深度迁移：学习像模拟器一样“看”以实现现实世界无人机导航
Depth Transfer: Learning to See Like a Simulator for Real-World Drone Navigation
AI总结：
针对机器人强化学习中仿真与现实的视觉差异问题，提出基于域适应的深度迁移方法，通过VAE对齐仿真与真实深度的潜在空间实现策略直接迁移，在无人机导航任务中显著提升避障成功率并具备强泛化性。
摘要：
仿真到现实的迁移是机器人强化学习中的一项核心挑战。仿真与现实之间的差异会严重削弱策略性能，尤其是当策略接收高维输入（例如来自视觉的密集深度估计）时。我们提出了一种基于域适应的新型深度迁移方法，以弥合仿真深度数据与现实世界深度数据之间的视觉差距。首先训练一个变分自编码器（Variational Autoencoder, VAE），将仿真中的真实深度图像编码到潜在空间中，该潜在空间用作强化学习（reinforcement learning, RL）策略的输入。在部署阶段，对编码器进行微调，使立体深度图像与该潜在空间对齐，从而无需微调即可实现直接策略迁移。我们将该方法应用于无人机在杂乱环境中的自主导航任务。在IsaacGym中的实验表明，当输入从真实深度切换为立体深度时，我们的方法将避障成功率几乎提升了一倍。此外，我们证明仅使用IsaacGym生成的立体数据，就能成功迁移到照片级真实感模拟器AvoidBench，且性能优于现有最优基线。在室内和室外环境中的现实世界评估均证实了该方法的有效性，能够实现跨不同域的鲁棒且可泛化的基于深度的导航。
英文摘要：
Sim-to-real transfer is a fundamental challenge in robot reinforcement learning. Discrepancies between simulation and reality can significantly impair policy performance, especially if it receives high-dimensional inputs such as dense depth estimates from vision. We propose a novel depth transfer method based on domain adaptation to bridge the visual gap between simulated and real-world depth data. A Variational Autoencoder (VAE) is first trained to encode ground-truth depth images from simulation into a latent space, which serves as input to a reinforcement learning (RL) policy. During deployment, the encoder is refined to align stereo depth images with this latent space, enabling direct policy transfer without fine-tuning. We apply our method to the task of autonomous drone navigation through cluttered environments. Experiments in IsaacGym show that our method nearly doubles the obstacle avoidance success rate when switching from ground-truth to stereo depth input. Furthermore, we demonstrate successful transfer to the photo-realistic simulator AvoidBench using only IsaacGym-generated stereo data, achieving superior performance compared to state-of-the-art baselines. Real-world evaluations in both indoor and outdoor environments confirm the effectiveness of our approach, enabling robust and generalizable depth-based navigation across diverse domains.
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。
