Splat-Nav：高斯泼溅地图中的安全实时机器人导航
Splat-Nav: Safe Real-Time Robot Navigation in Gaussian Splatting Maps
AI总结：
该研究提出基于高斯泼溅地图的Splat-Nav实时机器人导航系统，含安全规划与视觉位姿估计模块，实现高速重规划与定位，性能优于传统及NeRF类导航方法。
摘要：
我们提出了Splat-Nav，一种适用于高斯泼溅（GSplat）场景的实时机器人导航流水线，GSplat是一种强大的新型3D场景表示方法。Splat-Nav由两个组件构成：1）Splat-Plan，一个安全规划模块；2）Splat-Loc，一个鲁棒的基于视觉的位姿估计模块。Splat-Plan基于数学上严格的碰撞约束，在地图中构建出本质安全的多面体走廊，随后在该走廊内生成一条贝塞尔曲线轨迹。Splat-Loc仅利用机载相机的RGB输入，借助GSplat场景固有的点云表示，提供实时递归状态估计。两个模块协同工作，使机器人能够递归地重新规划通往目标位置的平滑安全轨迹。目标可以通过位置坐标指定，也可以借助语义GSplat通过语言指令指定。我们在大量仿真实验中证明，与基于点云的方法相比，该方法的安全性有所提升。在总计126次硬件飞行实验中，我们证明其安全性和速度与动作捕捉和视觉里程计相当，但无需这些方法所需的手动帧对齐。我们实现了超过2Hz的在线重规划和约25Hz的位姿估计，比基于神经辐射场（NeRF）的导航方法快一个数量级，从而实现了实时导航。我们在项目页面https://chengine.github.io/splatnav/提供了实验视频。我们的代码库和ROS节点可在https://github.com/chengine/splatnav获取。
英文摘要：
We present Splat-Nav, a real-time robot navigation pipeline for Gaussian Splatting (GSplat) scenes, a powerful new 3D scene representation. Splat-Nav consists of two components: 1) Splat-Plan, a safe planning module, and 2) Splat-Loc, a robust vision-based pose estimation module. Splat-Plan builds a safe-by-construction polytope corridor through the map based on mathematically rigorous collision constraints and then constructs a Bézier curve trajectory through this corridor. Splat-Loc provides real-time recursive state estimates given only an RGB feed from an on-board camera, leveraging the point-cloud representation inherent in GSplat scenes. Working together, these modules give robots the ability to recursively re-plan smooth and safe trajectories to goal locations. Goals can be specified with position coordinates, or with language commands by using a semantic GSplat. We demonstrate improved safety compared to point cloud-based methods in extensive simulation experiments. In a total of 126 hardware flights, we demonstrate equivalent safety and speed compared to motion capture and visual odometry, but without a manual frame alignment required by those methods. We show online re-planning at more than 2 Hz and pose estimation at about 25 Hz, an order of magnitude faster than Neural Radiance Field (NeRF)-based navigation methods, thereby enabling real-time navigation. We provide experiment videos on our project page at https://chengine.github.io/splatnav/. Our codebase and ROS nodes can be found at https://github.com/chengine/splatnav.
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。
