Watch and Learn: Learning to control feedback linearizable systems from expert demonstrations

Alimzhan Sultangazin, Luigi Pannocchi, Lucas Fraile, Paulo TabuadaICRA 2022 · OpenReview

Abstract

In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert. By focusing on feedback linearizable systems, we show how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$n+1$</tex> of them, where <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$n$</tex> is the number of states of the system being controlled. The results are experimentally demonstrated on a CrazyFlie 2.0 quadrotor.
BibTeX
@inproceedings{sultangazin2022watch,
  author = {Alimzhan Sultangazin and Luigi Pannocchi and Lucas Fraile and Paulo Tabuada},
  title = {{Watch and Learn: Learning to control feedback linearizable systems from expert demonstrations}},
  booktitle = {IEEE International Conference on Robotics and Automation},
  year = {2022},
  url = {https://openreview.net/forum?id=AiPvvRkRrGX},
}

Loading related content...

Figure