Intrinsic, the intelligent robotics software company owned by Google LLC’s parent Alphabet Inc., said today that it’s open-sourcing the core components of its industrial robotics platform.
Announced at ROSCon 2026 in Toronto today, the new offering is called Intrinsic Core, and its release under a permissive Apache 2.0 license is all about democratizing access to intelligent robotics, the company said. Founded in 2021, Intrinsic was incorporated into Google’s operations in February to accelerate the development of physical AI to push the envelope of artificial intelligence beyond digital applications and into real-world industrial environments.
Physical AI describes AI systems that use sensors, actuators, and control systems to perceive, reason, act and learn in real-world environments. It differs from pure software because it bridges the gap between bits and atoms – allowing autonomous machines such as robots, self-driving cars, drones and smart infrastructure to take action.
Though physical AI is interesting, its progress has long been stalled by the complexity of developing the underlying software and training the AI models that sit at the heart of intelligent robots. Google and Intrinsic both believe that progress can be accelerated with the availability of a reusable, foundational software layer that provides the basic infrastructure for physical AI, so that developers don’t have to rebuild everything from scratch for each new robot they create.
This is where Intrinsic Core should come in handy. It’s a preconfigured, Robot Operating System-compatible software environment designed to run on local hardware. It provides a number of reusable building blocks that developers can integrate with their physical robotics systems, providing them with the capabilities they need to operate in industrial environments.
These building blocks include Intrinsic Control, which is a hardware-agnostic real-time control framework capable of dynamically adapting a robot’s trajectory mid-movement, based on the feedback provided by its sensors. This will make it easier for developers to use various kinds of hardware, such as arms and grippers, without rewriting the underlying software and drivers for them each time, Intrinsic said.
Other components include Pose Estimation, a capability based on Nvidia Corp.’s FoundationPose that enables robots to dynamically detect and handle parts, removing the need for rigid, expensive physical fixtures. There’s also a motion planning capability that automates collision-avoidance path generation, eliminating the need for developers to program robots manually, joint by joint in a position-controlled way. And there’s a grasp planning function that allows various types of robotic grippers to automatically and dynamically adapt to the location and orientation of the objects they’re trying to grasp.
Intrinsic Core also provides simulation and calibration services that make it possible to simulate, visualize and troubleshoot robotics and calibrate their vision systems through a single interface. Finally, there are Intrinsic-ROS drivers, which make it easier for developers to integrate sensors with third-party grippers, 3D cameras and other hardware components.
To showcase how Intrinsic Core can aid robotics developers, the company has also released the Open Machine Tending Solution, which is a kind of open reference design for AI-powered CNC machine tending tasks. It supports modular customization for different hardware setups from major robotics manufacturers, including Universal Robots A/S and FANUC Corp.
Intrinsic said the Open Machine Tending Solution is designed to help accelerate automation in the machine building industry. The company said the U.S. and Europe are home to tens of thousands of shops that fabricate intricate parts for machines in a wide range of industries, yet only 8% of those shops use any form of automation at all due to the high costs and technical barriers of adoption. By providing a customizable starting point, Intrinsic believes, its reference design will pave the way for much smaller fabricators to automate lower-value tasks and accelerate automation.
More broadly, Intrinsic said it hopes to foster the growth of a much broader robotics developer ecosystem based on shared, open-source tools and accelerate the adoption of physical AI in various industries.
