Corpus ID: 221095826

Visual Imitation Made Easy

@article{Young2020VisualIM,
  title={Visual Imitation Made Easy},
  author={Sarah Young and Dhiraj Gandhi and Shubham Tulsiani and Abhinav Gupta and P. Abbeel and Lerrel Pinto},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.04899}
}
  • Sarah Young, Dhiraj Gandhi, +3 authors Lerrel Pinto
  • Published 2020
  • Computer Science
  • ArXiv
  • Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching or teleoperation prohibitively restrict our ability to efficiently collect large-scale data in the wild. Obtaining such diverse demonstration data is paramount for the generalization of learned skills to novel scenarios. In this work, we present an alternate interface for imitation that simplifies… CONTINUE READING
    1 Citations
    Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds

    References

    SHOWING 1-10 OF 48 REFERENCES
    Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation
    • 19
    • PDF
    Unsupervised Perceptual Rewards for Imitation Learning
    • 71
    • PDF
    Reinforcement and Imitation Learning for Diverse Visuomotor Skills
    • 135
    • PDF
    Grasping in the Wild: Learning 6DoF Closed-Loop Grasping From Low-Cost Demonstrations
    • 7
    • PDF
    Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation
    • 166
    • PDF
    Asymmetric Actor Critic for Image-Based Robot Learning
    • 116
    • PDF
    Keyframe-based Learning from Demonstration
    • 153
    • PDF
    Domain randomization for transferring deep neural networks from simulation to the real world
    • 862
    • PDF
    Third-Person Imitation Learning
    • 121
    • PDF
    Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias
    • 41
    • PDF