Student Projects

Use Inverse Reinforcement Learning (IRL) to learn reward functions from previous expert drone demonstrations.

Explore online fine-tuning in the real world of sub-optimal policies.

When drones are operated in industrial environments, they are often flown in close proximity to large structures, such as bridges, buildings or ballast tanks. In those applications, the interactions of the induced flow produced by the drone’s propellers with the surrounding structures are significant and pose challenges to the stability and control of the vehicle. A common methodology to measure the airflow is particle image velocimetry (PIV). Here, smoke and small particles suspended in the surrounding air are tracked to estimate the flow field. In this project, we aim to leverage the high temporal resolution of event cameras to perform smoke-PIV, overcoming the main limitation of frame-based cameras in PIV setups. Applicants should have a strong background in machine learning and programming with Python/C++. Experience in fluid mechanics is beneficial but not a hard requirement.

Autonomous quadrotors are increasingly used in inspection tasks, where flight time is often limited by battery capacity. his project aims to explore and evaluate state-of-the-art path planning approaches that incorporate energy efficiency into trajectory optimization.

Recent research has demonstrated significant success in integrating foundational models with robotic systems. In this project, we aim to investigate how these foundational models can enhance the vision-based navigation of UAVs. The drone will utilize learned semantic relationships from extensive world-scale data to actively explore and navigate through unfamiliar environments. While previous research primarily focused on ground-based robots, our project seeks to explore the potential of integrating foundational models with aerial robots to enhance agility and flexibility.

In this project, we are going to develop a vision-based reinforcement learning policy for drone navigation in dynamic environments. The policy should adapt to two potentially conflicting navigation objectives: maximizing the visibility of a visual object as a perceptual constraint and obstacle avoidance to ensure safe flight.

This project focuses on developing robust reinforcement learning controllers for agile drone navigation using adaptive curricula. Commonly, these controllers are trained with a static, pre-defined curriculum. The goal is to develop a dynamic, adaptive curriculum that evolves online based on the agents' performance to increase the robustness of the controllers.

Automatic failure detection is an essential topic for aerial robots as small failures can already lead to catastrophic crashes. Classical methods in fault detection typically use a system model as a reference and check that the observed system dynamics are within a certain error margin. In this project, we want to explore sequence modeling as an alternative approach that feeds all available sensor data into a neural network. The network will be pre-trained on simulation data and finetuned on real-world flight data. Such a machine learning-based approach has significant potential because neural networks are very good at picking up patterns in the data that are hidden/invisible to hand-crafted detection algorithms.

Perform knowledge distillation from Transformers to more energy-efficient neural network architectures for Event-based Vision.

Study the application of Long Sequence Modeling techniques within Reinforcement Learning (RL) to improve autonomous drone racing capabilities.

This project explores and extends the novel "deep state-space models" framework by leveraging their transfer function representations.

This thesis develops hardware-optimized recurrent neural network architectures with novel parallelization and kernel-level strategies to efficiently process event-based vision data for real-time neuromorphic and GPU-based applications.

This thesis explores novel spiking neural network architectures that leverage event-based vision data and emergent neural synchronization to enable efficient and robust temporal reasoning for dynamic scene understanding and sequential tasks.

This research project aims to develop and evaluate a meta model-based reinforcement learning (RL) framework for addressing variable dynamics in flight control.

This project explores the effect of dynamic occlusions on the performance of event-based detection and VO algorithms. It involves the development of low-latency suppression strategies that mitigate such effects, restoring robust perception in adverse weather.

This project explores leveraging event-camera signals to suppress reflections and ghosting in images captured through glass or other reflective surfaces. By exploiting temporal and motion differences between scene content and reflection artifacts, the goal is to disentangle true scene information from distracting overlays.

This project investigates how asynchronous event streams can enhance 3D Gaussian Splatting for high dynamic range (HDR) reconstruction and photorealistic relighting. The aim is to achieve faithful scene reconstructions under challenging low-light conditions by fusing event data with sparse or degraded frames.

We aim to learn vision-based policies in the real world using embedded optimization layers within reinforcement learning.

This project aims to use vision-based world models as a basis for model-based reinforcement learning, aiming to achieve a generalizable approach for drone navigation.

In this project, we will use uncertainty-aware localization and an MPC layer within an RL policy to navigate challenging environments.

In this project, you will investigate the use of event-based cameras for vision-based landing on celestial bodies such as Mars or the Moon.

Humanoid robots require tactile sensing to achieve robust dexterous manipulation beyond the limits of vision-based perception. This project develops an event-based tactile sensor to provide low-power, high-bandwidth force estimation from material deformation, with the goal of integrating it into a human-scale robotic hand.

This project explores generative modeling of drone flight paths conditioned on natural language commands and spatial constraints, aiming to produce plausible 3D trajectories for training reinforcement learning policies. We investigate model architectures, data sources, and trajectory extraction methods to ensure generated paths are both physically feasible and stylistically aligned with textual descriptions.

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

This project develops an end-to-end pipeline for object segmentation using event camera data, leveraging their microsecond latency, high dynamic range, and sparse asynchronous output to overcome the limitations of frame-based vision. By combining advanced deep learning architectures with rigorous benchmarking, the approach aims to deliver accurate, temporally consistent, and robust segmentation for real-time applications in navigation and control.

Develop a vision-based aerial transportation system with reinforcement / imitation learning.

This project develops an end-to-end pipeline for acrobatic drone flight using event-based vision. It leverages the low latency and high dynamic range (HDR) of event cameras to accurately detect and predict the motion of a dynamic narrow gap, maximizing drone maneuverability through a reinforcement learning (RL)-based policy to navigate it successfully.

We aim to co-design a controller and the shape of a glider for a perching maneuver, involving deployment on the real system.

This project develops event-based representation learning methods for control tasks in environments with visual distractors, leveraging sparse, high-temporal-resolution event data to improve robustness and efficiency over traditional frame-based approaches.

This project explores integrating event-based vision into LLMs through custom layers and knowledge distillation, enabling efficient processing of sparse, asynchronous data for dynamic scene understanding in real-world applications.