About the position
Job description
Join TU Delft's MAVLab as a PhD candidate and develop fast, fully onboard autonomy that lets lightweight drones perceive, predict and overtake other drones in real flight.
Job description
Autonomous drones are becoming increasingly capable of flying at high speeds, but enabling them to interact reliably with other drones remains a major challenge. When drones fly in close proximity, they must rapidly perceive the motion and orientation of other vehicles, predict their future trajectories, and adapt their own flight paths accordingly.
In this PhD project, you will investigate new methods for fast autonomous navigation and close-range drone-to-drone interaction. You will develop and investigate sensing, state estimation, motion prediction, and guidance, navigation and control strategies that enable drones to interact reliably while flying at high speeds.
A central challenge is to achieve this with extremely lightweight and computationally efficient onboard systems. All essential perception, estimation, prediction, planning and control must run onboard the drone in real time, without relying on offboard computation, and within the strict size, weight and power (SWaP) constraints of small flying platforms.
The project will explore different approaches to sensing and autonomous control, including conventional cameras and potentially event-based vision sensors. You will investigate how drones can estimate the relative state of other drones, anticipate their motion, and use this information to plan and control their own trajectories. The specific sensors, algorithms and hardware solutions remain open to investigation.
The research aims to make an original scientific contribution to fast autonomous navigation, balancing reliable high-speed performance with the limited computational resources of lightweight drones. A key objective is to demonstrate reliable overtaking in real flight. The project therefore combines scientific research with implementation and experimental validation on real flying drones.
You will join the Micro Air Vehicle Lab (MAVLab) in the Control and Simulation group of the Department of Control and Operations at TU Delft's Faculty of Aerospace Engineering. MAVLab has a long history of developing autonomous drone technologies and demonstrating them in real-world competitions and races. The lab combines scientific research with a hands-on experimental culture, in which new ideas are implemented and tested on actual flying platforms. You will collaborate with other PhD researchers working on related topics in autonomous drone racing, giving you the opportunity to exchange ideas and build on complementary research in fast autonomous flight.
Job requirements
A master's degree in aerospace engineering, robotics, control engineering, AI, or another relevant discipline.
A strong scientific background relevant to the project, particularly in perception and control, autonomous systems, guidance, navigation and control, or related fields.
Strong programming skills, including proficiency in Python.
The ability and motivation to conduct independent scientific research, develop novel methods and publish scientific results.
An interest in developing efficient algorithms for autonomous systems operating under strict computational and hardware constraints.
A willingness to implement and test your research on real flying drones and to learn how to organise and conduct experimental flight tests.
Good communication skills and the ability to collaborate effectively in an international, multidisciplinary research team.
Excellent written and spoken English.
The following are beneficial but not required:
Experience in robotics, autonomous navigation, machine learning, reinforcement learning or computer vision.
Knowledge of C or C++, or a willingness to learn these languages for embedded software development.
Practical technical skills, such as building, programming or integrating drones and onboard systems.
Experience with experimental flight testing or autonomous drone racing.
Familiarity with FPV drone flying.
The position is primarily focused on scientific research. Practical engineering and flying experience can help you organise flight tests and iterate more quickly, but prior drone-building or flying experience is not required; you should be willing to learn the practical skills needed to demonstrate your research on real flying platforms.
We welcome candidates from different backgrounds, with a particular interest in aerospace engineering graduates with a strong background in control, as well as candidates from robotics, autonomous systems and related disciplines.
TU Delft (Delft University of Technology)
This listing was collected from a public source and is reproduced here for
information only. Always confirm the details on the original posting before applying.
View the original posting