Subject

A flight scheduler is a program that collects and processes data from multiple sources to plan flight paths for Unmanned Aerial Vehicles (UAVs). Current versions of flight schedules are not able to deal with the dynamism required for UAV flight planning.
The leveraging of a deep reinforcement learning (RL) based flight plan and scheduler, can help overcome limitations that exist with more traditional schedulers. These schedulers should be able to provide and update flight plans in a quicker and more efficient way, all in automated way.
A key component of the scheduler is the routing algorithm, which defines the optimal route that the UAV should follow to go from one point to another. These routing algorithms typically require data from multiple sources, including, but not limited to, power consumption, weather data and crowd data.
One possibility to design a more dynamic scheduler is the initial use of a traditional routing algorithm, such as A*. A* uses nodes, and the distances between them (which are assigned costs) and chooses the path with the lowest cost. The output of the A* algorithm can be passed to an RL agent, which incorporates several data sets to plan the ideal path of a drone quickly. Another possibility is the usage of an RL agent to calculate the weights of the paths between different nodes, and using A* to find the chosen path (sometimes known as Aleph*).

Kind of work

Objectives:
• Literature study on the two methods mentioned above (a third alternative can be proposed)
• A comparative analysis of these methods, based on clear, 360° encompassing and relevant metrics to compare the methods
• The implementation of the preferred method as a proof of concept

Framework of the Thesis

Support will be provided from a functional and IT technical side from Helicus and its core partners. A first conceptual study on this topic has been created as part of a Helicus coordinated ICON project HAI-SCS.

Number of Students

1 or 2 (preferably in the form of a duo thesis)

Expected Student Profile

Applied Computer Science or Electrical Engineering students with an interested in routing optimization, Deep Learning and/or Reinforcement Learning (RL)