NVIDIA releases Halos, a full-stack safety system for robotics

system for robotics">

Agility Robotics is the first to use NVIDIA Halos for Robotics to build safety into its humanoids working in factories, warehouses, and logistics operations for customers including Amazon, GXO, Schaeffler, and Toyota Motor Manufacturing Canada. | Source: NVIDIA

NVIDIA today launched NVIDIA Halos for Robotics. This is a full-stack, comprehensive safety system for robotics and physical AI that unifies AI compute and safety.

NVIDIA said autonomous robots will need AI foundation models, accelerated compute, and distributed sensors to operate in dynamic environments alongside humans. Scaling these systems requires a full-stack safety architecture.

NVIDIA said Halos enables companies to rely on a standardized, unified safety architecture that connects AI compute, system software, sensor data, safety applications, and inspection for robotic systems.

“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, the vice president of robotics and edge AI at NVIDIA. “With NVIDIA Halos for Robotics, developers and system builders can harness NVIDIA’s proven autonomous vehicle safety foundation to develop safer robots faster and bring them into industrial operations alongside workers with greater confidence.”

NVIDIA Halos Core for NVIDIA IGX is available in early access for registered developers in Linux and Linux plus QNX configurations. The open source NVIDIA Halos Outside-In Safety Blueprint , part of the Halos Applications layer of Halos OS, is now available in early access on GitHub.

To create Halos, NVIDIA drew on over 18,600 engineering years of autonomous vehicle safety development. Halos for Robotics provides developers with a common safety architecture for building, validating, and deploying physical AI systems.

The system spans the key layers needed for robot safety. NVIDIA IGX Thor and NVIDIA Holoscan Sensor Bridge provide industrial-grade AI compute, built-in safety, and sensor connectivity for real-time robotics and safety workloads.

NVIDIA Halos OS provides the software stack for robotics safety. This includes Halos Core to support safety-related operating functions and safety applications built with the NVIDIA Halos Outside-In Safety Blueprint. NVIDIA said this program extends robot perception using external cameras and AI agents to dynamically control robot behavior in industrial settings.

The NVIDIA Halos AI Systems Inspection Lab is an ANSI National Accreditation Board (ANAB)-accredited program for physical AI functional and AI safety. It helps partners prepare Halos integrations for third-party certification by leading certification bodies. These include TÜV Rheinland, UL Solutions, TÜV SÜD, exida, SGS, and CertX.