Corpus ID: 128342231

Learning Manipulation under Physics Constraints with Visual Perception

@article{Li2019LearningMU,
  title={Learning Manipulation under Physics Constraints with Visual Perception},
  author={Wenbin Li and Ale{\vs} Leonardis and Jeannette Bohg and Mario Fritz},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.09860}
}
  • Wenbin Li, Aleš Leonardis, +1 author Mario Fritz
  • Published 2019
  • Engineering, Computer Science
  • ArXiv
  • Understanding physical phenomena is a key competence that enables humans and animals to act and interact under uncertain perception in previously unseen environments containing novel objects and their configurations. In this work, we consider the problem of autonomous block stacking and explore solutions to learning manipulation under physics constraints with visual perception inherent to the task. Inspired by the intuitive physics in humans, we first present an end-to-end learning-based… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 63 REFERENCES

    Visual stability prediction for robotic manipulation

    VIEW 3 EXCERPTS

    Learning to Perform Physics Experiments via Deep Reinforcement Learning

    VIEW 1 EXCERPT

    Learning to Act by Predicting the Future

    VIEW 1 EXCERPT

    Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images

    VIEW 3 EXCERPTS

    ViZDoom: A Doom-based AI research platform for visual reinforcement learning

    VIEW 2 EXCERPTS