Vision-Based Autonomous Drone Landing on Moving Platforms With Uncertain Motion via Deep Reinforcement Learning
- 13 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (5) , 5542-5549
Abstract
This paper addresses vision-based autonomous landing of quadrotor drones on moving platforms with uncertain motion. Vision is attractive due to its low weight, low cost, and ability to provide direct relative observations without global reference frames. However, traditional visual landing relies on requiring accurate estimation and tuning, which limits robustness. Deep reinforcement learning (DRL) offers a data-driven alternative but often degrades under motion uncertainty or intermittent visual loss from a limited field of view (FOV). The key challenge is active perception, maintaining visual observability of the landing pad under FOV constraints during aggressive maneuvers. To address this challenge, we propose a vision-based DRL framework that jointly learns perception, estimation, and control, guided by an active-perception reward that couples visibility maintenance with control performance for stable touchdown. Simulation results demonstrate robustness over visual servoing and existing DRL baseline, including landings on a platform moving at speeds up to 8 m/s under limited visibility. Real-world experiments further confirm the feasibility and stability of the proposed approach.Keywords
Funding Information
- Theater Defense Research Center (UD200043CD)
- National Research Foundation of Korea (2023R1A2C2003130)
- Unmanned Vehicles Core Technology Research and Development Program
- Unmanned Vehicle Advanced Research Center
- Republic of Korea (2020M3C1C1A01082375)
This publication has 26 references indexed in Scilit:
- PACMAN: Rapid identification of keypoint patch-based fiducial marker in occluded environmentsImage and Vision Computing, 2025
- Vision-Based Optimal Landing Guidance Law for VTOL UAVs on a Moving PlatformInternational Journal of Aeronautical and Space Sciences, 2024
- Champion-level drone racing using deep reinforcement learningNature, 2023
- Planar fiducial markers: a comparative studyVirtual Reality, 2023
- Autonomous ship deck landing of a quadrotor UAV using feed-forward image-based visual servoingAerospace Science and Technology, 2022
- Towards better generalization in quadrotor landing using deep reinforcement learningApplied Intelligence, 2022
- An auto-landing strategy based on pan-tilt based visual servoing for unmanned aerial vehicle in GNSS-denied environmentsAerospace Science and Technology, 2021
- Robust visual servoing control for quadrotors landing on a moving targetJournal of the Franklin Institute, 2021
- Automatic generation and detection of highly reliable fiducial markers under occlusionPattern Recognition, 2014
- A tutorial on visual servo controlIEEE Transactions on Robotics and Automation, 1996