HyperAIHyperAI

Command Palette

Search for a command to run...

GraspGen: Scaling Sim2Real Grasping Grasp Generation Dataset

Date

Organization

NVIDIA

License

CC BY 4.0

GraspGen: Scaling Sim2Real Grasping is a large-scale simulated grasping dataset released by NVIDIA in 2025. The dataset contains over 57 million grasps generated from 8,515 objects in the Objaverse XL (LVIS) dataset, and is designed for the Franka Panda, Robotiq-2f-140 industrial gripper, and single-point contact suction gripper (30 mm radius). It aims to improve the transferability of robot grasping skills from simulation to reality through large-scale simulation data.

The dataset adopts the WebDataset format and contains over 57 million simulated grasps covering three different types of robot grippers, suitable for research in robot grasping, simulation-to-reality transfer (Sim2Real), and robot learning.

Dataset Composition

  • franka: Grasping data for the Franka Panda gripper.
  • robotiq2f140: Grasping data for the Robotiq-2f-140 industrial gripper.
  • suction: Grasping data for the single-point contact suction gripper.
数据集示例
数据集示例

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.

AI Co-coding
Ready-to-use GPUs
Best Pricing

HyperAI Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp