Diligent Robotics today said it has started rolling out Moxi 2.0 to health system customers across the U.S. The company said its five years of operation in over 25 hospitals shaped the next-generation platform.
With the new robot, Diligent is also launching its learning flywheel. The Austin, Texas-based company claimed that the proprietary world model learns from the experience of its robot fleet and improves continually with every hospital deployment.
“Today, we’re deploying our most sophisticated physical AI platform yet,” stated Andrea Thomaz, founder and CEO of Diligent Robotics. “Hospital hallways are some of the most dynamic environments a robot can operate in, full of fast-moving people, doors, and carts, all in tight spaces. To operate safely in that world, our first-generation platform often had to move conservatively. Moxi 2.0 is built with the compute, sensors and models to reason about that complexity in real time, so Moxi can move with more confidence without compromising safety.”
Moxi 2.0 is now rolling out to health systems including Endeavor Health Edward Hospital, Providence Saint John’s Health Center, and Children’s Hospital Los Angeles. It also has deployments expanding across the U.S.
Diligent is actively taking orders from health systems ready to bring the platform to their hospitals. The company first unveiled Moxi 2.0 in October 2025.
This is Diligent’s first major announcement since it was acquired by Serve Robotics, a sidewalk delivery robot developer, in January 2026 for $29 million. As part of Serve Robotics, Diligent said it benefits from shared investment in physical AI research. This has accelerated the pace of innovation across its hospital deployments.
Founded in 2017, Diligent Robotics has created the Moxi mobile manipulator to improve healthcare workflow efficiency. The company has deployed the robot in more than 25 hospitals across the U.S. These robots help nurses with routine tasks to free them up for patient care and prevent burnout.
Moxi 2.0 offers longer operating hours, faster deliveries #
Diligent Robotics said that Moxi 2.0 offers faster, more confident deliveries and longer robot operating hours. The company developed the platform using NVIDIA Isaac Sim open simulation framework and aspects of the NVIDIA Cosmos open world models such as the 3D lidar tokenizer.
Moxi 2.0 includes upgraded NVIDIA-powered A2000 compute. This compute perceives and interprets its surroundings 10 to 15 times faster than the previous generation. This enables quicker responses in dynamic hospital environments like crowded hallways, opening elevator doors and shifting foot traffic, said Diligent.
With Moxi 2.0, the company prioritized modularity. It created specialized packaging that facilitates easy integration of next-generation compute systems as emerging technologies become available. In addition, Diligent said its learning flywheel turns real-world deployment into smarter software updates.
Designed specifically for hospital workflows, Moxi operates within existing infrastructure from Day 1, asserted Diligent. It doesn’t require facility modifications, specialized automation systems, or lengthy IT overhauls.
What are the biggest upgrades with Moxi 2.0? #
Key upgrades in the latest Moxi 2.0 platform include:
10x onboard compute, 10 to 15x faster perception: Upgraded processing enables faster real-time decision-making and more confident navigation through dynamic hospital environments.Robotic World Model: A new physical AI architecture purpose-built for the complexity of hospital environments, designed to strengthen navigation, task completion, and adaptation over time as the learning flywheel feeds new fleet experience back into the world model.Up to 18 hours of runtime per day: With an operating time of up to 9 hours at a time and 30% faster charging, Diligent said Moxi is ready for long shifts.Improved autonomy and recovery: Enhanced handling of edge cases means Moxi can resolve more situations independently, keeping deliveries moving.Upgraded cameras, Moxi 2.0 adds an expanded sensor suite and redesigned storage drawers.sensors, and storage:Redesigned handles and ergonomics: These changes are informed by direct feedback from nurses and pharmacy teams, making it easier for care teams to interact with Moxi when they need to.
“Moxi has become an integral team member at Children’s Hospital Los Angeles,” said Omkar Kulkarni, Chief Innovation and Transformation Officer at Children’s Hospital Los Angeles. “Since Moxi joined our team, it has completed more than 40,000 deliveries, representing over 16,000 hours of work that our staff didn’t have to spend transporting supplies and medications across the hospital.”
“We expanded our Moxi fleet from two to three robots over time, and utilization continues to grow, increasing more than 10% in the second quarter alone,” Kulkarni added. “Our nursing leaders and pharmacy team appreciate that we’re investing in technology that allows team members to work at the top of their skill set.”
Will Moxie 2.0 keep using the Fetch Robotics base? #
Back in December 2025, we learned that Zebra Technologies is winding down its autonomous mobile robot (AMR) division. The group was built around Zebra’s $290 million acquisition of AMR maker Fetch Robotics in 2021.
A few months later, in April, Skild AI acquired the robotics division of Zebra Technologies. All of the uncertainty has left Fetch customers, including Diligent Robotics, in limbo. Diligent use the Fetch mobile robot as the base for its first Moxie robot.
Now, the company told The Robot Report, it designed Moxie 2.0 with modularity in mind. This way, the company can continue to use the Fetch base or transition to another at some point in the future.
Diligent focuses on feeding its AI ‘flywheel’ #
Diligent Robotics said it designed Moxi 2.0 to speed its learning “flywheel.” With upgraded sensors and enhanced edge compute, Moxi 2.0 now captures richer signals from the full complexity of working hospitals.
As that experience flows into Diligent’s cloud training infrastructure, each iteration of the Robotic World Model sharpens Moxi’s understanding of hospital environments, edge-case recovery, and task execution. It creates a compounding loop of better data, stronger models, and more capable robots, said the company.
“We’ve spent years in the field learning what hospitals actually need,” said Thomaz. “This is just the beginning of what a true learning flywheel makes possible.”
Diligent built the cloud infrastructure powering this flywheel in collaboration with Amazon Web Services (AWS). The company trained Moxi’s World Model on Amazon SageMaker HyperPod enabling continuous improvement from deployment data at scale.
T-Mobile for Business has collaborated with Diligent to help ensure reliable network access across complex hospital environments. It has also helped Diligent plan for private 5G hospital deployments ahead.
All safety and autonomy behaviors run onboard, so Moxi completes tasks end-to-end even without Wi-Fi, with cellular fallback available when hospital networks have dead zones, explained Diligent.