Foxconn needed to reduce nurse burnout and repetitive transport work in hospitals, but deploying autonomous clinical robots required safe simulation, real-time edge perception, and dependable navigation inside busy wards.
Reported impact
Foxconn reduced nurse workload by 30 percent, saved nurses two to three hours per day on transport tasks, cut deployment time by 40 percent through simulation-driven validation, and achieved 98 percent navigation accuracy in smart-hospital pilots.
Foxconn built Nurabot with the NVIDIA Isaac for Healthcare framework so hospitals could shift repetitive transport and logistics work away from nurses. The solution starts in digital twin hospital environments created with Isaac Sim and Omniverse, where Foxconn tests workflows, navigation, and model behavior before field deployment. Once validated, Nurabot runs in wards on Jetson AGX Orin edge compute, using multimodal perception, natural-language interaction, and real-time sensor processing to move medication, specimens, and supplies autonomously. The broader stack also uses Holoscan for real-time data handling and Cosmos-based scheduling and route optimization, while DGX infrastructure supports training for tasks such as audio classification and action recognition. That architecture let Foxconn move from simulation-driven validation into live pilots at Taichung Veterans General Hospital and then extend the model toward broader smart-hospital rollouts.
Hospital workflow requirements are modeled in Omniverse and Isaac Sim, where Foxconn trains and validates Nurabot behaviors. The resulting models are deployed onto Jetson AGX Orin-powered robots that process ward sensor data locally, navigate autonomously, and return operational feedback that informs wider hospital rollouts.
Deployment time was cut by 40% using simulation-driven validation.
Navigation tasks were performed with 98% accuracy.
Nurses saved 2-3 hours a day on transport-related tasks.
The implementation of Foxconn's Nurabot, powered by Isaac for Healthcare, resulted in a 30% reduction in nurse workload.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample Aug 25, 2026 Siemens Siemens needed to help industrial teams overcome fragmented engineering tools, labor shortages, and slow design and maintenance workflows so they could design, simulate, and operate complex products and factories faster… 10%–15% reductions in capital expenditure NVIDIA CUDA · NVIDIA DGX B200 · NVIDIA DGX H200 NVIDIA Sample Aug 24, 2026 Noble Machines Noble Machines needed to train, evaluate, and deploy a general-purpose industrial robot fast enough for real customer environments without relying on slow, physical-only testing or cloud-dependent inference. 15 people NVIDIA GeForce RTX 5090 GPUs · NVIDIA H100 GPUs · NVIDIA Isaac GR00T 1.7 NVIDIA Sample Aug 12, 2026 Pegatron Pegatron needed to improve factory planning, quality control, and operational efficiency across large manufacturing sites, but manual line design, fragmented agent development, scarce defect data, and labor-intensive… 10% decrease in operational effort NVIDIA AI Enterprise · NVIDIA Cosmos · NVIDIA DGX 