Sorry, you need to enable JavaScript to visit this website.

Robotics & Autonomous Systems


The Robot Operating System (ROS) is a set of software libraries and tools that help you build robot applications. From drivers to state-of-the-art algorithms, and with powerful developer tools, ROS has what you need for your next robotics project. And it's all open source.

Since ROS was started in 2007, a lot has changed in the robotics and ROS community. The goal of the ROS 2 project is to adapt to these changes, leveraging what is great about ROS 1 and improving what isn’t. There’s a full article on the motivation of ROS 2 here. Intel® Robotics open source project applies Intel® hardware and software technologies to ROS and ROS2, bringing artificial intelligence and more possibilities to robotics applications.


Robot Development Kit

An open source project which enables developers to easily and efficiently create, customize, optimize, and deploy a robot software stack to an Autonomous Mobile Robot (AMR) platform based on the Robot Operating System 2 (ROS2) framework. In the near future this will be extended to add manipulation of robot arms. Check out our code at Robot DevKit github and tutorial at Robot DevKit Tutorial.



There are multiple packages optimized with Intel technologies in perception domain. From 3D realsense camera, OpenVINO inference engine with CPU/GPU/VPU/FPGA, to object tracking and 3D localization, perception packages improved the computer vision performance through hetegenerous hardware platforms.

  • RealSense (ROS, ROS2) ROS/ROS2 packages for Intel® RealSense™ D400 series cameras.

  • Movidius NCS (ROS, ROS2) ROS/ROS2 package for object detection with Intel® Movidius™ Neural Computing Stick (NCS).

  • OpenVINO (ROS, ROS2) ROS/ROS2 package for Intel® Visual Inference and Neural Network Optimization Toolkit to develop multi-platform computer vision solutions.

  • Object Analytics (ROS, ROS2) ROS/ROS2 package for object detection, tracking and 2D/3D localization.



Robot 2D navigation (ROS2) with collision avoidance based on a map. This is a foundamental capability for an automonous mobile robot (AMR) to find an optimal path to the destination.



Robot arm need a way to identify the objects to be manipulated, and plan a best path to approach and grasp the object. MoveIt is a popular open source projects for robot manipulation, we added visual manipulation and deep learning based grasp planner for it.

  • Grasp library (ROS2) ROS2 package for grasp position analysis, compatible with MoveIt grasp interfaces.

  • Hand-eye calibration (Coming soon)

  • MoveIt sample applications (Coming soon)


Get Involved

You can find all the github projects at Intel ROS Projects and Intel ROS2 Projects, fetch the source code, report issues and submit requests through individual github projects to get more support and communicate with developers directly. Your code contributions are highly welcome, join us as a developer!