An ultra-light indoor fixed-wing platform with a Gaussian-splat twin: vision-only leader-follower and zero-shot autonomous landing.
137 g airframe + 9 g analog camera, 150 g total. Offboard compute. Released as an open flight kit.
We introduce FalconWing, an ultra-light (150 g) indoor fixed-wing UAV platform for vision-based autonomy. Controlled indoor environments enable year-round repeatable UAV experiments but impose strict weight and maneuverability limits on the UAV, motivating our ultra-light FalconWing design. FalconWing couples a lightweight hardware stack (137 g airframe with a 9 g camera) and offboard computation with a software stack featuring a photorealistic 3D Gaussian Splat (GSplat) simulator for developing and evaluating vision-based controllers.
We validate FalconWing on two challenging vision-based aerial case studies. In the leader-follower case study, our best vision-based controller, trained via imitation learning on GSplat-rendered data augmented with domain randomization, achieves 100% tracking success across 3 types of leader maneuvers over 30 trials and shows robustness to the leader's appearance shifts in simulation. In the autonomous landing case study, our vision-based controller trained purely in simulation transfers zero-shot to real hardware, achieving an 80% success rate over ten landing trials.
We will release hardware designs, GSplat scenes, and dynamics models to make FalconWing an open-source flight kit for engineering students and research labs.
The FalconWing stack: 137 g airframe + 9 g camera, offboard compute, and a GSplat simulator for controller development.
The photorealistic Gaussian-splat digital twin of the indoor flight space.
@inproceedings{miao2027falconwing,
title = {FalconWing: An Ultra-Light Indoor Fixed-Wing UAV Platform for Vision-Based Autonomy},
author = {Miao, Yan and Shen, Will and Cui, Hang and Mitra, Sayan},
booktitle = {AIAA SciTech Forum},
year = {2027}
}