RoboticFirms

Article • medical-pharmaceutical-robots

Diligent Robotics Begins Rolling Out Moxi 2.0 Hospital Robot

ByAyshathul Mushrifa

Diligent Robotics, a Serve Robotics company, has begun rolling out Moxi 2.0 to health systems across the United States. The next-generation mobile manipulation platform is shaped by five years of operations across more than 25 hospitals.

Moxi 2.0 introduces Diligent's proprietary World Model and learning flywheel, which use fleet experience to improve software over time. The platform was developed using NVIDIA Isaac Sim and aspects of NVIDIA Cosmos open world models.

Andrea Thomaz, Founder and CEO of Diligent Robotics, stated:

“Today we’re deploying our most sophisticated physical AI platform yet. 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.”

The upgraded system uses NVIDIA-powered A2000 compute, delivering 10x onboard compute and 10–15x faster perception than the previous generation. Diligent says this enables faster real-time decision-making and more confident navigation in dynamic hospital environments.

Moxi 2.0 also provides up to 18 hours of operating time per day, 30% faster charging, improved autonomy and recovery, upgraded cameras and sensors, redesigned storage drawers, and ergonomic handles informed by feedback from nurses and pharmacy teams.

The platform is rolling out to Endeavor Health Edward Hospital, Providence Saint John’s Health Center, and Children’s Hospital Los Angeles, with additional U.S. deployments planned.

At Children’s Hospital Los Angeles, Moxi has completed more than 40,000 deliveries, representing over 16,000 hours of transport work that staff did not have to perform, according to the hospital.

Diligent trained Moxi’s World Model on Amazon SageMaker HyperPod, while T-Mobile for Business is supporting network connectivity and private 5G planning. Safety and autonomy behaviors run onboard, allowing Moxi to continue operating during Wi-Fi interruptions.