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.
Reported impact
Noble Machines cut its development timeline by nearly 3x, shipped Moby to Asia within 18 months of founding, and achieved that pace with a team of about 15 people instead of a much larger conventional robotics program.
Noble Machines uses the NVIDIA Isaac GR00T stack as the backbone for developing Moby, its general-purpose industrial robot, across simulation, training, evaluation, and onboard deployment. Engineers import mechanical designs and customer facility twins into NVIDIA Isaac Sim, use the Newton Physics Engine to model contact-rich behaviors such as grasping and lifting, and scale policy training with Isaac Lab plus VR teleoperation data. Pretraining runs on NVIDIA H100 GPUs, post-training and scene simulation use NVIDIA RTX 6000 PRO and GeForce RTX 5090 GPUs, and thousands of digital Moby instances can run in parallel before policies ever reach hardware. On the robot itself, NVIDIA Jetson Thor processes camera and sensor data and runs foundation-model inference locally, while partners such as ADLINK, Solomon, and Schaeffler help ruggedize hardware and adapt workflows for semiconductor facilities.
Digital facility models and teleoperation examples feed Isaac Sim and Isaac Lab training workflows, large GPU clusters refine policies across thousands of simulated Mobys, and the trained models are deployed onto Jetson Thor for real-time perception and control on the physical robot.
Accelerated Moby's development timeline by nearly 3x, from an expected four years to 18 months.
Achieve these milestones with a team of about 15 people, versus a conventional approach that would require at least 50 people.
Isaac Sim and Isaac Lab let Noble Machines run thousands of digital Moby instances in parallel.
NVIDIA Jetson Thor processes sensor data and runs robotics foundation-model inference onboard.
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.
The company profile lists 'Headquarters' as 'Sunnyvale' in the 'United States'.
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 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 NVIDIA Sample Jul 21, 2026 Wistron Corporation Wistron needed to scale production of NVIDIA AI infrastructure while improving quality, energy efficiency, and worker training across global plants, but traditional CFD studies, sparse defect data, and reactive factory… 10% energy reduction Apple Vision Pro · Cadence Reality Digital Twin Platform · NVIDIA Cosmos 