GeoFlow-SLAM：一种面向动态足式机器人的鲁棒紧耦合 RGBD-惯性与足式里程计融合 SLAM
GeoFlow-SLAM: A Robust Tightly-Coupled RGBD-Inertial and Legged Odometry Fusion SLAM for Dynamic Legged Robotics
- Horizon Robotics（地平线机器人）
- D-Robotics（达闼机器人）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
GeoFlow-SLAM 提出紧耦合 RGBD-惯性与足式里程计融合框架，利用双流光流增强快速运动下的特征匹配，并通过新型几何约束优化提升无纹理环境中的鲁棒性与精度，在足式机器人数据集上达到 SOTA。
AI中文摘要：
本文提出了 GeoFlow-SLAM，一种鲁棒且有效的紧耦合 RGBD-惯性 SLAM，适用于经历剧烈高频运动的足式机器人。通过融合几何一致性、足式里程计约束和双流光流（GeoFlow），本方法解决了三个关键挑战：快速运动过程中的特征匹配与位姿初始化失败，以及无纹理场景中的视觉特征稀缺问题。具体而言，在快速运动场景中，通过利用结合先验地图点和位姿的双流光流，特征匹配得到显著增强。此外，我们提出了一种针对足式机器人快速运动和 IMU 误差的鲁棒位姿初始化方法，融合了 IMU/足式里程计、帧间 Perspective-n-Point（PnP）和广义迭代最近点（GICP）。进一步地，首次引入了一种紧耦合深度到地图与 GICP 几何约束的新型优化框架，以提高长时间、视觉无纹理环境下的鲁棒性和精度。所提出的算法在采集的足式机器人数据和开源数据集上达到了最先进（SOTA）水平。为进一步促进研究与发展，开源数据集和代码将在 https://github.com/HorizonRobotics/GeoFlowSlam 公开提供。
英文摘要：
This paper presents GeoFlow-SLAM, a robust and effective Tightly-Coupled RGBD-inertial SLAM for legged robotics undergoing aggressive and high-frequency motions.By integrating geometric consistency, legged odometry constraints, and dual-stream optical flow (GeoFlow), our method addresses three critical challenges:feature matching and pose initialization failures during fast locomotion and visual feature scarcity in texture-less scenes.Specifically, in rapid motion scenarios, feature matching is notably enhanced by leveraging dual-stream optical flow, which combines prior map points and poses. Additionally, we propose a robust pose initialization method for fast locomotion and IMU error in legged robots, integrating IMU/Legged odometry, inter-frame Perspective-n-Point (PnP), and Generalized Iterative Closest Point (GICP). Furthermore, a novel optimization framework that tightly couples depth-to-map and GICP geometric constraints is first introduced to improve the robustness and accuracy in long-duration, visually texture-less environments. The proposed algorithms achieve state-of-the-art (SOTA) on collected legged robots and open-source datasets. To further promote research and development, the open-source datasets and code will be made publicly available at https://github.com/HorizonRobotics/GeoFlowSlam
