
Nvidia Expands Halos Safety System From Robotaxis to Humanoid Robots
Nvidia is extending its Halos safety platform beyond self-driving cars to robotics, with hardware and software tools designed to keep autonomous mobile robots, humanoids and surgical robots safe around people.
Nvidia Expands Halos Safety System to Robotics
Nvidia is expanding its Halos safety system, launched in 2025 for self-driving cars, into physical AI. The company announced Nvidia Halos for Robotics in June 2026, aiming to enable safe deployments of autonomous mobile robots in warehouses, humanoid robots in factories and even surgical robots.
"Now the AI models are getting capable, the robot hardware is getting capable, and a thing we thought is going to be the next bottleneck is safety," said Amit Goel, head of robotics ecosystem and edge computing at Nvidia.
The expansion comes as CEO Jensen Huang described physical AI as already driving nearly $10 billion in annual revenue on the All-In Podcast in March 2026. Huang began highlighting physical AI as Nvidia's second-most important growth category in 2025. Nvidia has also invested in humanoid robotics startups Agility Robotics and Figure AI, and partnered with Chinese humanoid robotics company Unitree on an open humanoid robot reference design for researchers.
Hardware, Software and Simulation
The full-stack system starts with hardware such as the Nvidia IGX Thor computing module, which includes an independent processor dedicated to safety-related workloads. "In the context of physical AI, you need to have your functional system and your safety system all running on the same silicon," Goel said.
The Halos operating system constantly monitors every hardware block and software library to swiftly spot failures, and isolates safety-critical workloads to avoid interference. The package also includes the Nvidia Holoscan Sensor Bridge, which connects sensor data with safety processing in a way that can identify corrupted data and can be embedded in components such as microcontrollers or Field Programmable Gate Arrays. Rounding out the offering are simulation tools for testing robots in virtual environments and an inspection lab program that gives robotics companies quick feedback on safety artifacts.
Early Adopters Put Halos to Work
US startup Agility Robotics was first to incorporate Nvidia Halos into its latest Digit 5 humanoid robot, designed to work safely near people without isolated workstations or physical barriers. The system helped Agility bring all relevant safety sensors and hardware inside the robot, whereas previous Digit operations relied on external sensors around the robot's work cell. "Now the robot is literally unchained, the safety goes with the robot wherever it goes," Goel said.
Boston Dynamics has also been an early partner in the Halos safety accreditation program, focusing on its Spot robot dogs, wheeled Stretch robots and Atlas humanoid robots, which could start deploying in the automotive factories of parent company Hyundai by 2028. Other companies working to incorporate Halos include German company KION Group, which deploys self-driving forklifts and other autonomous mobile robots, and South Korean company LG, which is developing a humanoid robot based on Nvidia's Isaac GROOT foundation model.
Whether humanoid robots can become autonomous, general-purpose workers remains to be seen. But the latest push by the United States, China and Europe to deploy more robots extends well beyond humanoids. "Earlier robots were mostly confined in one station doing one thing," Goel said. "But in the new age of robotics with a generalized body as well as generalized skills, it is essential that the robots can do multiple tasks in multiple environments, and the only way you can do that in production is if you improve safety."
Sources: Arstechnica
SiTech — AI-powered web development
We build fast, modern websites and bring AI into real business workflows. Have a project or a question? We'd love to help.