Autonomous micro uav docks safely on moving airborne carrier
RTK-Vision PPO for Autonomous Micro UAV Recovery on an Airborne Carrier
Robotics
Summary
Landing a tiny drone on a moving aircraft is hard because the drone must fly close, match the motion, and land safely despite wind and sudden contact. The authors designed a system where a bigger carrier plane helps a smaller drone take off, do its mission, then return and land back on it while both share precise GPS data. They trained an AI controller in simulation to handle tricky landing conditions and tested it outdoors, achieving 93% mission success and very precise landings. Their approach is a complete cycle from deployment to recovery, useful for repeated drone missions.
What this means in practice
- •For inspection drone operators: Automate launch and precise recovery of small drones from moving airborne platforms to enable repeated inspection missions without human pilots.
- •For mobile logistics teams: Use autonomous drone deployment and landing on airborne carriers to transport small parcels in scenarios requiring midair vehicle coordination.
Authors
Aashish Sahu, R Prasanth Kumar
Abstract
Autonomous recovery of a micro unmanned aerial vehicle (UAV) onto a moving airborne carrier enables reusable deploy-mission-recover operation, but couples long-range rendezvous, close-range perception, carrier motion, aerodynamic interaction, and a discontinuous contact event. This paper presents an RTK-vision-guided reinforcement-learning framework in which a child UAV is physically transported by a larger carrier, takes off from the carrier while airborne, executes an independent sortie, returns to the carrier's current position, redocks, and subsequently descends with the carrier. Both vehicles carry RTK-GNSS, and the carrier continuously shares its navigation state with the child. Near the recovery deck, RTK remains active while a downward-facing camera with a fiducial marker detector provides marker-relative alignment cues. A proximal policy optimization (PPO) policy governing the terminal recovery phase is trained in a physics-based MuJoCo simulation environment with explicit sensor noise models, an aerodynamic disturbance surrogate, and marker-latency randomization, then transferred to hardware. PX4 retains low-level stabilization, and a deterministic safety gate authorizes descent independently of the learned policy. The PPO checkpoint achieves 99.55% success over 2,000 held-out randomized terminal episodes, compared with 78.4% for a tuned PD baseline under identical conditions, with a median planar terminal error of 6.62 cm. Across 14 outdoor trials, the full mission succeeds in 13 trials (92.9%), spanning both near-region recovery and recovery after the carrier translates away from the release point. The results demonstrate a complete autonomous aerial deployment-and-recovery cycle rather than an isolated landing maneuver, establishing a practical basis for reusable carrier-child operation in inspection, surveillance, and mobile-logistics applications.