arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.19600cs.RO
收藏

FlyMirage: 一种用于生成多样化和可扩展的无人机飞行数据的完全自动化生成流程

FlyMirage: A Fully Automated Generation Pipeline for Diverse and Scalable UAV Flight Data via Generative World Model

State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China(浙江大学工业控制技术状态重点实验室,杭州310027,中国);Differential Robotics, Hangzhou 311121, China(差分机器人,杭州311121,中国)

Jinhan Li, Xijie Huang, Weiqi Gai, Zhaoqi Wang, Qiyi He, Yijin Wang, Mo Zhu, Zhiyang Liu, Fei Gao, Xin Zhou, Yuze Wu, Ziming Ding

AI总结:

本文提出FlyMirage,一种完全自动化的生成流程,通过生成世界模型生成大规模、多样化且逼真的无人机视觉-语言导航数据,支持下一代具身导航模型的发展。

摘要:

在视觉-语言导航(VLN)领域,空中数据集在结合规模、多样性和现实感方面仍然有限,通常依赖于昂贵的真实世界场景或视觉受限的模拟。为了解决这些挑战,我们引入了FlyMirage,一种高度可扩展且完全自动化的空中VLN数据生成流程。我们的方法利用大型语言模型(LLM)作为环境设计师来促进场景多样性,配以生成世界模型,将这些设计转化为高保真的3D高斯点云(3DGS)场景。为了显著减少人工劳动并确保飞行数据的可行性,FlyMirage自动化了场景探索和语义信息获取,并进一步集成了动态可行的规划器用于无人机(UAV)轨迹生成。利用这一工具链,我们生成了一个大规模、多样化且逼真的空中VLN数据集,具有动态可行的飞行轨迹,旨在支持下一代具身导航模型的发展。

英文摘要:

In the field of Vision-Language Navigation (VLN), aerial datasets remain limited in their ability to combine scale, diversity, and realism, often relying on either costly real-world scenes or visually limited simulations. To address these challenges, we introduce FlyMirage, a highly scalable and fully automated data generation pipeline for aerial VLN. Our approach leverages large language models (LLM) as an environment designer to promote scene diversity, paired with a generative world model that instantiates these designs into high-fidelity 3D Gaussian Splatting (3DGS) scenes. To substantially reduce human labor and ensure the feasibility of flight data, FlyMirage automates scene exploration and semantic information acquisition, and further integrates a dynamically feasible planner for uncrewed aerial vehicle (UAV) trajectory generation. Utilizing this toolchain, we generate a large-scale, diverse, and photorealistic aerial VLN dataset. We further fine-tune the widely used pi_0 model on this dataset and demonstrate the improvement our data brings to the model's ability to navigate in completely unseen environments, both in simulation and in the real world. Project website: https://lij1500.github.io/flymirage_website/ .

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑