Generative Attention Learning: a "GenerAL" framework for high-performance multi-fingered grasping in clutter

@article{Wu2020GenerativeAL,
  title={Generative Attention Learning: a "GenerAL" framework for high-performance multi-fingered grasping in clutter},
  author={Bo-Han Wu and Iretiayo Akinola and Abhi Gupta and F. Xu and J. Varley and David Watkins-Valls and P. Allen},
  journal={Auton. Robots},
  year={2020},
  volume={44},
  pages={971-990}
}
  • Bo-Han Wu, Iretiayo Akinola, +4 authors P. Allen
  • Published 2020
  • Computer Science
  • Auton. Robots
  • Generative Attention Learning (GenerAL) is a framework for high-DOF multi-fingered grasping that is not only robust to dense clutter and novel objects but also effective with a variety of different parallel-jaw and multi-fingered robot hands. This framework introduces a novel attention mechanism that substantially improves the grasp success rate in clutter. Its generative nature allows the learning of full-DOF grasps with flexible end-effector positions and orientations, as well as all finger… CONTINUE READING
    3 Citations

    Figures, Tables, and Topics from this paper

    Explore Further: Topics Discussed in This Paper

    Multi-FinGAN: Generative Coarse-To-Fine Sampling of Multi-Finger Grasps
    • PDF
    Multi-Fingered Active Grasp Learning
    • 6
    • PDF

    References

    SHOWING 1-10 OF 62 REFERENCES
    Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes
    • 8
    • PDF
    Learning 6-DoF Grasping and Pick-Place Using Attention Focus
    • 25
    • PDF
    Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning
    • 155
    • PDF
    Domain Randomization and Generative Models for Robotic Grasping
    • J. Tobin, W. Zaremba, P. Abbeel
    • Computer Science, Engineering
    • 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    • 2018
    • 86
    • PDF
    Planning Multi-Fingered Grasps as Probabilistic Inference in a Learned Deep Network
    • 39
    • PDF
    QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
    • 377
    • PDF
    Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods
    • 86
    • PDF
    Grasping of Unknown Objects Using Deep Convolutional Neural Networks Based on Depth Images
    • 24
    • Highly Influential
    • PDF