# Energy-Efficient Trajectory Design for UAV-Aided Maritime Data Collection in Wind

arXiv: https://arxiv.org/abs/2112.13396 · HTML: https://mlsanity.com/paper/2112.13396/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2021.

## Built on by (most cited first, 2 of 2)

- [Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection](https://mlsanity.com/paper/2509.13934/) (2025)
- [Queue-Aware Graph Reinforcement Learning for UAV-ISAC-Assisted Maritime Data Collection](https://mlsanity.com/paper/2607.00324/) (2026)

## Abstract (arXiv)

Unmanned aerial vehicles (UAVs), especially fixed-wing ones that withstand strong winds, have great potential for oceanic exploration and research. This paper studies a UAV-aided maritime data collection system with a fixed-wing UAV dispatched to collect data from marine buoys. We aim to minimize the UAV's energy consumption in completing the task by jointly optimizing the communication time scheduling among the buoys and the UAV's flight trajectory subject to wind effect. The conventional successive convex approximation (SCA) method can provide efficient sub-optimal solutions for collecting small/moderate data volume, whereas the solution heavily relies on trajectory initialization and has not explicitly considered wind effect, while the computational/trajectory complexity both become prohibitive for the task with large data volume. To this end, we propose a new cyclical trajectory design framework with tailored initialization algorithm that can handle arbitrary data volume efficiently, as well as a hybrid offline-online (HO2) design that leverages convex stochastic programming (CSP) offline based on wind statistics, and refines the solution by adapting online to real-time wind velocity. Numerical results show that our optimized trajectory can better adapt to various setups with different target data volume and buoys' topology as well as various wind speed/direction/variance compared with benchmark schemes.