One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

@article{Yu2018OneShotIF,
  title={One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning},
  author={Tianhe Yu and Chelsea Finn and Annie Xie and Sudeep Dasari and Tianhao Zhang and Pieter Abbeel and Sergey Levine},
  journal={ArXiv},
  year={2018},
  volume={abs/1802.01557}
}
Humans and animals are capable of learning a new behavior by observing others perform the skill just once. We consider the problem of allowing a robot to do the same -- learning from a raw video pixels of a human, even when there is substantial domain shift in the perspective, environment, and embodiment between the robot and the observed human. Prior approaches to this problem have hand-specified how human and robot actions correspond and often relied on explicit human pose detection systems… CONTINUE READING

Similar Papers

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 40 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 61 REFERENCES

One-Shot Imitation Learning

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

End-to-end learning of deep visuomotor policies

S. Levine, C. Finn, T. Darrell, P. Abbeel
  • Journal of Machine Learning Research (JMLR),
  • 2016
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Learning robot activities from first-person human videos using convolutional future regression

  • 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2017
VIEW 1 EXCERPT