Beyond Proportional Navigation

Deep Reinforcement Learning for Robust Drone Interception

Master Thesis (2025)
Author(s)

M.L. Capelle (TU Delft - Mechanical Engineering)

Contributor(s)

L. Ferranti – Mentor (TU Delft - Learning & Autonomous Control)

E.J.J. Smeur – Mentor (TU Delft - Control & Simulation)

J. Alonso-Mora – Graduation committee member (TU Delft - Learning & Autonomous Control)

Riccardo M.G. Ferrari – Graduation committee member (TU Delft - Team Riccardo Ferrari)

Faculty
Mechanical Engineering
More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
05-11-2025
Awarding Institution
Delft University of Technology
Programme
['Mechanical Engineering | Vehicle Engineering | Cognitive Robotics']
Faculty
Mechanical Engineering
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The rapid increase in drone threats has created an urgent need for practical counter-drone systems for safety and defence purposes. Interceptor drones represent a promising and cost-effective solution for removing unwanted aerial vehicles. However, classical guidance laws such as Proportional Navigation (PN) are not well adapted to highly agile targets under realistic perception constraints. In parallel, deep reinforcement learning (DRL) has demonstrated exceptional performance in high-speed quadcopter control tasks, motivating its consideration for interception applications. A major challenge for such learning-based controllers lies in sim-to-real transfer. This work addresses this challenge through extensive domain randomization and explicit modelling of realistic perception constraints, including sensor noise, limited field of view, sensing ranges, and sensor update rates. A framework is proposed that trains Single Rotor Thrust (SRT) DRL policies for quadcopters and evaluates them against a classical PN implementation within a physics-based simulator. The resulting controllers generalise across platform variations and outperform classical guidance under modelled perception limitations, demonstrating improved robustness and transferability.

Github Repository of the code used for the thesis: https://github.com/maximecapelle/quadintercept_drl

Files

MScThesis_MaximeCapelle.pdf
(pdf | 2.65 Mb)
License info not available