A dataset of 40K naturalistic 6-degree-of-freedom robotic grasp demonstrations
This provides a valuable resource for researchers in robotics and machine learning working on grasp planning, though it is incremental as it builds on existing data collection efforts.
The authors tackled the lack of large-scale datasets for robotic grasping by introducing a new method for collecting naturalistic grasp demonstrations and releasing a dataset of 40,000 successful grasps with a three-fingered gripper.
Modern approaches to grasp planning often involve deep learning. However, there are only a few large datasets of labelled grasping examples on physical robots, and available datasets involve relatively simple planar grasps with two-fingered grippers. Here we present: 1) a new human grasp demonstration method that facilitates rapid collection of naturalistic grasp examples, with full six-degree-of-freedom gripper positioning; and 2) a dataset of roughly forty thousand successful grasps on 109 different rigid objects with the RightHand Robotics three-fingered ReFlex gripper.