Nvidia · AI Agent · NVIDIA Blog
NVIDIA Research Unlocks Furthered Grasping, Smarter Autonomous Driving and Agent Tuning at Scale
Compiled by KHAO Editorial — aggregated from 2 sources. See llms.txt for citation guidance.
★ Tier-1 Source
What makes a robot gripper useful isn’t that it can pick up one object, it’s that it can pick up the next one, and the one after that, with a tool it’s never held before.
Key facts
- Trained across more than 1,000 games and 40,000 hours of interaction using a model based on GR00T, the resulting agents learn to generalize across environments
- At this year’s Computer Vision and Pattern Recognition (CVPR) conference, NVIDIA Research is presenting three papers that address each of these challenges, and share a common theme: training at scale
- Building on the GraspGen research foundation, another paper, Grasp-MPC, presented at ICRA 2026, advances the next step in the pipeline: moving from grasp generation to closed-loop grasp execution
- NVIDIA also unveiled at CVPR new physical AI agent skills that help researchers and developers speed the development of autonomous vehicles, robots and vision AI systems
Summary
What makes an autonomous vehicle system safe isn’t that it can reason through a situation, it’s that it can do so quickly enough on the hardware installed in the car. What makes a virtual agent capable is exposure to as many different environments as possible before it faces the real world. At this year’s Computer Vision and Pattern Recognition (CVPR) conference, NVIDIA Research is presenting three papers that address each of these challenges, and share a common theme: training at scale creates systems that generalize across diverse applications. GraspGen-X, the first foundation model for zero-shot grasping, was trained on billions of simulated grasps to work with any gripper it’s shown.