One-Shot Imitation from Observing Humans

via Domain-Adaptive Meta-Learning

Tianhe Yu*, Chelsea Finn*, Annie Xie, Sudeep Dasari, Tianhao Zhang, Pieter Abbeel, Sergey Levine

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. In this work, we present an approach for one-shot learning from a video of a human by using human and robot demonstration data from a variety of previous tasks to build up prior knowledge through meta-learning. Then, combining this prior knowledge and only a single video demonstration from a human, the robot can perform the task that the human demonstrated. We show experiments on both a PR2 arm and a Sawyer arm, demonstrating that after meta-learning, the robot can learn to place, push, and pick-and-place new objects using just one video of a human performing the manipulation.

Paper: https://arxiv.org/abs/1802.01557

Appendix: https://drive.google.com/open?id=1jCQQ5-QzpnHVQIwXMRses5_B0dMj6Sc4

Code: https://github.com/tianheyu927/mil