SAN JOSE, Calif., March 20, 2026 /PRNewswire/ — For robots to operate reliably in the real world, they must train in environments that accurately represent it. This is the core challenge behind Real2Sim—and the focus of XGRIDS’ presence at GTC 2026 (March 16–19, San Jose).
XGRIDS’ spatial intelligence solution now supports NVIDIA Omniverse NuRec for OpenUSD-based rendering, and appeared across multiple venues: a featured Startup Pitch, robotics demonstrations within NVIDIA’s ecosystem, and a joint showcase with Amazon Web Services (AWS).
Real2Sim: From Physical Space to AI Training
During Startup Pitch, XGRIDS Director Sunny Liao posed a central question:
How do you build training environments that truly reflect real-world conditions?
XGRIDS’ answer is a pipeline built on real-world data. By combining LiDAR and computer vision for multimodal spatial perception with high-fidelity 3D reconstruction, physical environments can be transformed into usable world models for simulation.
Compared to manual 3D modeling, this approach:
- Reduces the cost of building high-fidelity environments
- Enables continuous updates as real spaces evolve
- Keeps simulation closer to real-world deployment
Developers at GTC noted this offers a more practical path for robotics training and validation.
Spatial Intelligence for Physical AI
Beyond the Inception stage, XGRIDS’ solutions appeared at multiple showcase areas across GTC.
At the NVIDIA Robotics session, XGRIDS demonstrated its solution for embodied AI systems. By deploying spatial perception and modeling on quadruped robot platforms, robots can continuously map and understand their environments, using full 3D spatial structure for path planning, behavioral decision-making, and task execution rather than relying solely on local sensors for immediate obstacle avoidance.
It demonstrated how spatial intelligence integrates into embodied AI systems—enabling robots to understand full 3D environments for path planning, decision-making, and task execution.
At the AWS showcase, XGRIDS presented a complete Real2Sim workflow—from capture to world model generation to simulation training.
Looking Ahead
XGRIDS’ long-term focus remains consistent: building spatial intelligence infrastructure that converts real-world environments into world models AI systems can understand, reason about, and train on.
GTC 2026 marked a step in bringing this work into the Physical AI ecosystem. As embodied AI systems move from labs into warehouses, cities, and construction sites, the demand for accurate, scalable digital representations of environments will only grow.
XGRIDS is building the capture-to-simulation layer that makes that possible.
Media Contact:
[email protected]
https://www.xgrids.com
SOURCE XGRIDS
