English

Learning to Grasp from a Single Demonstration

Computer Vision and Pattern Recognition 2018-06-12 v1 Machine Learning Robotics

Abstract

Learning-based approaches for robotic grasping using visual sensors typically require collecting a large size dataset, either manually labeled or by many trial and errors of a robotic manipulator in the real or simulated world. We propose a simpler learning-from-demonstration approach that is able to detect the object to grasp from merely a single demonstration using a convolutional neural network we call GraspNet. In order to increase robustness and decrease the training time even further, we leverage data from previous demonstrations to quickly fine-tune a GrapNet for each new demonstration. We present some preliminary results on a grasping experiment with the Franka Panda cobot for which we can train a GraspNet with only hundreds of train iterations.

Keywords

Cite

@article{arxiv.1806.03486,
  title  = {Learning to Grasp from a Single Demonstration},
  author = {Pieter Van Molle and Tim Verbelen and Elias De Coninck and Cedric De Boom and Pieter Simoens and Bart Dhoedt},
  journal= {arXiv preprint arXiv:1806.03486},
  year   = {2018}
}

Comments

10 pages, 5 figures, IAS-15 2018 workshop on Learning Applications for Intelligent Autonomous Robots

R2 v1 2026-06-23T02:24:32.731Z