Corpus ID: 84187227

Combining Coarse and Fine Physics for Manipulation using Parallel-in-Time Integration

@article{Agboh2019CombiningCA,
  title={Combining Coarse and Fine Physics for Manipulation using Parallel-in-Time Integration},
  author={Wisdom C. Agboh and D. Ruprecht and M. Dogar},
  journal={ArXiv},
  year={2019},
  volume={abs/1903.08470}
}
  • Wisdom C. Agboh, D. Ruprecht, M. Dogar
  • Published 2019
  • Engineering, Physics, Computer Science
  • ArXiv
  • We present a method for fast and accurate physics-based predictions during non-prehensile manipulation planning and control. Given an initial state and a sequence of controls, the problem of predicting the resulting sequence of states is a key component of a variety of model-based planning and control algorithms. We propose combining a coarse (i.e. computationally cheap but not very accurate) predictive physics model, with a fine (i.e. computationally expensive but accurate) predictive physics… CONTINUE READING
    Parareal with a learned coarse model for robotic manipulation
    Accurate Vision-based Manipulation through Contact Reasoning
    Human-like Planning for Reaching in Cluttered Environments
    Time-parallel simulation of the Schrödinger Equation
    1
    Introducing a Human-like Planner for Reaching in Cluttered Environments
    Applications of time parallelization
    2

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES
    MuJoCo: A physics engine for model-based control
    1533
    Simulation tools for model-based robotics: Comparison of Bullet, Havok, MuJoCo, ODE and PhysX
    123
    Real-Time Online Re-Planning for Grasping Under Clutter and Uncertainty
    16
    Combining learned and analytical models for predicting action effects
    44
    Time Integrating Articulated Body Dynamics Using Position-Based Collocation Methods.
    2