NVIDIA has introduced a new safety platform designed to help developers build and deploy autonomous robots that can operate alongside people in factories, warehouses, and logistics centers.

Called NVIDIA Halos for Robotics, the system combines computing hardware, software, sensors, and safety validation tools into a single framework. The company says it is the industry’s first full-stack safety system built specifically for robotics and physical AI applications.

The launch comes as humanoid robots and other autonomous machines are moving beyond controlled environments and into workplaces where they must safely interact with workers, vehicles, and equipment.

Agility Robotics has become the first company to adopt parts of the system. The humanoid robot maker plans to integrate NVIDIA technologies into Digit, its warehouse and manufacturing robot already being deployed by customers including Amazon, GXO, Schaeffler, and Toyota Motor Manufacturing Canada.

Building safer machines

NVIDIA said Halos for Robotics extends technologies originally developed for autonomous vehicles into robotics applications. The platform includes NVIDIA IGX Thor for industrial computing, Holoscan Sensor Bridge for sensor connectivity, and Halos Core software that supports safety-related operating functions.

Together, these components are designed to monitor robot behavior, process sensor data, and support safe operation in real-world environments. The company said the framework is backed by more than 18,600 engineering years of autonomous vehicle safety development.

“Physical AI is transforming how factories, warehouses and logistics operations work, and robotics teams need a unified safety architecture to scale autonomous systems into these environments,” said Deepu Talla, vice president of robotics and edge AI at NVIDIA.

One key component is the NVIDIA Halos AI Systems Inspection Lab, which the company says is the first ANSI National Accreditation Board-accredited program focused on both functional safety and intelligent robotic systems. The lab is designed to help companies prepare products for certification by organizations such as TÜV Rheinland, TÜV SÜD, UL Solutions, exida, SGS, and CertX.

According to NVIDIA, the inspection program gives developers a standardized process to evaluate safety, cybersecurity, and software performance before commercial deployment.

Certification meets robotics

Industry groups view certification as becoming increasingly important as autonomous machines take on more responsibilities in industrial settings. “As AI-enabled robotics moves into industrial environments, the industry needs standardized, internationally recognized frameworks to assess safety across increasingly complex systems,” said Laurie E. Locascio, president and CEO of ANSI.

Agility Robotics said safety remains one of the biggest requirements for deploying humanoids at scale. The company plans to integrate NVIDIA IGX Thor and Halos Core into its existing human detection and safety systems for Digit. It will also participate in the NVIDIA inspection program to evaluate software, computing systems, and cybersecurity protections against standards including IEC 61508, ISO 13849, and ISO/IEC TR 5469.

“For humanoids to deliver value at scale, safety has to be built into the robot and validated across the entire system,” said Peggy Johnson, CEO of Agility. NVIDIA said more than 40 companies are already participating in the broader Halos ecosystem, including software vendors, chipmakers, certification agencies, robotics companies, and industrial technology providers.

Recommended Articles