Unitree G1
Bipedal humanoid robot by Unitree Robotics, designed as a compact research, development, and developer platform.
Applications
- Research
- Home Assistance
Active Open source API available ROS
CATEGORYPerception · SDKs
READINESSTRL 9
ADOPTION SCALEIndustry Standard
LICENSESApache-2.0
FIRST RELEASE2018
Intel RealSenseRealSenseDepth Camera3D VisionSDKPerceptionRGB-DRobotics
Intel RealSense SDK 2.0 (also known as librealsense2) is the official developer kit supporting the RealSense family: depth (D415, D435, D435i, D455, D456), tracking (T265), LiDAR (L515), and new stereo cameras (D421, D456). The SDK handles capture of RGB, depth, infrared, IMU, and tracking streams over USB 3.0 (UVC/HID).
The SDK has three layers: low-level libuvc/V4L2 (Linux) or Media Foundation (Windows) for USB transport, mid-level rs2 implementing rectification, depth-from-stereo, and temporal post-filters; the high level exposes processing blocks (align, colorize, decimation, hole-filling). The bundled Intel RealSense Viewer enables live debugging.
The SDK is open-source under Apache 2.0. It integrates natively with ROS 2 (realsense-ros wrapper), OpenCV, PCL, and AI frameworks (TensorFlow, PyTorch). Used in humanoids (Atlas, Digit, ARMAR-6), AMRs (Husky, MiR), VR/AR devices, and quality-inspection systems.
Type & Roles
Software types
SDK
An SDK (Software Development Kit) is a curated set of libraries, interfaces, tools, sample code, and documentation intended for building applications and integrating with a specific hardware device, platform, or service. In robotics, an SDK typically exposes device control, telemetry, sensor access, configuration, and execution functions, significantly reducing the time-to-first-integration for developers targeting a specific robot or platform.
Driver
A Driver is a software layer responsible for communication with a specific hardware device or component. In robotics, drivers enable support for sensors (LiDARs, cameras, IMUs), actuators, motor controllers, grippers, and other modules at the hardware or low-level OS layer. They abstract device-specific protocols (USB, CAN, UART, EtherCAT) and expose a standardised interface to the middleware or application layer above.
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.
Select an item to see its description.
Main category
SDKsPerception & Vision SoftwareDrivers & Firmware
Roles in robotics ecosystem
PerceptionComputer Vision
Device Integration
Device Integration denotes the role of software responsible for communication, configuration, initialization and handling of specific devices, sensors, controllers or hardware components within a robotic system.
Select an item to see its description.
Software family
Family
Intel RealSense
Maturity & Adoption
9 / 9
Proven in operational conditions
ResearchPrototypeProduction
Adoption scaleIndustry Standard
Maintenance statusMaintained by Single Vendor
First release2018
Last update12 February 2025
Deployments
Boston Dynamics Atlas (perception), Agility Robotics Digit, Universal Robots e-Series demo apps, Clearpath Husky (default RGB-D), thousands of academic projects and startups.
Community
7.7k★ on GitHub, ~150k apt/pip downloads monthly, 600+ contributors, the most popular depth-camera SDK in robotics.
Organizations
Related robotics software
L
librealsense
An open-source, cross-platform library for Intel RealSense cameras. The IntelRealSense/librealsense repository — the core of Intel RealSense SDK 2.0. Linux/Windows/macOS/Android, ARM64/x86-64.
R
realsense-ros
The official Intel ROS 2 wrapper for RealSense cameras. Publishes depth, color, infrared, IMU, and pointcloud2 topics; supports an Action Server for calibration triggers. The IntelRealSense/realsense-ros repo — the most installed camera wrapper in ROS 2.
R2
ROS 2 Humble Hawksbill
LTS release of the ROS 2 framework based on Ubuntu 22.04, supported through May 2027. The most widely deployed release in humanoids, AMRs, and research platforms. Full integration with Nav2, MoveIt 2 and ros2_control.
Supported robot models
Target robotic platforms
Humanoid
Mobile Robot
Robotic Arm
Quadruped
Research Robot
Service Robot
Drone / UAV
Supported hardware
Intel RealSense D435i
sensing · cameras · research · Stereo RGB-D camera
Intel RealSense D455
sensing · cameras · professional
Intel RealSense L515
sensing · cameras · professional
NVIDIA Jetson AGX Orin 64GB
NVIDIA Jetson Orin Nano 8GB
compute · compute_modules · professional
NVIDIA Jetson Orin NX 16GB
compute · compute_modules · industrial
ROS supportCompatibility with ROS / ROS 2 ecosystem
Official Vendor ROS 2 WrapperOficjalny wrapper ROS 2 tworzony i utrzymywany przez producenta sprzętu lub oprogramowania
Official Vendor ROS 1 WrapperOficjalny wrapper ROS 1 tworzony i utrzymywany przez producenta sprzętu
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++CPython
Operating systems
Ubuntu 22.04Ubuntu 20.04DebianJetPack LinuxWindowsmacOS
Minimum hardware requirements
Minimum hardware requirements
CPUDual-core x86-64 1.6 GHz or ARM64 (Jetson, Raspberry Pi 4+)
RAM (GB)2
GPUNot required; CUDA optional for rs-pointcloud GPU post-processing
Disk (GB)1
Requires USB 3.0 for full depth+RGB resolution at 30 fps. USB 2.0 limits to depth-only QVGA.
Packaging & distribution
Package managers
apt / debGitHub Releases / GitHub Actions ArtifactsDocker / Docker Hubpip / PyPISource – CMake / ament_cmake
CPU architectures
x86_64 (AMD64)ARM64 / AArch64NVIDIA Jetson – AArch64 (JetPack)Raspberry Pi – AArch64 (BCM)ARMv7 / ARM32 (armhf)
Installation difficulty
LevelOut of the box
Protocols and interfaces
Communication protocols
USB (Universal Serial Bus)Ethernet / TCP-IP
Hardware interfaces
USB 3.0 / 3.1 Gen 1USB 3.1 Gen 2 / USB 3.2USB 2.0
Latency classes
Soft Real-Time (20–100 ms)
Deployment types
On RobotEdgeLocal WorkstationContainerized
Supported simulators
Gazebo Harmonic
NVIDIA Isaac Sim
Official Docker images
intel/ros2_openvino_toolkit
Licenses
Apache-2.0Apache License 2.0v2.0
License family: Permissive
ModificationDistributionCommercial useSublicensingPrivate useROS-compatibleOSI approvedFSF Free/LibreRequires attributionPatent grant
Version history
2.56Feb 2025
ARM64 native build, Jetson Orin optimizations.
2.55Mar 2024
Improved post-processing filters, D421 support.
2.50Apr 2022
D405 support, IMU calibration tools.
2.34Jun 2020
L515 LiDAR support, T265 tracking integration.
2.0Jan 2018
Rewrite from legacy SDK, unified API for D-series.