Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes

@article{Wu2019PixelAttentivePG,
  title={Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes},
  author={B. Wu and Iretiayo Akinola and P. Allen},
  journal={2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2019},
  pages={1789-1796}
}
  • B. Wu, Iretiayo Akinola, P. Allen
  • Published 2019
  • Computer Science
  • 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    • Recent advances in on-policy reinforcement learning (RL) methods enabled learning agents in virtual environments to master complex tasks with high-dimensional and continuous observation and action spaces. However, leveraging this family of algorithms in multi-fingered robotic grasping remains a challenge due to large sim-to-real fidelity gaps and the high sample complexity of on-policy RL algorithms. This work aims to bridge these gaps by first reinforcement-learning a multi-fingered robotic… CONTINUE READING
    View on IEEE
    arxiv.org
    8 Citations
    Background Citations
    5
    Methods Citations
    1
    8 Citations
    Citation Type

    Citation Type

    MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning
    • 14
    • PDF
    Generative Attention Learning: a "GenerAL" framework for high-performance multi-fingered grasping in clutter
    • 3
    • PDF
    Disentangled Planning and Control in Vision Based Robotics via Reward Machines
    • PDF
    Multi-Fingered Grasp Planning via Inference in Deep Neural Networks
    • 5
    • PDF
    Multifingered Grasp Planning via Inference in Deep Neural Networks: Outperforming Sampling by Learning Differentiable Models
    • 5
    Learning Manipulation Skills via Hierarchical Spatial Attention
    • 2
    • PDF
    Review of Deep Reinforcement Learning-Based Object Grasping: Techniques, Open Challenges, and Recommendations
    • 2
    • PDF
    Learning Precise 3D Manipulation from Multiple Uncalibrated Cameras
    • 3
    • PDF

    References

    SHOWING 1-10 OF 31 REFERENCES
    Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods
    • 86
    • PDF
    Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning
    • 155
    • PDF
    QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
    • 377
    • Highly Influential
    • 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
    End-to-End Training of Deep Visuomotor Policies
    • 1,986
    • PDF
    Learning a visuomotor controller for real world robotic grasping using simulated depth images
    • 84
    • PDF
    Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach
    • 147
    • Highly Influential
    • PDF
    Learning Hand-Eye Coordination for Robotic Grasping with Large-Scale Data Collection
    • 176
    • PDF
    Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping
    • 315
    • PDF
    Grasping of Unknown Objects Using Deep Convolutional Neural Networks Based on Depth Images
    • 24
    • PDF