Published September 28, 2022 | Version v1
Dataset Open

VIMA: General Robot Manipulation with Multimodal Prompts

Authors/Creators

  • 1. NVIDIA, Stanford University
  • 2. Stanford University
  • 3. Macalester College
  • 4. NVIDIA, California Institute of Technology
  • 5. Tsinghua University
  • 6. NVIDIA, University of Texas, Austin
  • 7. NVIDIA

Description

VIMA dataset for learning general robot manipulation with multimodal prompts.

Files

vima.zip

Files (21.5 GB)

Name Size Download all
md5:82a52e6a13b90e41840e2cae7708a4ac
21.5 GB Preview Download