ROS 2 LiDAR SLAM for pointcloud-map authoring, benchmarking, and Autoware-compatible map workflows.

3D LIDAR Localization using NDT/GICP and pointcloud map in ROS 2 (Not SLAM)

100+ robotics algorithms in Rust: planning, localization, SLAM, control, and benchmarks.

Modern C++ GNSS/RTK/PPP/CLAS toolkit.

GPU particle-filter GNSS positioning for the urban canyon: ray-traced NLOS rejection & FGO

GPU-accelerated robotics (CUDA + C++)

ROS 2 package of tightly-coupled lidar inertial ndt/gicp slam

gnss/imu localization using kalman filter

lidar localizer in Autoware AI

Numpy-only dynamic object removal for LiDAR point clouds — 3D box crop + temporal filtering. No GPU, no deep learning.

ROS2 porting of ndt_omp

Python sample code of 3D pose optimization SLAM

C++ from-paper reimplementations of LiDAR localization & odometry papers — honestly benchmarked on KITTI, with tests.

A ROS2 Wrapper for LittleSLAM, which is a 2D-LiDAR SLAM for educational use

Python sample code of 2D NDT Scan Matching

(unofficial)(2025)RANSAC Revisited: An Improved Algorithm for Robust Subspace Recovery under Adversarial and Noisy Corruptions

ros1 package for 2d laser deskew using tf.

A header-only program of 3d rotary lidar undistortion using 9-axis imu

AMCL(Adaptive Monte Carlo Localization) using 3D LiDAR for ROS.

attitude estimator with gyro bias correction

Python sample of Gaussian Particle Filter localization

CLI-first QA toolkit for point clouds, trajectories, and 3D perception outputs.

C++ program for performing 3D and 2D velocity transformations using Lie algebra.

ROS 2 underwater localization for real AUV/ROV data, validated on public ocean datasets.

SLAM Handbookの内容をPython + Jupyter Notebookで学ぶハンズオン教材

A readiness checker for recorded ROS1/ROS2 bags

gnss/imu/wheel localizer for autoware

A C++ port of the MathematicalRobotics library

Particle filtering model predictive control simulation.

Single-image 6DoF Visual Positioning System on top of COLMAP / hloc. CLI + Python API + ROS2 node. Verified on south-building and Cambridge Landmarks ShopFacade.

Run existing World Models from ROS 2 — runtime, adapters, benchmark, visualization.

Same-place comparison for LiDAR and camera: retrieve, align, compare, validate maps.

Pure-Rust visual & visual-inertial SLAM for GPS-denied robots and UAVs — beats ORB-SLAM2's published KITTI ATE on seq00/09, OV2SLAM-class accuracy on EuRoC

GLIL CPU reproduction fork: reproducible LiDAR odometry configs for MegaParticles samples and Ouster smoke checks

ROS2-native runtime, benchmark, and adapter hub for Vision-Language-Action models.

GNSS-denied space navigation: star tracker, lunar TRN, VO, and hazard-aware routing.

ROS 2-native embodied runtime infrastructure for Genesis World. Multi-agent navigation, replay, benchmarks, and AI-tool safety boundaries.

Runtime DevTools for ROS 2 — live graph, bottleneck detection, callback tracing, AI briefings, and a fleet view.

Nav2 planners & controllers battle head-to-head. ROS 2 · ONNX · browser game.

lidar_slam_2d: 2D LiDAR SLAM experiment platform with Cartographer parity and benchmark-driven iteration.

estimator to minimize Wahba's loss function for satellite attitude

Swarm robot battles + a pure-Python MAPF algorithm zoo.

Robot Native Engine — robot-native Rust simulation core with physics, sensors, Python bindings, and optional ROS 2 adapters.

Robot escape game + semantic graph navigation in Python.

Readable Visual SLAM in 6k lines of C++17. Mono/RGB-D/Stereo/DL-Depth, loop closing, ROS2 node. BSD-2-Clause.

Detect and map individual tree trunks from LiDAR point clouds

Curated catalog of notable repositories from major robotics GitHub organizations

Readable C++17 sparse Structure-from-Motion toolkit inspired by COLMAP, focused on modular incremental mapping, tests, COLMAP-style I/O, and comparison tooling.

Physical AI-friendly robotics middleware for replayable, inspectable, simulation-native robot runtimes.

Minimal Python robotics examples for planning, manipulation, active perception, and embodied AI. No ROS, GPU, or heavy simulator.

GNSS-Radar is a web application to show the current GNSS constellation

Rust-native spatial computing: point clouds, LiDAR/COPC, geometry, wgpu, RANSAC, ICP, and robotics-ready spatial data

🎮 8 browser games + 11 Roblox games. Play now: https://rsasaki0109.github.io/game_product_ws/

Rust-first, agent-first robotics workspace with ROS 2 hooks, YAML skills, simulator/hardware backends, and LLM-plannable execution.

Lightweight paper notes repository for robotics papers

Lightweight, GPU-free Python CLI to benchmark LLM-generated robotics: perception (GNSS, LiDAR, vision), planning (grid A*), control (1st-order tracking). Swappable model hooks + JSON.

CLI-first navigation observability, benchmarking, visualization, and failure analysis for ROS2/Nav2 and Autoware.

No description.

MATLAB and C++ implementations of sideslip angle estimators

Web-first visual AI flow builder built around Flow IR, deterministic validation, server-side execution, and TypeScript.

No description.

No description.

Character-first pair programming app with Live2D/fallback personas, local LLM support, and a GitHub Pages demo.

Camera-based ADAS OSS in Python. Perception today, planning next.

AI-native open-source parametric 3D CAD engine in Rust with OCCT, semantic TopoRef, and JSON-RPC agent API.

AI-native, GPU-native 3D creation platform in Rust. SceneDB + ECS editor with GLB import, point clouds, and Gaussian splat viewport rendering.

v1.7β — ROS2 observability. Boost Lanelet2 bin, action preempt, gateways.

AI-native · Cloud-native · GPU-native open geospatial workbench — workflow graphs, DuckDB, wgpu, COG/COPC, WASM plugins.

Exploration control plane for rsasaki0109 public repos — cross-repo comparison, heuristic evaluation, and minimal interface synthesis

Local wardrobe assistant: Ollama Vision + SQLite → 3 outfit ideas (safe/clean/bold). CLI & Streamlit. No cloud APIs.

部屋画像からインテリア改善案を返す MVP（FastAPI / Next.js / Ollama Qwen2.5-VL）

ジェンダー動画変換

2026年4月施行「自転車青切符」対応 — ながらスマホ・信号無視・傘差し運転をAIで自動検知 | YOLO + pose estimation + VLM verification

Automatic point cloud to IFC (BIM) conversion using semantic segmentation

Panoptic segmentation for autonomous forest navigation

Evaluate BIM model quality against point cloud measurements

No description.

ROS2 bridge and workflow workspace for Virtual Tsukuba Challenge (VTC)

Detect construction progress by comparing point cloud scans over time

Rust + Dora dataflow demos and ROS2 bridge integration for navigation/SLAM stack ports paired with ros2-from-ros.

ROS2 (Jazzy) reimplementations and Nav2 integration demos for selected ROS1 navigation, SLAM, and planning packages.

No description.

Find localization & perception edge cases in driving logs. Supports KITTI, nuScenes, rosbag (GLIM/FAST-LIO), PPC. Auto-detects turning, braking, GPS drift, loop closure.

青空文庫の文学作品を登場人物と対話しながら読むインタラクティブ読書アプリ

Cross-domain object detection/tracking evaluation tool for robotics datasets (YOLOv8, Grounding DINO, ByteTrack, COCO mAP)

Interactive genealogy of robotics & AI companies and their technology evolution

Season-invariant visual place recognition in forest environments

Annotate Rohbau3D construction site point clouds via panorama back-projection

鬼退治！豆まきバトル

No description.

No description.

No description.

No description.

ROS1/ROS2 data analystics tools

No description.

Benchmark-first experimentation overlay for Autoware. Plug research methods in, compare on shared scenarios and rosbags, turn failures into new benchmarks.

Nav2 behavior-tree plugins that bridge semantic-toponav's v1.0 SemanticWaypointArray to NavigateThroughPoses.

No description.

GitHub Action: config-driven point cloud / SLAM / perception QA with PR comments

Interactive genealogy tree of Robotics & AI technologies. Live demo available.

Scenario-as-Code test runner for Nav2. Run repeatable navigation regression tests in simulation and CI.

GitHub Action for bagx — benchmark gates, PR readiness diffs, and shields.io badges

Foxglove extension panel that visualizes FleetPlanResult / ConflictExplanation from the semantic-toponav planning layer.

Human video → humanoid motion. MuJoCo 1v1 fights & tournaments. pip: robotdance

Executable visual guide to mathematics for future robotics, Physical AI, world models, and humanoids — tiny Python code + GIFs.

GitHub profile README for Ryohei Sasaki

The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating

A Robust Approach for LiDAR-Inertial Odometry Without Sensor-Specific Modelling

A collection of GTSAM factors and optimizers for point cloud SLAM

Open source visual localization for self-driving vehicles

No description.

A computationally efficient and robust LiDAR-inertial odometry (LIO) package

Real World Datasets for Autonomous Navigation

Release repo for our SLAM Handbook

システム設計面接をAIが自動評価するWebアプリ + CLIツール (Next.js / Supabase / Claude API)

ロボティクス・自動運転・3D再構成・VLA関連の技術ポストを月次でアーカイブ | Monthly archive of robotics, autonomous driving, 3D reconstruction & VLA posts

No description.

No description.