Physical trials risked hardware damage. Simulating years of learning in hours cut dev cycles from weeks to days.
A developer of general-purpose humanoid robots designed to work in existing warehouses where installing fixed automation is too costly and slow.
Achieving reliable whole-body control requires handling unpredictable variables, from slippery floors to physical bumps from human workers....
“Isaac Sim running on NVIDIA GPUs lets us simulate years of real-world learning for Digit in just hours. That simulation speedup means we can train for all the conditions we might see on the factory floor.”
Bipedal humanoid robots for warehouse automation and material handling.
NVIDIA is a technology company that specializes in semiconductors, graphics processing units, and artificial intelligence for applications in data centers, gaming, and more.
Related implementations across industries and use cases
Limited on-prem GPUs constrained training. Agility now runs tens of thousands of parallel simulations to refine robot navigation.
Reprogramming robots required weeks of expert coding. Now, staff retask machines in five minutes using a simple tablet interface.
Engineers sat on hazardous floors to test controls. Now, digital twins validate logic virtually, cutting commissioning time by years.
Patent strategy relied on subjective manual judgment. AI now standardizes analysis, cutting research cycles from months to days.
IT staff logged in every six hours to check 30 systems. GenAI now automates monitoring, saving 3,000 hours and ending downtime risk.
Lab supply orders were handwritten in notebooks. Digital ordering now takes seconds, saving 30,000 hours for research annually.
Experts spent 15 minutes pulling data from scattered systems. Natural language prompts now generate detailed reports instantly.