#Localization (6)

SSIO: Self-Supervised Inertial Odometry Without Labels

@QiuYuhengQiu · 25 views · 2026-10-28

GeoFlow-SLAM: A Robust Tightly-Coupled RGBD-Inertial and Legged Odometry Fusion SLAM for Dynamic Legged Robotics

GeoFlow-SLAM (Horizon Robotics, IROS 2025) targets three stacked failure modes of quadruped localization: motion blur and IMU distortion from fast locomotion, and feature scarcity in texture-less scenes. Three interlocking contributions: dual-stream optical-flow tracking aided by prior map points and poses (a 3D-to-2D reprojection stream plus a 2D-to-2D fallback stream); a pose-initialization priority chain degrading from leg odometry to IMU, PnP, GICP, and finally a constant-velocity model; and a tightly-coupled optimization framework placing depth-to-map point-to-plane and GICP relative-pose residuals alongside visual reprojection and IMU pre-integration in one factor graph. On four real Go2 sequences (office, texture-less corridor, underground parking, open plaza) it is the only method that succeeds on Seq2-4, with 88% improvement over VINS-RGBD on Seq1. ScanNet mean ATE 0.0779 m (~70% better than ORB-SLAM3), TUM 0.0129 m; global plane-feature maps are still built in the structure-less texture-less TUM extremes. Code and data are open source (HorizonRobotics/GeoFlowSlam).

Xiao, Tingyang, Zhou, Xiaolin, Liu, Liu · 643 views · Mar 18, 2025

SLAMLocalization

Mar 18, 2025

UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization

Recent geometric foundation models enable feed-forward inference for SLAM, but their predictions are strongly dependent on the input view set, which leads to geometric inconsistencies and trajectory drift when results are chained over long sequences. Online deployment further exposes a trade-off between the low latency of two-view tracking and the constraint richness of multi-view inference. We introduce UniSim-SLAM, an integrated system that runs lightweight two-view keyframe tracking in the frontend and performs periodic multi-view submap refinement in the backend. To combine predictions defined in heterogeneous local coordinates with inconsistent scales, we formulate a unified multi-level factor graph on Sim(3) that jointly optimizes global keyframe poses and submap poses. The graph integrates temporal view-to-view odometry edges, view-to-submap bridge edges with depth-statistics scale anchoring, and submap-to-submap tie and scale constraints to enforce consistent similarity relations across submaps. Experiments on TUM RGB-D and 7-Scenes show that UniSim-SLAM achieves state-of-the-art accuracy in the uncalibrated setting, reducing trajectory error by 38.5% on TUM RGB-D and 45.9% on 7-Scenes compared to prior best results. Project page: https://vision3d-lab.github.io/unisim-slam/

Inha Lee, Dongjae Jeong, Junhee Lee · 632 views · Aug 3, 2026

SLAM3D Vision

Aug 3, 2026

Movella Xsens MTi-8 RTK GNSS/INS Module

Movella (formerly Xsens, Netherlands) MTi-8 is an RTK-enhanced GNSS/INS module: 1 cm + 1 ppm CEP RTK position, 1 deg RMS heading, 0.5 deg RMS roll/pitch; 2000 deg/s gyro range, 6 deg/h bias stability, 0.003 deg/s/sqrt(Hz) noise density in a 12.1x12.1x2.55 mm, 0.6 g package with up to 1 kHz output. Centimeter-grade position and attitude for drones, inspection robots and autonomous systems.

COMPONENT

GNSS/INSRTK

Movella Xsens MTi-7 GNSS/INS Module

Movella (formerly Xsens, Netherlands) MTi-7 is the smallest GNSS/INS module of its kind: 12.1x12.1x2.55 mm at 0.6 g with 0.5 deg RMS roll/pitch, 1.5 deg RMS heading, 1 m CEP position; 2000 deg/s gyro range, 6 deg/h in-run bias stability, 0.003 deg/s/sqrt(Hz) noise density, onboard magnetometer, up to 1 kHz output at <150 mW. Miniature position and attitude for drones, inspection robots and autonomous navigation devices.

COMPONENT

GNSS/INSIMU

Movella Xsens MTi-670G GNSS/INS Module

Movella (formerly Xsens, Netherlands) MTi-670G is an industrial-grade GNSS/INS module fusing an onboard u-blox ZED-F9 GNSS receiver with the IMU: 0.2 deg RMS roll/pitch, 0.8 deg RMS heading, 1 m CEP position; gyro range +/-2000 deg/s with 8 deg/h in-run bias stability and 0.007 deg/s/sqrt(Hz) noise density; onboard magnetometer and barometer; IP68-equivalent, 56.5x40.9x36.75 mm at 98 g, 4.5-24 V input at <1 W, CAN/RS232, up to 2 kHz output. Delivers continuous, reliable position and attitude for inspection robots, AGV/AMR and unmanned platforms in GNSS-denied areas such as urban canyons and tunnels.

COMPONENT

GNSS/INSIMU

As an Amazon Associate, we earn from qualifying purchases.