Comau NVIDIA Physical AI integration is bringing NVIDIA simulation and accelerated computing technologies into the company’s industrial robotics and automation portfolio.
Comau is integrating NVIDIA technology across its products and design processes, including NVIDIA Jetson edge computing for its next-generation industrial robot controllers and NVIDIA Isaac Sim for robotics simulation, testing and synthetic data generation.
The work also extends to Comau’s MI.RA vision systems and intralogistics applications, where NVIDIA software is being used to train AI models and develop new control strategies.
Comau NVIDIA Physical AI Integration Expands Across Robotics
The next generation of Comau industrial robot controllers will combine with NVIDIA technology to provide the computing power needed for advanced AI applications.
NVIDIA Jetson edge compute will form part of the controller architecture, supporting AI-driven workloads across Comau’s robotic applications.
Comau says the architecture is being developed for smarter, more adaptive and autonomous robotic solutions across different applications and customer requirements.
Comau Robots Move Into NVIDIA Isaac Sim
Comau is also integrating its industrial, collaborative and mobile robot portfolio into NVIDIA Isaac Sim.
Built on NVIDIA Omniverse libraries, Isaac Sim is an open-source framework for robotics simulation, testing and synthetic data generation.
Comau is contributing SimReady OpenUSD robot assets to the SimReady Central Library on Hugging Face. Developers can use the library to find and reuse validated assets when building and testing robotic applications.
This reduces the preparation time needed to create and test applications in simulation.
NVIDIA AI Supports Comau MI.RA Vision Systems
NVIDIA’s simulation and AI libraries are also being used in Comau’s work on vision-based applications and intralogistics control strategies.
This includes training AI models for the company’s MI.RA vision system family and using reinforcement learning for advanced palletising and depalletising tasks.
Comau is combining NVIDIA Isaac Sim’s high-fidelity physics with Discrete Event Simulation for logistics workflows and NVIDIA Isaac Lab’s learning capabilities.
The company uses these technologies to create virtual models where AI-driven control strategies can be trained before reaching the factory floor.
Training Robot Applications Before Deployment
For Comau, simulation provides an environment where robotic applications can be developed and validated before physical deployment.
The company says photorealistic, physics-based simulated environments can help accelerate the deployment of these capabilities in industrial applications.
Andrew Lloyd, Chief Engineering Officer of Comau, said:
“The combination of NVIDIA Physical AI simulation libraries and accelerated computing with Comau’s platforms and automation expertise will help us develop intelligent solutions faster and make advanced automation easier for our customers globally to deploy across different applications and industrial sectors.”
The same approach runs through Comau’s use of Isaac Sim and Isaac Lab, where robotic applications can be simulated, trained and validated ahead of deployment.
Paolo Guglielmini, vice president EMEA at NVIDIA, said:
“Physical AI is bringing new levels of intelligence and adaptability to industrial robotics.”
He added:
“By combining its robotics expertise with NVIDIA Isaac Sim and Isaac Lab, Comau can simulate, train and validate robotic applications before deployment, helping manufacturers worldwide accelerate the adoption of AI-powered automation.”
MTN Analysis: Comau Connects Physical AI With Industrial Robotics
There are several parts to the Comau and NVIDIA integration, but they all connect around the same idea: developing more of a robotic application virtually before putting it into operation.
Isaac Sim and Isaac Lab provide the simulation and training environment. NVIDIA Jetson brings accelerated computing into Comau’s next-generation robot controllers. Comau is then applying NVIDIA technology to existing areas such as MI.RA vision and intralogistics.
That gives the announcement a practical industrial focus. Reinforcement learning for palletising and depalletising is one example given by Comau, alongside AI model training for its vision systems.
Much will now depend on how these technologies are used across Comau’s applications and customer projects. What the announcement already shows is that Physical AI is becoming part of the company’s wider robotics development process, from simulation and training through to robot control.
Further Reading
For more on Physical AI, AI and robotics in manufacturing:
