{"ID":2861618,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.02248","arxiv_id":"2510.02248","title":"Performance-Guided Refinement for Visual Aerial Navigation using Editable Gaussian Splatting in FalconGym 2.0","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.","short_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 programm...","url_abs":"https://arxiv.org/abs/2510.02248","url_pdf":"https://arxiv.org/pdf/2510.02248v1","authors":"[\"Yan Miao\",\"Ege Yuceel\",\"Georgios Fainekos\",\"Bardh Hoxha\",\"Hideki Okamoto\",\"Sayan Mitra\"]","published":"2025-10-02T17:36:50Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}