Google’s Intrinsic Open-Sources Core Robotics Software for Industrial AI
aiinsider ·
Google's Intrinsic has open-sourced its core robotics software platform, named Intrinsic Core, to accelerate the development of AI-enabled industrial robot applications. Released under an Apache 2.0 license on GitHub, the software provides developers with ROS-compatible tools for building systems from prototype to production stages. Key features include real-time control, pose estimation using Nvidia FoundationPose, automatic motion and grasp planning, and Gazebo-based simulation services. The release aims to reduce infrastructure burdens by offering hardware-independent control and preconfigured drivers for various robots and sensors. Additionally, Intrinsic introduced the Open Machine Tending Solution (OMTS), an open reference design for CNC machine tending that supports hardware from manufacturers like Fanuc and Universal Robots. This solution allows developers to customize automation tasks without starting from scratch, serving as a practical starting point for systems integrators. Applications built with Intrinsic Core are designed to integrate seamlessly with Intrinsic Flowstate and other cloud services without requiring code rewrites. This move highlights Google's strategy to support broader adoption of physical AI in manufacturing environments.
aiinsider