Agility Robotics
Agility Robotics said that its new humanoid robot, Digit 5, can work in close proximity to humans.
Get news, papers, media and research delivered. Sign up for our free newsletters.
Stay up-to-date with news and resources you need to do your job. Research industry trends, compare companies and get weekly market intelligence with Robotics 24/7.
Agility Robotics
Agility Robotics said that its new humanoid robot, Digit 5, can work in close proximity to humans.
Humanoid robotics and physical AI company Agility Robotics has unveiled Digit 5, the next generation of its general-purpose humanoid robot.
The company said that Digit 5 is its first humanoid robot engineered for cooperatively safe work at scale, allowing it to work closely to people without the physical safety barriers required by traditional automation.
Agility Robotics said that safety has been one of the biggest obstacles to scaling humanoid robots in commercial settings. The company said that Digit 5's new safety architecture is designed to reduce dependence on the protective barriers typically used in traditional robotic automation, allowing it to work in close proximity to people.
"Digit 5 is removing a major barrier to scaling humanoid robots in industrial environments," said Peggy Johnson, CEO of Agility Robotics. "We built it to the exact requirements our customers gave us after three years of Digit 4 working on their production floors, and the market has responded with more than $300 million in multi-year orders and a growing pipeline of customers across manufacturing, warehousing, and logistics. That's value that compounds as Digit's capabilities expand, backed by real demand."
The company said that, by building on its milestone of becoming the first humanoid to pass an independent field evaluation on a customer production line for industrial safety standards administered by the U.S. Occupational Safety and Health Administration (OSHA), Digit 5 adds:
Agility said that it is expanding Digit 5’s safety architecture by partnering with industry leaders and is the first launch partner for NVIDIA's Halos for Robotics platform, pairing Agility's systems with NVIDIA IGX Thor and Halos Core infrastructure. Digit 5 will also use NVIDIA’s Halos AI Systems Inspection Lab to accelerate its path to safety certification.
"Safely operating around people and assets is what moves humanoid robots from pilots to industrial deployments at scale,” said Deepu Talla, vice president of robotics and edge AI at NVIDIA. “Agility's Digit 5 is building on more than 65,000 hours of real-world operation and pairing its new safety architecture developed on top of NVIDIA IGX Thor and Halos safety framework for Robotics to help humanoids collaborate safely in factories and warehouses".
Agility added that it is also helping shape the standards that will govern safe robotics, as a project leader and active contributor to the American National Standards Institute’s ANSI/A3 TR R15.108, the technical report under development for dynamically stable industrial mobile robots - including humanoids - in the U.S. and Canada, and to the International Organization for Standardization’s ISO 25785-1, the first international safety standard for the humanoid category.
The company said that Digit 5 was developed in response to three years of customer feedback and brings the following substantial hardware upgrades:
"Agility's Digit 5 represents a genuine breakthrough in operational capacity for humanoid robots,” said Abdil Tunca, senior principal analyst, Gartner Supply Chain. “While the ability to work safely in close proximity to humans is a significant industry milestone, warehouse and logistics leaders should bear in mind additional factors when formulating their robotics investment plans.”
Agility Robotics said that together, these upgrades enable a single Digit 5 robot to take on work that used to require a specialized technology at every stage and remove constraints on scale. Since its first commercial deployments, the company said that Digit 4 has largely focused on automating tote-based material handling.
The company said that Digit 5 will utilize its proprietary approach to physical AI-based capability training to add more manipulation skills and expand to cover a facility's full workflow: from depalletizing goods as they arrive, then machine tending, kitting and sequencing, and quality inspection as items move through the facility, and finally palletizing them for shipment as they leave.
With Agility’s robot management platform, the company said that Digit coordinates each handoff with a facility’s existing AMRs, conveyors and warehouse systems, so material keeps moving between stations. Agility said that it will continue to build out the physical AI stack that lets engineers develop new, reliable behaviors for Digit 5 across each new workflow.
The company said that Digit has the longest tenure among humanoid robots actively working in industrial facilities, with nearly three years of continuous commercial deployment. Digit 4 has logged more than 65,000 hours of operational time and work across numerous customer sites in North America, including GXO, Schaeffler, Amazon, and Toyota Motor Manufacturing Canada.
At GXO's Flowery Branch facility near Atlanta, Agility said that Digit 4 reached a cumulative 100,000-tote milestone in November 2025, maintaining approximately 98% accuracy while on-task.
The company said that customer commitment is translating into orders. As of May 2026, Agility said that it had more than $300 million in multi-year customer orders for Digit 5, with a sales pipeline of prospective customers across manufacturing, warehousing and logistics, reflecting accelerating demand as customers like Schaeffler move from pilot programs to full-scale deployment.
The company said that Digit 5 remains fully integrated with Agility Arc, Agility's cloud platform for deploying and managing Digit fleets, which is essential as deployments scale. The company said that Arc gives operational visibility into fleet KPIs such as - uptime, throughput and Mean Time Between Incidents, - and connects with existing Warehouse Management, Warehouse Execution and Manufacturing Execution Systems.
Agility said that it protects Digit’s platform with end-to-end encryption, strict access controls and localized data processing.
The company said that Digit utilizes onboard cameras, depth sensors and inertial measurement units to navigate and operate safely, processing sensory data locally and transmitting essential system health and diagnostic information to Agility Arc. Transmitted data is encrypted, segregated by customer and secured using mTLS and TLS 1.2+ rooted to a private certificate authority, while on-robot storage is encrypted for data at rest.
Digit is assembled at RoboFab, Agility's 70,000-square-foot facility in Salem, Oregon. The company said that RoboFab represents the first factory purpose-built to assemble humanoid robots at scale.
At full capacity, Agility said that RoboFab is designed to produce up to 10,000 Digit robots per year and employ more than 500 people.
In addition to the U.S. and Canada, Agility said that it plans to make Digit available for commercial deployment outside North America for the first time, starting with the European Union and United Kingdom. The company said that Digit 5 is expected to carry a CE mark and additional regulatory marks to enable market access to the EU, Great Britain, and Northern Ireland.
Agility said that early access to Digit 5 is expected to begin in the first half of 2027, with general availability for manufacturing, warehouse and distribution operators expected by the end of 2027.
Artificial Intelligence Deep Learning Machine Vision Machine Learning Autonomy Mobile Robots Industrial Automation Collaborative Robots Components Controllers Grippers Motion Control Sensors Cameras Lidar Software Cloud and Edge Fleet Management News Press Release Agility Agility Robotics Autonomous Mobile Robots Cybersecurity Deployment Humanoid Machine Tending Mobile Manipulation Physical AI Safety
Enjoyed this article? Add Robotics 24/7 as a preferred source in Google Search.
Edge computing gives AI agents the processing power to turn instructions into…
Daimon-TWM world model debuts for the public
Platform helps robots adapt to complex tasks
Look beyond the headlines for the latest in humanoid robots