Corpus ID: 188459715

Learning from Intended Corrections

@article{Zhang2018LearningFI,
  title={Learning from Intended Corrections},
  author={J-Y. Zhang and Anca D. Dragan},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.01225}
}
  • J-Y. Zhang, Anca D. Dragan
  • Published 2018
  • Computer Science
  • ArXiv
  • Our goal is to enable robots to learn cost functions from user guidance. Often it is difficult or impossible for users to provide full demonstrations, so corrections have emerged as an easier guidance channel. However, when robots learn cost functions from corrections rather than demonstrations, they have to extrapolate a small amount of information -- the change of a waypoint along the way -- to the rest of the trajectory. We cast this extrapolation problem as online function approximation… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 22 REFERENCES

    Movement primitives via optimization

    VIEW 4 EXCERPTS

    Learning to predict trajectories of cooperatively navigating agents

    VIEW 1 EXCERPT

    Maximum margin planning

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Planning-based prediction for pedestrians

    VIEW 1 EXCERPT

    Trajectories and keyframes for kinesthetic teaching: A human-robot interaction perspective

    VIEW 1 EXCERPT