Distributed sensor fusion for collaborative drones

The trend towards autonomous drones is currently driving the integration of an increasing number of sensors for safe navigation under all circumstances, forcing algorithms and hardware to be energy efficient and fast. When drone technology continues to mature, deploying swarms of them will enable even more advanced use cases, for example in precision agriculture. Swarms also offer the possibility of sharing both sensory and compute resources, making the swarm act and respond as a single collaborative entity with overall better performance.

In this PhD project, you will work with real-world multi-sensory data collected by multiple drones and develop communication and collaborative sensor fusion solutions running on commercial compute hardware.

More specifically, you will focus on following research questions:

• How to take advantage of multiple sensors (e.g. radar, IMU, camera, UWB, sonar, …), mounted on different drones, in order to come to a joint understanding of the environment with minimal overall effort (in terms of compute power and communication load)? Different approaches w.r.t. distributed sensor fusion will be explored, including early and late fusion algorithms.
• Can intermittent connectivity be handled such that the drone system continues to safely operate, autonomously (possibly in a sub-optimal operation mode, due to the lack of support from other drones or remote infrastructure)?
• For a given task (e.g. area mapping, parcel delivery, …), can we find algorithms that automate task splitting between drones (and possibly handle unforeseen complications, such as change of wind direction)? (both in a centralized and a distributed setting).