150克超轻无人机，用仿真训练视觉自主控制，落地成功率80%
FalconWing: An Ultra-Light Indoor Fixed-Wing UAV Platform for Vision-Based Autonomy
- 超轻机身+离线计算，配合3D高斯溅射仿真训练视觉控制器
- 跟踪任务100%成功，模拟到真实零样本迁移落地成功率80%
- 适合机器人、飞行控制方向学生与研究者快速搭建视觉自主系统
我们提出FalconWing，一款重150克的室内固定翼无人机平台，用于视觉自主。受控室内环境支持全年重复实验，但对重量和机动性有严格限制，因此设计了超轻型平台。FalconWing采用轻量级硬件（137克机体+9克相机）与离线计算，结合基于光栅化3D高斯溅射（GSplat）的逼真三维仿真软件栈，用于开发和评估视觉控制器。在两个挑战性视觉自主任务中验证：在领航-跟随任务中，最佳视觉控制器在30次试验中对3类领导动作实现100%跟踪成功率，并在模拟中对领导者外观变化保持鲁棒；在自主着陆任务中，纯仿真训练的控制器零样本迁移到真实硬件，10次着陆试验中达到80%成功率。论文发表后将开源硬件设计、GSplat场景及动力学模型，使FalconWing成为面向工程学生与科研实验室的开放飞行套件。
原文摘要 · Abstract (English)
We introduce FalconWing, an ultra-light (150 g) indoor fixed-wing UAV platform for vision-based autonomy. Controlled indoor environment enables year-round repeatable UAV experiment but imposes strict weight and maneuverability limits on the UAV, motivating our ultra-light FalconWing design. FalconWing couples a lightweight hardware stack (137g airframe with a 9g 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 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 upon publication to make FalconWing an open-source flight kit for engineering students and research labs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。