: Titus Cieslewski ( titus at ifi.uzh.ch ), ATTACH CV AND TRANSCRIPT (also Bachelor)! Preferred skills: Linux, Python, “Vision Algorithms for Mobile Robots” class or equivalent, TensorFlow/PyTorch or equivalent.

Thesis Type: Master Thesis

See project on SiROP

Safe Reinforcement Learning for Robotics - Available

Description: Reinforcement Learning (RL) has recently emerged has a technique to let robots learn by their own experience. Current methods for RL are very data-intensive, and require a robot to fail many times before actually accomplishing their goal. However some systems, such as flying robots, require to respect safety constraints during learning and/or deployment. While maximizing performance, those methods usually aim to minimize the number of system failures and overall risk.

Goal: During this project, we will develop machine learning based techniques to let a (real) drone learn to fly nimbly through gaps and gates, while minimizing the risk of critical failures and collisions.

Contact Details: **Antonio Loquercio** loquercio@ifi.uzh.ch

Thesis Type: Semester Project / Master Thesis

See project on SiROP

Unsupervised Obstacle Detection Learning - Available

Description: Supervised learning is the gold standard algorithm to solve computer vision tasks like classification, detection or segmentation. However, for several interesting tasks (e.g. moving object detection, depth estimation, etc.) collecting the large annotated datasets required by the aforementioned algorithms is a very tedious and costly process. In this project, we aim to build a self-supervised depth estimation and segmentation algorithm by embedding classic computer vision principles (e.g. brightness constancy) into a neural network. **Requirements**: Computer vision knowledge; programming experience with python. Machine learning knowledge is a plus but it is not required.

Goal: The goal of this project consists of building a perception system which can learn to detect obstacles without any ground truth annotations.

Contact Details: Antonio Loquercio, _loquercio@ifi.uzh.ch_

Thesis Type: Semester Project / Master Thesis

See project on SiROP

Optimization for Spiking Neural Networks - Available

Description: Spiking neural networks (SNNs) are neural networks that process information with timing of events/spikes rather than numerical values. Together with event-cameras, SNNs show promise to both lower latency and computational burden compared to artificial neural networks. In recent years, researchers have proposed several methods to estimate gradients of SNN parameters in a supervised learning context. In practice, many of these approaches rely on assumptions that might not hold in all scenarios. Requirements: - Background in machine learning; especially deep learning - Good programming skills; experience in CUDA is a plus.

Goal: In this project we explore state-of-the-art optimization methods for SNNs and their suitability to solve the temporal credit-assignment problem. As a first step, an in-depth evaluation of a selection of algorithms is required. Based on the acquired insights, the prospective student can propose improvements and implement their own method.

Contact Details: Mathias Gehrig, mgehrig (at) ifi (dot) uzh (dot) ch

Thesis Type: Master Thesis

See project on SiROP

High-Performance Simulation of Spiking Neural Network on GPUs - Available

Description: One major complication in research of biologically-inspired spiking neural Networks (SNNs) is simulation performance on conventional hardware (CPU/GPU). Computation in SNNs is dominated by operations on sparse tensors but usually this potential benefit is ignored to save development time. However, the exploitation of sparsity could be beneficial to scale simulation of SNNs to larger datasets. Requirements: - Experience with deep learning frameworks (e.g. TensorFlow or PyTorch) - Excellent programming skills and experience in CUDA

Goal: In this project, you will leverage sparse computation to develop high-performance simulations of SNNs that can be used for optimization. This will help to scale experiments and drastically improve results obtained by SNNs.

Contact Details: Mathias Gehrig, mgehrig (at) ifi (dot) uzh (dot) ch

Thesis Type: Semester Project

See project on SiROP

Target following on nano-scale UAV - Available

Description: Autonomous Unmanned Aerial Vehicles (UAVs) have numerous applications due to their agility and flexibility. However, navigation algorithms are computationally demanding, and it is challenging to run them on-board of nano-scale UAVs (i.e., few centimeters of diameter). This project focuses on the object tracking, (i.e., target following) on such nano-UAVs. To do this, we will first train a Convolutional Neural Network (CNN) with data collected in simulation, and then run the aforementioned network on a parallel ultra-low-power (PULP) processor, enabling flight with on-board sensing and computing only. **Requirements**: Knowledge of python, cpp and embedded programming. Machine learning knowledge is a plus but it is not strictly required.

Contact Details: Antonio Loquercio, _loquercio@ifi.uzh.ch_

Thesis Type: Semester Project / Master Thesis

See project on SiROP

Decentralized Visual Map Building - Available

Description: In State-of-the-Art decentralized mapping methods, optimization (correcting odometry drift) is typically done using pose graph optimization due to the fact that a pose graph is a very compact representation. Unfortunately, this compression in data results in limitations in precision and robustness. Bundle Adjustment is a map optimization method for visual maps which is much more precise and robust, but also much more data intensive.

Goal: In this work, you will figure out a way to achieve the superior precision of Bundle Adjustment while minimizing the amount of data that needs to be exchanged between robots in a decentralized setting.

Contact Details: Titus Cieslewski ( titus at ifi.uzh.ch ), ATTACH CV AND TRANSCRIPT! Required skills: Matlab or C++, with a preference for the latter. Desirable: Background in optimization (Nonlinear least squares, Gauss-Newton or similar)

Thesis Type: Semester Project / Master Thesis

See project on SiROP

Event-based Deep Learning - Available

Description: 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 explore new algorithms for processing events within a deep-learning context. The goal of the project should be implementing and comparing different frameworks for processing events, and applying them to challenging tasks, such as optical flow prediction. This is a project with considerable room for creativity. Experience in coding image processing algorithms in C++ and experience with learning frameworks in python is required.

Goal: The goal of this project is to explore new algorithms for processing events within a deep-learning context.

Contact Details: Daniel Gehrig (dgehrig at ifi.uzh.ch), Antonio Loquercio (antonilo (at) ifi.uzh.ch)

Thesis Type: Semester Project / Master Thesis

See project on SiROP

Asynchronous Processing for Event-based Deep Learning - Available

Description: Event cameras such as the Dynamic Vision Sensor (DVS) are recent sensors with large potential for high-speed and high dynamic range robotic applications. Since their output is sparse traditional algorithms, which are designed for dense inputs such as frames, are not well suited. The goal of this project is explore ways to adapt existing deep learning algorithms to handle sparse asynchronous data from events. Applicants should have experience in C++ and python deep learning frameworks (tensorflow or pytorch), and have a strong background in computer vision.

Goal: The goal of this project is explore ways to adapt existing deep learning algorithms to handle sparse asynchronous data from events.

Contact Details: Daniel Gehrig (dgehrig at ifi.uzh.ch)

Thesis Type: Semester Project / Master Thesis

See project on SiROP

Open-Source Research Flight Controller interfacing Hobbyist Hardware - Available

Description: Due to the popularity of drones, a wide variety of models is available on the market. The branches of this market reaches from toys, consumer grade hardware for photography, professional equipment for cinematography to first-person-view drones for racing and freestyle flight, and even research drones. Although there are multiple research platforms available, they often come with disadvantages like high price, large size, high weight and a certain amount of ecosystem lock-in or restrictions on development tools. This project aims at programming existing flight controller hardware to replace the hobbyist software. Tasks within this project involve identifying the communication interfaces used, writing libraries for communication with motor controllers, on-board computers and sensors, and implementing simple filter and control functions. All of this runs embedded on an ARM chip (hardware will be provided) and in a POSIX environment. Good embedded programming skills are required.

Goal: The goal is a simple embedded flight stack, consisting of multiple libraries which should be easy to modify and maintain, and optionally could be released to the research community as a open-source package.

Contact Details: Philipp Föhn (foehn at ifi.uzh.ch)

Thesis Type: Semester Project / Master Thesis

See project on SiROP

Generation of Fast or Time-Optimal Tracjectories for Quadrotor Flight - Available

Description: With the rise of complex control and planning methods, quadrotors are capable of executing astonishing maneuvers. While generating trajectories between two known poses or states is relatively simple, planning through multiple waypoints is rather complicated. The master class of this problem is the task of flying as fast as possible through multiple gates, as done in drone racing. While humans can perform such fast racing maneuvers at extreme speeds of more than 100 km/h, algorithms struggle with even planning such trajectories. Within this thesis, we want to research methods to generate such fast trajectories and work towards a time-optimal planner. This requires some prior knowledge in at least some of the topics including: planning for robots, optimization techniques, model predictive control, RRT, and quadrotors or UAVs in general. The tasks will reach from problem analysis, approximation, and solution concepts to implementation and testing in simulation with existing software tools.

Goal: The goal would be to analyse the planning problem, develop approximation techniques and solve it as time-optimal as possible during thesis.

Contact Details: Philipp Föhn (foehn at ifi.uzh.ch)

Thesis Type: Master Thesis

See project on SiROP

3D Reconstruction using an Event Camera - Available

Description: Event cameras such as the Dynamic Vision Sensor (DVS) are recent sensors with large potential for high-speed and high dynamic range robotic applications. In this project we want to explore the possibility of active sensing using an event camera, where the task is to do asynchronous 3D reconstruction. This is important for low-latency updates about the scene and can be useful in fast obstacle avoidance. Applicant should have a strong background in C++ programming and low-level vision.

Goal: In this project we want to explore the possibility of active sensing using an event camera, where the task is to do asynchronous 3D reconstruction.

Contact Details: Daniel Gehrig (dgehrig (at) ifi.uzh.ch), Dario Brescianini (brescianini (at) ifi.uzh.ch)

Thesis Type: Semester Project / Master Thesis

See project on SiROP

MPC for high speed trajectory tracking - Available

Description: Many algorithms exist for model predictive control for trajectory tracking for quadrotors and equally many implementation advantages and disadvantages can be listed. This thesis should find the main influence factors on high speed/high precision trajectory tracking such as: modell accuracy, aerodynamic forces modelling, execution speed, underlying low-level controllers, sampling times and sampling strategies, noise sensitivity or even come up with a novel implementation.

Goal: The end-goal of the thesis should be a comparison of the influence factors and based on that a recommendation or even implementation of an improved solution.

Contact Details: Philipp Föhn (foehn at ifi.uzh.ch)

Thesis Type: Master Thesis

See project on SiROP