ToolsThe story, in brief
Nvidia wants to scale robot simulation training with Lyra 2.0
Nvidia just made robot sim training 10x faster. One photo. Real-time 3D worlds. Direct to production.
The KeyNews take
Why it matters
Lyra 2.0 dramatically reduces the friction in robot learning pipelines by auto-generating production-ready simulation environments from single images. This directly impacts how fast robotics companies can iterate on embodied AI training—a critical bottleneck in the race to scalable robot deployment.
The key facts
5 to knowNvidia Lyra 2.0 generates coherent 3D environments from single photograph
Generated scenes are real-time explorable
Environments can be used directly in robot simulations
Addresses robot simulation training at scale
Published April 16, 2026
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: Nvidia researchers have unveiled Lyra 2.0, a system that generates large, coherent 3D environments from a single photograph. The resulting scenes can be explored in real time and used directly in robot simulations.