Grasp planning and most specifically the grasp space exploration is still an open issue in robotics. This article presents an efficient procedure for exploring the grasp space of a multifingered adaptive gripper for generating reliable grasps given a known object pose. This procedure relies on a limited dataset of manually specified expert grasps, and use a mixed analytic and data-driven approach based on the use of a grasp quality metric and variational autoencoders. The performances of this method are assessed by generating grasps in simulation for three different objects. On this grasp planning task, this method reaches a grasp success rate of 99.91% on 7000 trials.
@article{arxiv.2109.09572,
title = {Human Initiated Grasp Space Exploration Algorithm for an Underactuated Robot Gripper Using Variational Autoencoder},
author = {Clément Rolinat and Mathieu Grossard and Saifeddine Aloui and Christelle Godin},
journal= {arXiv preprint arXiv:2109.09572},
year = {2021}
}
Comments
accepted at ICRA 2021 conference. arXiv admin note: substantial text overlap with arXiv:2109.08504