This paper presents GeoFlow-SLAM, a robust and effective Tightly-Coupled RGBD-inertial SLAM for legged robots operating in highly dynamicthis http URLintegrating 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-lessthis http URL, 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 atthis https URL
View on arXiv@article{xiao2025_2503.14247,
title={ GeoFlow-SLAM: A Robust Tightly-Coupled RGBD-Inertial Fusion SLAM for Dynamic Legged Robotics },
author={ Tingyang Xiao and Xiaolin Zhou and Liu Liu and Wei Sui and Wei Feng and Jiaxiong Qiu and Xinjie Wang and Zhizhong Su },
journal={arXiv preprint arXiv:2503.14247},
year={ 2025 }
}