Student Projects

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, ...).

  • Drone racing requires human pilots to not only complete a given race track in minimum-time, but also to compete with other pilots through strategic blocking, or to overtake opponents during extreme maneuvers. Single-player RL allows autonomous agents to achieve near-time-optimal performance in time trial racing. While being highly competitive in this setting, such training strategy can not generalize to the multi-agent scenario. An important step towards artificial general intelligence (AGI) is versatility -- the capability of discovering novel skills via self-play and self-supervised autocurriculum. In this project, we tackle multi-agent drone racing via self-play and reinforcement learning.

    More …

  • Design and implement a fast GPU-based simulator for generating low-level computer vision ground truth.

    More …

  • Design and implement efficient asynchronous event-based networks to achieve low latency inference.

    More …

  • This project will explore the application of event camera setups for scene reconstruction

    More …

  • Design and implement an unsupervised domain adaption approach for transferring multiple tasks from labelled frame datasets to event data.

    More …

  • Design and implement a data-driven keypoint extractor for event data.

    More …

  • Eyetracking Toolbox for Drone Racing Research

    More …

  • Dynamic obstacle avoidance is a grand challenge in vision-based drone navigation. The classical mapping-planning-control pipeline might have difficulties when facing dynamic objects.

    More …

  • This project will focus on event-based depth estimation using structured light systems.

    More …

  • Develop a machine-learning-based motion estimation pipeline using event cameras.

    More …

  • Train a neural network to predict and intermediate representation that can be used by an MPC.

    More …

  • This work investigates the usage of Gaussian Processes for uncertainty-aware system identification of a quadrotor platform.

    More …

  • Online learning-aided visual inertial odometry for robust state estimation

    More …

  • CT-VIO for agile flights

    More …

  • Collect a dataset of high-speed maneuvers in the optitrack and identify the quadrotor platform. Use this model to create a fast and accurate quadrotor simulation. Verify the simulator by comparing it to real-world data.

    More …

  • Perception aware MPC for powerlines tracking

    More …

  • Visual inertial odometry algorithms rely on high-quality data and struggle with fast motion. Current solutions timestamp their data from unsynchronized clocks and suffer from timestamp drift and offsets. We aim to develop a custom sensor board that overcomes these shortcomings.

    More …

  • Deep Learning for Vision-Based State Estimation in Drone Racing

    More …

  • The goal of this project is to explore new techniques for modelling an event camera.

    More …

  • Event cameras have shown amazing capabilities in slowing down video as was shown in our previous work, TimeLens (https://www.youtube.com/watch?v=dVLyia-ezvo). This is because, compared to standard cameras, event cameras only capture a highly compressed representation of the visual signal, and do thi

    More …

  • Event cameras such as the Dynamic Vision Sensor (DVS) are recent sensors with large potential for high-speed and high dynamic range robotic applications, such as fast obstacle avoidance. In particular, event cameras can be used to track features or objects in the blind time between two frames which makes it possible to react quickly to changes in the scene. In this project we want to deploy a feature tracking algorithm on a resource constrained platform such as a drone. Applicants should have a strong background in C++ programming and low-level vision. Experience with embedded programming is a plus.

    More …

  • This work will address intrinsic calibration of event cameras, a fundamental problem for application of event cameras to many computer vision tasks, by incorporating deep learning.

    More …

  • Camera ego-motion tracking with spiking neural networks and event cameras

    More …

  • Planning for Multi-player Competitive Drone Racing

    More …

  • Online Replanning for Autonomous Drone Racing

    More …

  • Model Predictive Contouring Control (MPCC) has shown to achieve very good results. There are two relevant parameters to be tuned in the cost function: contour weight and progress weight. We aim to exploit the low dimensionality of this parameter space and apply learning techniques to tune the MPCC.

    More …

  • In this project, we aim to modify the design of our platform to build a quadcopter that is able to generate thrust in both positive and negative directions. This will provide the quadcopter with new ways of performing complex maneuvers in ways unseen until now.

    More …

  • Perception Aware Minimum-time Planning in Cluttered Environments

    More …

  • Study on the effects of camera resolution in Visual Odometry

    More …

  • Reinforcement Learning for Offboard Control of a Racing Drone

    More …