Corpus ID: 28326841

Self-Supervised Visual Planning with Temporal Skip Connections

@inproceedings{Ebert2017SelfSupervisedVP,
  title={Self-Supervised Visual Planning with Temporal Skip Connections},
  author={Frederik Ebert and Chelsea Finn and Alex X. Lee and S. Levine},
  booktitle={CoRL},
  year={2017}
}
  • Frederik Ebert, Chelsea Finn, +1 author S. Levine
  • Published in CoRL 2017
  • Engineering, Computer Science
  • In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected data is prediction: if a robot can learn to predict the future, it can use this predictive model to take actions to produce desired outcomes, such as moving an object to a particular location. However, in complex open-world scenarios, designing a… CONTINUE READING
    146 Citations

    Figures, Tables, and Topics from this paper

    Explore Further: Topics Discussed in This Paper

    Learning Robotic Manipulation through Visual Planning and Acting
    • 29
    • PDF
    Time Reversal as Self-Supervision
    • 8
    • PDF
    Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning
    • 34
    • PDF
    Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
    • 107
    • PDF
    TRASS: Time Reversal as Self-Supervision
    Few-Shot Goal Inference for Visuomotor Learning and Planning
    • 23
    • PDF
    Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller
    • 9
    • PDF
    Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning
    • 2
    • Highly Influenced
    • PDF
    Motion Perception in Reinforcement Learning with Dynamic Objects
    • 11
    • PDF

    References

    SHOWING 1-10 OF 30 REFERENCES
    Deep visual foresight for planning robot motion
    • Chelsea Finn, S. Levine
    • Computer Science
    • 2017 IEEE International Conference on Robotics and Automation (ICRA)
    • 2017
    • 396
    • PDF
    Unsupervised Learning for Physical Interaction through Video Prediction
    • 627
    • PDF
    Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours
    • Lerrel Pinto, A. Gupta
    • Computer Science
    • 2016 IEEE International Conference on Robotics and Automation (ICRA)
    • 2016
    • 665
    • PDF
    Learning to Poke by Poking: Experiential Learning of Intuitive Physics
    • 349
    • PDF
    Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
    • 490
    • PDF
    Learning predictive models of a depth camera & manipulator from raw execution traces
    • 40
    • PDF
    Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection
    • 1,052
    • PDF
    Autonomously Acquiring Instance-Based Object Models from Experience
    • 22
    • PDF
    DeepMPC: Learning Deep Latent Features for Model Predictive Control
    • 210
    • PDF
    Uncertainty-Aware Reinforcement Learning for Collision Avoidance
    • 149
    • PDF