Research Analyzer
← Back ICRA 2026

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

PDF

AI summary

Key figure (auto-extracted from paper)
A single visual policy trained with Performance-Guided Refinement in an editable Gaussian Splatting simulator generalizes to unseen tracks and transfers zero-shot to real hardware with near-perfect success.
Gaussian Splatting Sim-to-Real Visual Navigation Policy Refinement Aerial Robotics FalconGym

Problem

State-of-the-art visual policies for aerial navigation overfit to specific training tracks and fail to generalize to new geometries, requiring costly per-track data collection and retraining.

Approach

The authors introduce FalconGym 2.0, a photorealistic simulator with a programmatic Edit API for rapid track generation, and develop a Performance-Guided Refinement algorithm that iteratively targets challenging tracks to train a robust, modular visual policy.

Key results

  • FalconGym 2.0 enables millisecond-scale generation of diverse photorealistic tracks via an editable GSplat API
  • The PGR algorithm trains a single visual policy that achieves 100% success across three unseen simulation tracks without per-track retraining
  • The policy maintains higher robustness under gate-pose perturbations compared to state-of-the-art baselines
  • Zero-shot sim-to-real transfer to quadrotor hardware achieves a 98.6% success rate across multiple tracks

Why it matters

It eliminates the need for per-track data collection and retraining, enabling robust, generalizable visual navigation for aerial robots in dynamic real-world environments.

Abstract

Visual policy design is crucial for aerial naviga- tion. However, state-of-the-art visual policies often overfit to a single track and their performance degrades when track geom- etry changes. We develop FalconGym 2.0, a photorealistic sim- ulation 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 training on chal- lenging tracks while iteratively improving 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 zero-shot sim-to- real transfer of the PGR-trained visual policy to quadrotor hardware, achieving a 98.6% success rate (69/70 gates) over 30 trials across two three-gate tracks and one moving-gate track.

Index terms

Vision-Based Navigation Aerial Systems: Perception and Autonomy

Related papers