SOUS VIDE：在高斯泼溅真空环境中“烹饪”视觉无人机导航策略
SOUS VIDE: Cooking Visual Drone Navigation Policies in a Gaussian Splatting Vacuum
AI总结：
本研究提出名为SOUS VIDE的端到端视觉无人机导航方案，结合FiGS高斯泼溅仿真器与SV-Net轻量策略网络，实现零样本 sim-to-real 迁移，在多种复杂扰动下仍具备强鲁棒性。
摘要：
我们提出了一套全新的模拟器、训练方法与策略架构，统称为SOUS VIDE，用于实现端到端的视觉无人机导航。我们训练得到的策略可实现零样本从仿真到现实的迁移，仅依靠机载感知与计算就能在真实场景中表现出鲁棒的性能。我们开发的模拟器名为FiGS，将计算简洁的无人机动力学模型与高视觉保真度的高斯泼溅场景重建相结合。FiGS能够快速模拟无人机飞行过程，生成照片级真实感图像的速率最高可达130 fps。我们利用FiGS从具备特权状态与动力学信息的专家模型预测控制（MPC）中收集10万至30万组图像/状态-动作对，数据采集过程中会对动力学参数与空间扰动进行随机化处理。随后我们将该专家MPC的知识蒸馏到一个名为SV-Net的轻量级神经网络架构中，形成端到端的视觉运动策略。SV-Net可处理彩色图像、光流与IMU数据流，在无人机上以20 Hz的频率输出低空推力与机体速率指令。至关重要的是，SV-Net包含一个用于低空控制的可学习模块，可在运行时适应无人机动力学的变化。在包含105次硬件实验的测试中，我们证明SOUS VIDE策略对以下情况均具备鲁棒性：30%的质量变化、40 m/s的阵风、60%的环境亮度变化、场景中物体被移动或移除，以及人员在无人机视野内快速移动。代码、数据与实验视频可在项目页面获取：https://stanfordmsl.github.io/SousVide/。
英文摘要：
We propose a new simulator, training approach, and policy architecture, collectively called SOUS VIDE, for end-to-end visual drone navigation. Our trained policies exhibit zero-shot sim-to-real transfer with robust real-world performance using only onboard perception and computation. Our simulator, called FiGS, couples a computationally simple drone dynamics model with a high visual fidelity Gaussian Splatting scene reconstruction. FiGS can quickly simulate drone flights producing photorealistic images at up to 130 fps. We use FiGS to collect 100k-300k image/state-action pairs from an expert MPC with privileged state and dynamics information, randomized over dynamics parameters and spatial disturbances. We then distill this expert MPC into an end-to-end visuomotor policy with a lightweight neural architecture, called SV-Net. SV-Net processes color image, optical flow and IMU data streams into low-level thrust and body rate commands at 20 Hz onboard a drone. Crucially, SV-Net includes a learned module for low-level control that adapts at runtime to variations in drone dynamics. In a campaign of 105 hardware experiments, we show SOUS VIDE policies to be robust to 30% mass variations, 40 m/s wind gusts, 60% changes in ambient brightness, shifting or removing objects from the scene, and people moving aggressively through the drone's visual field. Code, data, and experiment videos can be found on our project page: https://stanfordmsl.github.io/SousVide/.
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。
