WaveLander: A Generalizable Hierarchical Control Framework for UAV Landing on Wave-Disturbed Platforms via Reinforcement Learning

2026-07-01

AI Summary

This work addresses the challenges of autonomous drone recovery on offshore platforms subjected to wave-induced stochastic motion, time-varying attitudes, and uncertain touchdown conditions. A hierarchical control framework is proposed that decouples high-level vertical landing decisions from low-level flight stabilization. The approach integrates reinforcement learning with conventional control: the upper layer employs a temporal-aware reinforcement learning policy, operating on compact relative observations, to generate a reference vertical velocity; the lower layer ensures precise trajectory tracking. The framework achieves smooth landings without requiring explicit switching logic and demonstrates strong generalization and robustness to unseen wave disturbances in simulation, validating its effectiveness for autonomous maritime drone recovery.

Abstract

Autonomous landing of unmanned aerial vehicles (UAVs) on wave-disturbed marine platforms remains challenging due to stochastic platform motion, time-varying platform attitude, and uncertain touchdown conditions. Existing model-based methods often require accurate motion prediction and online optimization, while end-to-end learning approaches may suffer from high training complexity and limited interpretability. This paper presents WaveLander, a hierarchical control framework via reinforcement learning (RL) that decouples vertical landing decision-making from low-level flight stabilization. The RL policy maps a compact platform-relative observation to a scalar vertical velocity reference, while a conventional low-level flight controller maintains attitude stability and lateral tracking. This formulation reduces dynamic platform landing to a low-dimensional, timing-aware control problem and enables smooth landing behavior without explicit switching rules. Simulation results under randomized wave-induced platform motions show that WaveLander achieves robust landing performance and generalizes to unseen disturbance conditions, demonstrating the potential of hierarchical learning-based control for marine UAV recovery.

Problem

• UAV landing
• wave-disturbed platforms
• autonomous landing
• marine UAV recovery
• stochastic platform motion

Innovation

• hierarchical reinforcement learning
• UAV landing
• wave-disturbed platforms
• decoupled control
• generalizable control