Skip to content
Agientry
← Back to Videos

ROS 2 3D LiDAR Localization on Prior Maps

Loading video
Loading video

An open-source ROS 2 localization stack using NDT or GICP against prior point-cloud maps, with Nav2 and Livox MID-360 support; a 390m outdoor run reports about 0.26m RMSE.

ROS2LiDAR LocalizationPoint cloudsNDTGICPNav2Livox MID-360RoboticsLiDAR
Category: perception
Author: @rsasaki0109
Date: 2026-10-16T00:00:00
Source: https://x.com/rsasaki0109/status/2111200555179860268
Reference: https://github.com/rsasaki0109/lidar_localization_ros2

Related Videos

A Drone That Flies on Two Cameras and an IMU, No Map or GNSS
0:20

A Drone That Flies on Two Cameras and an IMU, No Map or GNSS

@tokufxug · 438 views · 2026-09-22
DronesVisual navigationStereo Camera
RoboSense Ships 719K LiDAR Units in H1 2026
0:08

RoboSense Ships 719K LiDAR Units in H1 2026

@techniahqrobot · 478 views · 2026-08-01
LiDARRoboSensePerception
Jev 1.14 adds image bounding box generation, now served through the TypeLLM API

Jev 1.14 adds image bounding box generation, now served through the TypeLLM API

@TypeLLM · 37 views · 2026-10-15
JevTypeLLMBounding Box
DirtyMoCap: Robust Motion Capture from Noisy, Unconstrained Markers
0:23

DirtyMoCap: Robust Motion Capture from Noisy, Unconstrained Markers

@yuliangxiu · 193 views · 2026-10-11
Motion CaptureDirtyMoCapSMPL-H
SpatialLM: Labeled 3D Room Layouts from Monocular Phone Video
0:51

SpatialLM: Labeled 3D Room Layouts from Monocular Phone Video

@0x0SojalSec · 537 views · 2026-10-09
Spatial Intelligence3D Scene UnderstandingVision-language models
R3: streaming feed-forward 3D reconstruction via relative-pose regression — 372M params, 20+ FPS, thousands of frames, open-sourced for NeurIPS 2026
0:25

R3: streaming feed-forward 3D reconstruction via relative-pose regression — 372M params, 20+ FPS, thousands of frames, open-sourced for NeurIPS 2026

@CongrongX · 593 views · 2026-10-01
R33D reconstructionStreaming

As an Amazon Associate, we earn from qualifying purchases.