Landing an unmanned aerial vehicle (UAV) on top of an unmanned surface vehicle (USV) in harsh open waters is a challenging problem, owing to forces that can damage the UAV due to a severe roll and/or pitch angle of the USV during touchdown. To tackle this, we propose a novel model predictive control (MPC) approach enabling a UAV to land autonomously on a USV in these harsh conditions. The MPC employs a novel objective function and an online decomposition of the oscillatory motion of the vessel to predict, attempt, and accomplish the landing during near-zero tilt of the landing platform. The nonlinear prediction of the motion of the vessel is performed using visual data from an onboard camera. Therefore, the system does not require any communication with the USV or a control station. The proposed method was analyzed in numerous robotics simulations in harsh and extreme conditions and further validated in various real-world scenarios.


PDF: http://mrs.felk.cvut.cz/data/papers/ral2023boatlanding.pdf
Arxiv: https://arxiv.org/abs/2301.00255
DOI: https://ieeexplore.ieee.org/document/9998066


Primary Video

This video highlights the results of simulations and two types of real-world conditions. We discuss the approach and describe the outcomes of the applied methods.


Supplementary Video

In this video, we highlight how two of our assumptions can be relaxed without breaking the approach. Those two assumptions being Z-axis oscillation and XY-drift. When a random acceleration is used to account for drift in XY-plane, and a small but characteristic oscillation component is added to the simulation, the controller manages to land correctly but takes a little more time. This showcases the robustness of the controller proposed.