Deep Learning Approaches to Grasp Synthesis: a Review

Authors: Rhys Newbury, Morris Gu, Lachlan Chumbley, Arsalan Mousavian, Clemens Eppner, Jürgen Leitner, Jeannette Bohg, Antonio Morales, Tamim Asfour, Danica Kragic, Dieter Fox, Akansel Cosgun

Abstract This article surveys the literature on 6 degrees of freedom (6-DoF) Grasping using deep learning. We focus our review on robotic grasping in table-top scenarios, where the robot requires all 6 degrees of freedom of the end-effector pose to pick objects from the table successfully. Our review found the following ive approaches most prevalent in literature:sampling based approaches, direct regression, using shape-completion, reinforcement learning or considering semantics. We structure over review around these common methodologies, exploring the current research behind each approach. We report a list of the quantitative metrics commonly used to assess the success of the grasping tasks, while we also review the current object sets, datasets and sensor modalities used in the deep-learning methods. We then discuss the findings of our reviews and make recommendations on the future directions for the field hoping to mitigate some of the current issues which exist in this field.

If you find our review useful, please cite us.

@misc{newbury2022review,
    title={Deep Learning Approaches to Grasp Synthesis: A Review}, 
    author={Rhys Newbury and Morris Gu and Lachlan Chumbley and Arsalan Mousavian and Clemens Eppner and Jürgen Leitner and Jeannette Bohg and Antonio Morales and Tamim Asfour and Danica Kragic and Dieter Fox and Akansel Cosgun},
    year={2022},
    eprint={2207.02556},
    archivePrefix={arXiv},
    primaryClass={cs.RO}
}

Publication Published at T-RO

Preprint arXiv

Acknowledgments