Performance-Guided Refinement for Visual Aerial Navigation using Editable Gaussian Splatting in FalconGym 2.0

Yan Miao, Ege Yuceel, Georgios Fainekos, Bardh Hoxha, Hideki Okamoto, Sayan Mitra

Abstract

Visual policy design is crucial for aerial navigation. However, state-of-the-art visual policies often overfit to a single track and their performance degrades when track geometry changes. We develop FalconGym 2.0, a photorealistic simulation framework built on Gaussian Splatting (GSplat) with an Edit API that programmatically generates diverse static and dynamic tracks in milliseconds. Leveraging FalconGym 2.0's editability, we propose a Performance-Guided Refinement (PGR) algorithm, which concentrates visual policy's training on challenging tracks while iteratively improving its performance. Across two case studies (fixed-wing UAVs and quadrotors) with distinct dynamics and environments, we show that a single visual policy trained with PGR in FalconGym 2.0 outperforms state-of-the-art baselines in generalization and robustness: it generalizes to three unseen tracks with 100% success without per-track retraining and maintains higher success rates under gate-pose perturbations. Finally, we demonstrate that the visual policy trained with PGR in FalconGym 2.0 can be zero-shot sim-to-real transferred to a quadrotor hardware, achieving a 98.6% success rate (69 / 70 gates) over 30 trials spanning two three-gate tracks and a moving-gate track.
BibTeX
@misc{miao2025performance,
  author = {Yan Miao and Ege Yuceel and Georgios Fainekos and Bardh Hoxha and Hideki Okamoto and Sayan Mitra},
  title = {{Performance-Guided Refinement for Visual Aerial Navigation using Editable Gaussian Splatting in FalconGym 2.0}},
  year = {2025},
  eprint = {2510.02248},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.02248},
}

Loading related content...

Figure