Unitree G1
Bipedal humanoid robot by Unitree Robotics, designed as a compact research, development, and developer platform.
Applications
- Research
- Home Assistance
Perception · Perception & Vision Software
LIO-SAM
lio-sam-ros2 (community port)·Tixiao Shan (autor LIO-SAM)
Active Open source Real-time capable API available
CATEGORYPerception · Perception & Vision Software
READINESSTRL 8
ADOPTION SCALEEstablished Open Source
LICENSESBSD-3-Clause
FIRST RELEASE2020
LIO-SAM (Tightly-Coupled LiDAR-Inertial Odometry via Smoothing and Mapping) is an open-source 3D LiDAR-Inertial SLAM framework developed at MIT CSAIL's Marine Robotics Group (Prof. John J. Leonard) by Tixiao Shan, Brendan Englot, Drew Meyers, Wei Wang, Carlo Ratti, and Daniela Rus (IROS 2020). The innovation: tightly-coupled fusion of LiDAR + IMU + GPS in a factor graph using the GTSAM library (Georgia Tech). BSD-3-Clause license.
The factor-graph architecture contains four types of factors: (1) IMU preintegration factors between LiDAR frames (~10 Hz), (2) LiDAR odometry factors with scan-to-local-map matching, (3) GPS factors for absolute global localization (optional), (4) loop closure factors with appearance or geometric matching. Optimization via iSAM2 (incremental smoothing and mapping) — efficient online update without full re-optimization. A sliding-window LiDAR matching keeps the computational complexity constant.
Sensor support: Velodyne VLP-16/HDL-32/HDL-64, Ouster OS0/OS1/OS2, Livox Mid-70/Mid-360/Avia, 9-axis IMUs (e.g., Xsens MTi-300, Bosch BMI088). ROS 1 package and a community port for ROS 2 Humble. A baseline benchmark for hundreds of new LiDAR-Inertial SLAM papers (e.g., FAST-LIO, FAST-LIO2, Point-LIO, LVI-SAM by the same author). Runs in real time on Jetson AGX Orin and consumer CPUs (Intel i7+). LIO-SAM has been used in the MIT autonomous "Roboat" boat as well as many mobile robots and off-road autonomous vehicles.
Type & Roles
Software types
SLAM Library
Perception Stack
A Perception Stack encompasses the software layers that process data from cameras, LiDARs, IMUs, microphones, and other sensors in order to recognise the surrounding environment, perform localisation, detect and track objects, and interpret the scene. It is typically the first processing stage in an autonomous robot's data pipeline, feeding its outputs to planning and control stacks.
API Library
An API Library is a software package that exposes programmatic interfaces for communicating with a device, service, or system. In robotics it typically forms a lightweight integration layer built on top of the manufacturer's official API or an open-source project, abstracting low-level protocol details and providing language-native bindings (Python, C++, Java, etc.).
Select an item to see its description.
Main category
Perception & Vision SoftwareSDKs
Roles in robotics ecosystem
PerceptionSLAM & LocalizationComputer VisionAPI AccessDeveloper Enablement
Software family
Family
Perception & Vision
A family of open-source robotic perception libraries: Visual SLAM (ORB-SLAM, RTAB-Map), computer vision (OpenCV), point cloud processing (PCL, Open3D), detection and segmentation (YOLO, Detectron2).
Maturity & Adoption
8 / 9
Prototype / pilot phase
ResearchPrototypeProduction
Adoption scaleEstablished Open Source
Maintenance statusPassively Maintained
First release2020
Last update20 May 2026
Deployments
MIT Roboat — an autonomous research boat in Amsterdam (Senseable City Lab + AMS Institute) uses LIO-SAM as the base localization stack. Off-road autonomous vehicles (Hyundai, Toyota Research). An academic benchmark cited in hundreds of IROS / ICRA / RSS 2021–2025 papers. A foundation for many commercial mobile-mapping systems (FARO, Emesent Hovermap).
Community
github.com/TixiaoShan/LIO-SAM ~3.8k★, ~1.3k forks. The seminal paper (Shan et al., IROS 2020) has > 1500 citations. Active fork lio-sam-ros2 (~700★) for ROS 2.
Depends on
P(
PCL (Point Cloud Library)
An open-source C++ library for processing 3D point clouds — filtering, segmentation, registration (ICP), 3D features, surface reconstruction. Initiated at Willow Garage in 2010.
O
OpenCV
Open Source Computer Vision Library — the most widely used open-source computer vision library (> 4000 functions). Initiated in 1999 by Gary Bradski at Intel; today maintained by the OpenCV Foundation.
R2
ROS 2
Open-source framework for building robot software. The successor to ROS 1, built on DDS with native support for distributed, real-time and multi-platform systems. The de facto standard in research and commercial robotics.
Integrates with
R2
ROS 2
Open-source framework for building robot software. The successor to ROS 1, built on DDS with native support for distributed, real-time and multi-platform systems. The de facto standard in research and commercial robotics.
R1
ROS 1 Noetic Ninjemys
The last and final LTS distribution of ROS 1, released in May 2020 for Ubuntu 20.04. Support ended on 31 May 2025 — all new projects should be built on ROS 2 instead.
Related robotics software
O
ORB-SLAM3
An open-source third-generation Visual SLAM framework from the University of Zaragoza. Supports monocular, stereo, and RGB-D cameras as well as Visual-Inertial SLAM. Version 1.0 was released in July 2021.
R
RTAB-Map
Real-Time Appearance-Based Mapping — an open-source graph-based RGB-D / Stereo / LiDAR SLAM developed since 2013 at IntRoLab (Université de Sherbrooke). The most widely used SLAM in the ROS / ROS 2 ecosystem.
C
Cartographer
An open-source 2D / 3D pose-graph SLAM library. Created at Google in 2016 (Wolfgang Hess et al.). Supports 2D and 3D LiDAR with IMU integration and a cartographer_ros package for ROS / ROS 2.
P(
PCL (Point Cloud Library)
An open-source C++ library for processing 3D point clouds — filtering, segmentation, registration (ICP), 3D features, surface reconstruction. Initiated at Willow Garage in 2010.
O
OpenCV
Open Source Computer Vision Library — the most widely used open-source computer vision library (> 4000 functions). Initiated in 1999 by Gary Bradski at Intel; today maintained by the OpenCV Foundation.
R2
ROS 2
Open-source framework for building robot software. The successor to ROS 1, built on DDS with native support for distributed, real-time and multi-platform systems. The de facto standard in research and commercial robotics.
Supported robot models
Unitree H1
Full-size general-purpose humanoid (~180 cm, ~47 kg). Bipedal, 5 DOF per leg, 3.3 m/s walking speed, 360° perception via 3D LiDAR + depth camera, Unitree M107 PMSM joint motors (~360 N·m peak knee torque).
Applications
- Research
Atlas
Boston Dynamics bipedal humanoid robot. The fully electric generation unveiled in 2024 succeeds the hydraulic Atlas that was retired after more than a decade of research.
Applications
- Factory Automation
- Research
- Production Line Operation
- Object Manipulation
Target robotic platforms
Humanoid
Quadruped
Mobile Robot
Robotic Arm
Service Robot
Research Robot
Drone / UAV
Supported hardware
NVIDIA Jetson AGX Orin 64GB
NVIDIA Jetson AGX Xavier
compute · compute_modules · industrial
NVIDIA Jetson Orin NX 16GB
compute · compute_modules · industrial
Velodyne VLP-16 (Puck)
sensing · lidar · industrial
Livox Mid-360
sensing · lidar · industrial · LiDAR Sensor Family
Ouster OS1 (REV8)
sensing · lidar · industrial · Ouster REV8 OS
ROS supportCompatibility with ROS / ROS 2 ecosystem
Official ROS 1 PackagePakiet dostępny w oficjalnym rejestrze ROS 1 (packages.ros.org)
Community ROS 2 WrapperWrapper ROS 2 tworzony i utrzymywany przez społeczność, nie przez producenta
System capabilities
⊙
Open source
Source code is publicly available under an open-source license — enables security audits, custom modifications, and integration without licensing barriers.
✓
⚡
Real-time capable
Designed with timing-determinism guarantees — meets the requirements of control loops, safety systems, and tasks demanding low, predictable latency.
✓
⟨/⟩
API available
The software exposes a programmable interface (REST, gRPC, SDK, or language bindings) that enables automation and integration with other systems.
✓
📦
Pre-built / binary
Distributed as ready-to-use binary packages, container images, or installers — no need to build from source.
×
Programming languages
C++
Operating systems
Ubuntu 22.04Ubuntu 20.04Debian
Minimum hardware requirements
Minimum hardware requirements
CPUSix-core x86-64 ≥ 2.5 GHz (Intel i7 / AMD Ryzen 7) or Jetson AGX Orin — LIO-SAM is CPU-bound and uses OpenMP for parallelization.
RAM (GB)8
GPUNot required. LIO-SAM is CPU-only — GTSAM iSAM2 and scan matching run on the CPU.
Disk (GB)5
Requires GTSAM ≥ 4.0.3, PCL ≥ 1.10, OpenCV ≥ 4.2, Eigen3 ≥ 3.3.7. Ubuntu 20.04 + ROS 1 Noetic (original) or Ubuntu 22.04 + ROS 2 Humble (community fork lio-sam-ros2).
Packaging & distribution
Package managers
Source – CMake / ament_cmakeGitHub Releases / GitHub Actions Artifacts
CPU architectures
x86_64 (AMD64)ARM64 / AArch64NVIDIA Jetson – AArch64 (JetPack)
Installation difficulty
LevelAdvanced
Protocols and interfaces
Communication protocols
ROS 2 TopicsDDS (Data Distribution Service)Shared Memory (POSIX / mmap)
Hardware interfaces
Ethernet 1000BASE-T (Gigabit Ethernet)USB 3.0 / 3.1 Gen 1Ethernet 100BASE-TX (Fast Ethernet)
Latency classes
Soft Real-Time (20–100 ms)Hard Real-Time (5–20 ms)
Deployment types
On RobotEdgeLocal WorkstationContainerized
Supported simulators
Gazebo Harmonic
Gazebo Classic (Gazebo 11)
NVIDIA Isaac Sim
Official Docker images
ros:humble-desktop
Licenses
BSD-3-ClauseBSD 3-Clause Licensev3-Clause
License family: Permissive
ModificationDistributionCommercial useSublicensingPrivate useROS-compatibleOSI approvedFSF Free/LibreRequires attribution
Version history
lio-sam-ros2 (community port)Apr 2023
First stable community port to ROS 2 Humble (maintained by yashvardhansethi/lio-sam-ros2).
LIO-SAM v1.3 (GTSAM 4.1)Nov 2022
GTSAM 4.1 and Ubuntu 22.04 compatibility.
LIO-SAM v1.2 (Livox support)Aug 2021
Livox solid-state LiDAR support (Mid-70, Avia).
LIO-SAM v1.1 (Ouster support)Feb 2021
Ouster OS1 support; added custom point types.
LIO-SAM v1.0Sept 2020
Stable production release; API cleanup, documentation, full Velodyne support.
LIO-SAM v0.1 (initial open-source release)Jul 2020
First public open-source release accompanying the IROS 2020 paper.