New NVIDIA Halos Tech Secures Agility Humanoid Robots

The era of physical AI is rapidly materialising on the factory floor but scaling these autonomous systems requires a unified approach to safety.
Addressing this critical need, NVIDIA has announced NVIDIA Halos for Robotics, which it calls the industry’s first full-stack, comprehensive safety system for robotics and physical AI that unifies AI compute and safety.
Originally developed as an autonomous vehicle safety system that brings together vehicle architecture, AI models, chips, software, tools and services, NVIDIA is extending the technology to humanoid robotics.
Deepu Talla, Vice President of Robotics and Edge AI at NVIDIA, explains: “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.”
With NVIDIA Halos for Robotics, developers and system builders can harness a proven autonomous vehicle safety foundation to develop safer robots faster. Deepu says this allows companies to bring robots into industrial operations alongside workers with greater confidence.
The system relies on a multi-layered configuration to achieve industrial-grade reliability. Halos for Robotics is built on three key layers: NVIDIA IGX Thor and Holoscan Sensor Bridge for AI compute and sensor connectivity, the Halos OS software stack for safety functions and applications and the NVIDIA Halos AI Systems Inspection Lab for third-party certification.
Humanoid robotics safety deployed at Agility
Humanoid robotics and physical AI company Agility is the first to use NVIDIA Halos for Robotics to build safety into its humanoids working in factories, warehouses and logistics operations.
Agility has built elements of NVIDIA Halos for Robotics into its humanoids, helping serve its customers like Amazon, GXO, Schaeffler and Toyota Motor Manufacturing Canada.
The company says its humanoid, Digit, is the first humanoid robot in production deployment. Digit runs on Arc, which is a multi-cloud management platform by Microsoft.
Peggy Johnson, CEO of Agility, emphasises that safety must be a core component of deployment rather than an afterthought: “For humanoids to deliver value at scale, safety has to be built into the robot and validated across the entire system.”
Partnering with NVIDIA to implement and optimise the Halos for Robotics system extends Agility’s leadership in responsible automation, which is a non-negotiable requirement for bringing humanoids safely into industrial workflows.
Peggy adds: “This collaboration unlocks true human-robot teamwork, driving the long-term returns that will power next-generation manufacturing and logistics operations.”
Industrial automation growth demands new safety standards
Working with its partners, Agility is bringing advanced automation to facility floors at a time of unprecedented growth. Increasingly, robots and humanoid robots are being deployed on the factory floor.
The International Federation of Robotics World Robotics 2025 statistics on industrial robots showed 542,000 robots installed in 2024. This figure represents more than double the number of installations recorded 10 years ago.
As robots and humanoid robots continue to expand in the manufacturing sector, more questions are asked about the safety of the machines. These concerns are rising especially as there have been well-documented issues with deployments of autonomous vehicles.
In a June 2026 interview told to McKinsey, Daniela Rus, Director of the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory, highlighted the inherent unpredictability of these systems. Daniela says: “AI models that control robots are typically not closed-form solutions.”
There is always a chance that the systems will make a mistake. She concludes: “How will the robot respond if the AI brain tells it to do something wrong?”
For Digit, NVIDIA IGX Thor delivers industrial-grade AI compute with built-in safety capabilities, while Halos Core supports the software layer for safety-related operating functions.
By combining this architecture with cloud-based management, the partners aim to resolve these safety questions on the facility floor.

