Diligent Robotics Unveils Moxi 2.0, Advancing The Largest Fleet of Deployed AI-Powered Mobile Manipulation Robots Operating in Unstructured, Human-Centric Work Environments
Moxi 2.0, powered by NVIDIA AI and accelerated computing, combines redesigned hardware and a new AI foundation model built on three years of real-world deployment data to expand autonomy and scale
Austin, October 28, 2025 — Diligent Robotics, the company behind Moxi, the world’s largest deployed fleet of mobile manipulation robots working side by side with people, today unveiled plans for Moxi 2.0, its next-generation platform built with AI from the ground up. The launch builds on three years of proprietary real-world data, collected from over 1.25 million deliveries in busy hospital environments and representing one of the largest datasets of real-world human-robot interaction.
Representing one of the largest deployed fleets of NVIDIA-powered mobile manipulator robots in healthcare, Moxi currently operates in over 25 hospitals across the U.S. to help nurses and pharmacy staff with routine tasks, such as delivering medications and lab samples. The company is planning its expansion into the senior living sector with its participation in the AgeTech Collaborative™ from AARP accelerator program.
“Interactive environments are the hardest to simulate, but they’re where robots can deliver the most value,” said Andrea Thomaz, co-founder and CEO of Diligent Robotics. “We’ve collected millions of examples of Moxi operating in dynamic human environments, now built into Moxi 2.0, the first system to truly reflect that lived experience and everything we have learned.”
Diligent Robotics is an early adopter of NVIDIA’s newly-unveiled IGX™ Thor, an NVIDIA Blackwell-powered, industrial-grade, enterprise-ready platform designed for industrial, robotics and medical edge AI applications. It features real-time sensor processing, AI reasoning, functional safety and long-term enterprise support.
“Moxi 2.0 has 10x the compute of Moxi 1.0, thanks to the rapid advancement of the NVIDIA Jetson line,” continued Thomaz. “We’re excited about how the new NVIDIA IGX Thor platform pushes the boundaries of AI performance at the edge, unlocking possibilities for future generations of intelligent, human-centered robots.”
With Moxi 2.0, Diligent introduces upgraded intelligence and hardware, designed to handle the real-world complexity of crowded, dynamic indoor human environments. The new system pairs next-generation AI compute with Diligent’s proprietary AI stack, enabling Moxi to reason, predict, and adapt for a wider range of capabilities in real-time, including pre-emptively navigating around beds and wheelchairs.
What’s New in Moxi 2.0
● Next-Gen AI Compute: Powered by NVIDIA Thor, Moxi 2.0 is equipped with increased compute, allowing Diligent to deploy significantly more powerful and capable AI models and faster inference speeds.
● Next-Gen Hardware Platform: The new design is optimized for manufacturability and hardened to support the fleet’s quickly growing scale.
● Robot Foundation Model: Diligent is developing an end-to-end action model optimized for enhanced dense navigation behaviors and high precision, complex manipulation. Leveraging its growing dataset of deployment data—expected to grow to petabytes next year with Moxi 2.0—Diligent will be releasing increasingly more powerful foundation models to power the next generation of robotic applications.
● Physical User Interaction Points: Deployment has provided detailed user feedback on how to service and physically interact with the Moxi platform. Moxi 2.0 has improved handles and servicing panels for easier user navigation.
Solving Robotics’ Chicken-and-Egg Data Problem
Most robotics platforms face a fundamental challenge: the models need deployment to improve, but the models must improve before wide deployment. Diligent has solved this problem by scaling its MVP humanoid platform early, allowing it to collect massive volumes of high-value data from the real-world. This is the true value of the learning flywheel that a deployed fleet offers: The ability for data to capture the millions of edge cases of dynamic interactive environments and fuel faster learning of models to handle them.
Today, Moxi already excels at mobile manipulation when faced with variations, predictive inference in busy environments, and human interactions in shared spaces. Moxi 2.0 will continue building on this foundation.
Moxi 2.0’s platform improvements are designed to support increased robot deployments within a single hospital, scaling to 15+ units per site as more advanced capabilities come online. As a result, Diligent expects to double its hospital footprint annually, and deploy thousands of robots deployed 2030.