Command Palette
Search for a command to run...
GraspGen: Scaling Sim2Real Grasping Grasp Generation Dataset
GraspGen: Scaling Sim2Real Grasping is a large-scale simulated grasping dataset released by NVIDIA in 2025. It contains over 57 million grasp samples generated from 8,515 objects in the Objaverse XL (LVIS) dataset, designed for the Franka Panda, Robotiq-2f-140 industrial gripper, and single-point contact suction gripper (30 mm radius). The goal is to enhance the transferability of robotic grasping skills from simulation to reality through large-scale simulation data.
The dataset is provided in WebDataset format and includes over 57 million simulated grasp samples in total, covering three different types of robotic grippers. It is suitable for research in robotic grasping, simulation-to-reality transfer (Sim2Real), and robot learning.
Dataset Composition
- franka: Grasp data for the Franka Panda gripper.
- robotiq2f140: Grasp data for the Robotiq-2f-140 industrial gripper.
- suction: Grasp data for the single-point contact suction gripper.
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.
