NVIDIA introduces NVIDIA Halos for Robotics full-stack safety system

NVIDIA introduced NVIDIA Halos for Robotics as a comprehensive safety system for robotics and physical AI that unifies AI compute and safety. The company presented the offering as a single safety architecture intended to support robots that sense, decide, and act in real-world environments.

NVIDIA said next-generation autonomous robots will operate in dynamic environments alongside humans using AI foundation models, accelerated compute, and distributed sensors. The company added that scaling these systems requires a full-stack safety architecture that connects AI compute, system software, sensor data, safety applications, and inspection for robotic systems.

NVIDIA Halos for Robotics spans multiple layers. NVIDIA IGX Thor and NVIDIA Holoscan Sensor Bridge provide industrial-grade AI compute and sensor connectivity for real-time robotics and safety workloads. NVIDIA Halos OS provides a software stack for robotics safety, including Halos Core and safety applications built with the NVIDIA Halos Outside-In Safety Blueprint. The NVIDIA Halos AI Systems Inspection Lab is described as the first ANSI National Accreditation Board (ANAB)-accredited program for functional and AI safety for physical AI, supporting partner preparation for third-party certification by TÜV Rheinland, UL Solutions, TÜV SÜD, exida, SGS, and CertX.

Agility was named as the first company to incorporate elements of Halos for Robotics into its proprietary safety system for its humanoid robot Digit. NVIDIA said Agility integrated NVIDIA IGX Thor and Halos Core into Digit’s safe human detection system and planned to use the Halos AI Systems Inspection Lab to assess Digit’s safety-related software, AI components, and cybersecurity protections against IEC 61508, ISO 13849, and ISO/IEC TR 5469 prior to final third-party certification. “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. “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. “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. “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. Forward-looking statements in the release included expectations and projections that were described as statements other than historical facts.

Provided by Globe Newswire on behalf of Nvidia. Click to read original content.