English

Improving Data Efficiency of Self-supervised Learning for Robotic Grasping

Robotics 2019-03-04 v1

Abstract

Given the task of learning robotic grasping solely based on a depth camera input and gripper force feedback, we derive a learning algorithm from an applied point of view to significantly reduce the amount of required training data. Major improvements in time and data efficiency are achieved by: Firstly, we exploit the geometric consistency between the undistorted depth images and the task space. Using a relative small, fully-convolutional neural network, we predict grasp and gripper parameters with great advantages in training as well as inference performance. Secondly, motivated by the small random grasp success rate of around 3%, the grasp space was explored in a systematic manner. The final system was learned with 23000 grasp attempts in around 60h, improving current solutions by an order of magnitude. For typical bin picking scenarios, we measured a grasp success rate of 96.6%. Further experiments showed that the system is able to generalize and transfer knowledge to novel objects and environments.

Keywords

Cite

@article{arxiv.1903.00228,
  title  = {Improving Data Efficiency of Self-supervised Learning for Robotic Grasping},
  author = {Lars Berscheid and Thomas Rühr and Torsten Kröger},
  journal= {arXiv preprint arXiv:1903.00228},
  year   = {2019}
}

Comments

Accepted for ICRA 2019

R2 v1 2026-06-23T07:55:13.230Z