← Back to the feed
Robotics & manufacturingResearch findings

GraspIT Dataset: Bridging Simulation and Reality for Reliable Grasp Pose Generation

Original published 2026.07.07 15:00 KSTAdded to Blackdeck 2026.11.20 20:17 KST

What has changed?

Physical slip tests on Franka Panda robots in simulation provide validated grasp quality scores

Key points

  1. Physical slip tests on Franka Panda robots in simulation validate grasp quality in realistic conditions
  2. Approximately 316k annotated RGB-D frames are provided across 1035 simulation and 100 real scenes
  3. Includes 6-DoF grasp poses, object properties, and instance masks for robust grasp learning

Connect it to your work

Grasp quality is validated through real-world physical testing, enabling reliable 6-DoF grasp pose generation

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivGraspIT: A Dataset Bridging the Sim-to-Real gap and back for Validated Grasping SE(3) Pose Generation