Intrinsic
Canvas Category Software : Operational Technology : Industrial Robot
We’re making industrial robotics accessible and usable for millions more businesses, entrepreneurs and developers.
Assembly Line
EuroBLECH: TRUMPF achieves breakthrough in automated sorting
New solutions SortMaster Station and SortMaster Vision from TRUMPF make it possible for the first time to sort fully automatically without any programming // To achieve this, TRUMPF uses an innovative process and artificial intelligence in partnership with Intrinsic, a leading AI and robotics software company // The solution can be used flexibly for all components, especially for thick sheets and complex geometries.
At EuroBLECH 2024, TRUMPF is presenting a completely new solution for the automated sorting of 2D laser-cut parts. With the SortMaster Station and the SortMaster Vision, customers will be able to sort parts particularly reliably and without any programming effort. The key to this is that the SortMaster Station removes the parts from the sheet metal in the first step, regardless of their geometry. The machine operator then sorts the separated parts manually or has them removed and palletized fully automatically by the SortMaster Vision. Meanwhile, the laser cutting machine is already processing the next sheet. “The automated sorting of parts is one of the biggest challenges in the sheet metal world. Conventional methods are particularly suitable for simple components with medium sheet thicknesses of up to 12 millimeters. For many companies, their common automation solutions are too inflexible and time-consuming to program, so they have their parts sorted by hand. With the SortMaster Station and the SortMaster Vision, TRUMPF enables automated sorting of any sheet metal parts and once again demonstrates its technological leadership,” said TRUMPF CTO for Machine Tools Thomas Schneider. TRUMPF offers its customers the new solution in a 3-meter format for the laser cutting machines of the 3000 and 5000 series.
Unlocking new value in industrial automation with AI
Working with the robotics team at NVIDIA, we have successfully tested NVIDIA robotics platform technologies, including NVIDIA Isaac Manipulator foundation models for robot a grasping skill with the Intrinsic platform. This prototype features an industrial application specified by one of our partners and customers, Trumpf Machine Tools. This grasping skill, trained with 100% synthetic data generated by NVIDIA Isaac Sim, can be used to build sophisticated solutions that can perform adaptive and versatile object grasping tasks in sim and real. Instead of hard-coding specific grippers to grasp specific objects in a certain way, efficient code for a particular gripper and object is auto-generated to complete the task using the foundation model and synthetic training data.
Together with Google DeepMind, we’ve demonstrated some novel and high value methods for robotic programming and orchestration — many of which have practical applications today:
- Multi-robot motion planning with machine learning
- Learning from demonstration, applied to two-handed dexterous manipulation
- Foundation model for perception by enabling a robotic system to understand the next task and the physical objects involved requires a real-time, accurate, and semantic understanding of the environment.
Building openness into industrial robotics
Since we began working together, the Open Robotics team at Intrinsic has first and foremost been continuing its efforts as core contributors to improve ROS, Gazebo, and Open-RMF as tools and resources that serve as backbones for robotics projects the world over. In the past months, we’ve celebrated Iron Irwini, the latest ROS release, and Harmonic, the latest Gazebo release. Today at ROSCon, the Open Robotics team at Intrinsic introduced the progress we’re making on the development of alternative middleware protocols as well as our first integrations between ROS and the Intrinsic platform.
In addition to core contributions to ROS, the Open Robotics team at Intrinsic is also working on building the first integrations between ROS and the Intrinsic platform. When we announced Intrinsic Flowstate earlier this year as our first web-based developer tool to make building robotic solutions easier and more accessible, we indicated our intention to build strong bridges between ROS and our Intrinsic platforms. With Flowstate currently in private beta, we’re gradually increasing the number of testers and exploring prototypes of potential integrations between our platforms.
🧠🦾 Intrinsic and Siemens collaborate to accelerate the integration of AI-based robotics and automation technology
Intrinsic, an Alphabet company, and Siemens have teamed up to explore integrations and interfaces between Intrinsic’s robotics software, which is designed for easy use of AI-based capabilities, and Siemens Digital Industries with their open and interoperable portfolio for automating and operating industrial production.
Currently, the development and runtime environments for AI-based robotics and automation components differ significantly in their development paradigms and make integration cumbersome. For example, deploying advanced robotic capabilities such as pose estimation, robot manipulation or automated path planning are complex processes that typically require teams of domain experts to operationalize. The two companies intend to investigate new methods to seamlessly bridge the gaps between robotics, automation engineering and IT development.
Comau uses Intrinsic Flowstate to automate the assembly of rigid components
Comau unveiled as Intrinsic’s first industrial and innovation partner
Comau, a worldwide leader in delivering advanced industrial automation products and systems, was unveiled as the first industry partner of Intrinsic, which is on a mission to make industrial robotics accessible and usable for millions more businesses, entrepreneurs, and developers. On stage, Pietro Gorlier, Comau’s CEO, demonstrated how the company has recently used Intrinsic’s new Flowstate developer product and underlying platform to create a modular solution to enable the assembly of a plug-in hybrid electric vehicle (PHEV) supermodule – just one of many possibilities for new applications made possible through the platform. As the longest standing innovation partner of Intrinsic, Comau has contributed on all levels – providing their expertise and talent to test and validate the technology
A new chapter for Intrinsic
I’m thrilled to share that Intrinsic and Vicarious are now one team with an ambitious mission to unlock the creative and economic potential of industrial robotics for millions more businesses and developers.
Over the last few years, Vicarious has carved a unique path in the robotics as a service (RaaS) space, serving market-leading customers with turnkey solutions for high-demand tasks like kitting and palletizing, among others. They also built a passionate and multidisciplinary team in the process, including folks from their recently acquired subsidiary, Akasha Imaging — a computational imaging company offering perception capabilities and a proprietary vision system enabling robots to ‘see’ with the help of AI.
Introducing Intrinsic
Intrinsic is working to unlock the creative and economic potential of industrial robotics for millions more businesses, entrepreneurs, and developers. We’re developing software tools designed to make industrial robots (which are used to make everything from solar panels to cars) easier to use, less costly and more flexible, so that more people can use them to make new products, businesses and services.