Modern autonomous navigation systems predominantly rely on lidar and depth cameras. However, a fundamental question remains: Can flying robots navigate in clutter using solely monocular RGB images? Given the prohibitive costs of real-world data collection, learning policies in simulation offers a promising path. Yet, deploying such policies directly in the physical world is hindered by the significant sim-to-real perception gap. Thus, we propose a framework that couples the photorealism of 3D Gaussian Splatting (3DGS) environments with Adversarial Domain Adaptation. By training in high-fidelity simulation while explicitly minimizing feature discrepancy, our method ensures the policy relies on domain-invariant cues. Experimental results demonstrate that our policy achieves robust zero-shot transfer to the physical world, enabling safe and agile flight in unstructured environments with varying illumination.
@article{arxiv.2512.17349,
title = {Flying in Clutter on Monocular RGB by Learning in 3D Radiance Fields with Domain Adaptation},
author = {Xijie Huang and Jinhan Li and Tianyue Wu and Xin Zhou and Zhichao Han and Fei Gao},
journal= {arXiv preprint arXiv:2512.17349},
year = {2025}
}