The ros driver for the Odin product.

Statistical Uncertainty Learning for Robust Visual-Inertial State Estimation

[TRO 2025] OmniMap: A General Mapping Framework Integrating Optics, Geometry, and Semantics

Lidar Localization and Mapping

Source code for [TRO2025] VINGS-Mono: Visual Inertial Gaussian Splatting Monocular SLAM in Large Scenes.

Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM.

An open source implementation of CLIP.

ROS2 shm_msg based zero-copy for image and pointcloud.

ros2不同通信方式的使用示例，包括进程间（inter process）、零拷贝（zero copy）、进程内（intra process）通信，并结合测试数据和通信机制分析不同通信方式的性能差异。

[IROS 2025] LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction

A simple implementation of occupancy grid mapping.

Official code release for ConceptGraphs

[RAL-25] An online open-vocabulary mapping system that enables natural language querying to navigate dynamic scenes, with ROS support.

[ICLR 2025] Point-SAM: Promptable 3D Segmentation Model for Point Clouds

LIV-Eye: A Low-Cost LiDAR-Inertial-Visual Fusion 3D Sensor for Robotics and Embodied AI.

Robust and Adaptive Real-Time Localization for Electrified Vehicles in Complex Environments

[ICCV 25] 2D Gaussian Splatting based LiDAR Odometry And Mapping

Code of π^3: Permutation-Equivariant Visual Geometry Learning

Ground-Fusion++: a modular sensor-fusion SLAM system(IROS2025)

M3DGR: A Multi-sensor, Multi-scenario and Massive-baseline SLAM Dataset for Ground Robots(IROS2025)

Realtime implementation of CREStE in C++

[RSS 2025] CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance

The Online ROS2-Based Gaussian Splatting-Enabled Visualizer

FreeDOM: Online Dynamic Object Removal Framework for Static Map Construction Based on Conservative Free Space Estimation [RA-L 25]

[IROS 2025] CM-LIUW-Odometry: Robust and High-Precision LiDAR-Inertial-UWB-Wheel Odometry for Extreme Degradation Coal Mine Tunnels

[ICRA 25] InsCMPR: Efficient Cross-Modal Place Recognition via Instance-Aware Hybrid Mamba-Transformer

[IEEE RAL'25] LRFusionPR: A Polar BEV-Based LiDAR-Radar Fusion Network for Place Recognition