NVIDIA releases GR00T 2 and Isaac Lab 3.0 at CoRL
Image: NVIDIA / NVIDIA Blog · press-kit
On 9 November 2026 NVIDIA said GR00T 2 averages 71% success across 50 robot tasks from one demonstration each, and learns from human video.
NVIDIA introduced GR00T 2 and Isaac Lab 3.0 on 9 November 2026 at the Conference on Robot Learning. GR00T 2 is an open world action model built on NVIDIA Cosmos and trained on robot data and human data, including 100,000 hours of egocentric human video. According to NVIDIA, it completed 40 of 50 evaluated tasks at least once with no task-specific demonstrations, averaged 71% success across the 50 tasks with one demonstration per task, and reached 95% with five. NVIDIA also says it transfers skills learned from human demonstrations between different robot bodies without robot demonstrations.
Isaac Lab 3.0 is the new release of NVIDIA's open-source robot-learning framework, published on GitHub under the tag v3.0.0. It lets users switch between the PhysX and Newton physics solvers, adds a reinforcement-learning post-training library for foundation models such as GR00T, and models deformable objects like cables and cloth. On a vision-based dexterous manipulation benchmark NVIDIA reports up to 2.5 times the training throughput of Isaac Lab 2.3 with PhysX.
Early testers named by NVIDIA include Nexuni, Foxconn, Siemens and MicroAGI. NVIDIA's blog calls GR00T 2 open but does not state its licence terms. All performance figures are NVIDIA's own.
Sources
- NVIDIA Blog Primary source
- The Robot Report
