Learning Visual Navigation for Drones in Cluttered Environments
H.Y. Yu (TU Delft - Aerospace Engineering)
G.C.H.E. de Croon – Promotor (TU Delft - Aerospace Engineering)
C. de Wagter – Copromotor (TU Delft - Aerospace Engineering)
More Info
expand_more
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
Autonomous drones are increasingly used in cluttered, GPS-denied environments where safe and agile navigation depends on reliable visual obstacle avoidance. However, current approaches face three key challenges: the lack of a unified evaluation framework, the trade-off between safety and agility, and the gap between simulation-trained policies and real-world deployment.
This dissertation addresses these issues by developing learning-based methods and evaluation tools for onboard navigation. First, it introduces AvoidBench, a high-fidelity benchmarking suite with standardized environments and metrics to systematically evaluate obstacle avoidance performance.
Second, it presents MAVRL, a reinforcement learning algorithm that adapts flight speed to environmental complexity, achieving an improved balance between safety and agility. Third, it proposes Depth Transfer, a sim-to-real method that bridges differences in dynamics and perception, enabling robust deployment of trained policies on real drones.
Finally, a bio-inspired hierarchical architecture is introduced, separating high-level planning from low-level control to improve training efficiency and robustness.
Together, these contributions advance learning-based drone navigation by enabling reliable evaluation, adaptive behaviour, efficient training, and successful real-world deployment in complex environments.
help_outline