Autonomous Motion Conference Paper 2016

Ensuring Ethical Behavior from Autonomous Systems

Nao

We propose a method which generates reactive robot behavior learned from human demonstration. In order to do so, we use the Playful programming language which is based on the reactive programming paradigm. This allows us to represent the learned behavior as a set of associations between sensor and motor primitives in a human readable script. Distinguishing between sensor and motor primitives introduces a supplementary level of granularity and more importantly enforces feedback, increasing adaptability and robustness. As the experimental section shows, useful behaviors may be learned from a single demonstration covering a very limited portion of the task space.

Author(s): Anderson, Michael and Anderson, Susan Leigh and Berenz, Vincent
Book Title: Artificial Intelligence Applied to Assistive Technologies and Smart Environments, Papers from the 2016 AAAI Workshop, Phoenix, Arizona, USA, February 12, 2016
Year: 2016
Bibtex Type: Conference Paper (inproceedings)
URL: http://www.aaai.org/ocs/index.php/WS/AAAIW16/paper/view/12555
Cross Ref: DBLP:conf/aaai/2016assistive
Electronic Archiving: grant_archive

BibTex

@inproceedings{DBLP:conf/aaai/AndersonAB16,
  title = {Ensuring Ethical Behavior from Autonomous Systems},
  booktitle = {Artificial Intelligence Applied to Assistive Technologies and Smart Environments, Papers from the 2016 {AAAI} Workshop, Phoenix, Arizona, USA, February 12, 2016},
  abstract = {We propose a method which generates reactive
  robot behavior learned from human demonstration. In order
  to do so, we use the Playful programming language which is
  based on the reactive programming paradigm. This allows us to
  represent the learned behavior as a set of associations between
  sensor and motor primitives in a human readable script.
  Distinguishing between sensor and motor primitives introduces
  a supplementary level of granularity and more importantly
  enforces feedback, increasing adaptability and robustness. As
  the experimental section shows, useful behaviors may be learned
  from a single demonstration covering a very limited portion of
  the task space.},
  year = {2016},
  slug = {dblp-conf-aaai-andersonab16},
  author = {Anderson, Michael and Anderson, Susan Leigh and Berenz, Vincent},
  crossref = {DBLP:conf/aaai/2016assistive},
  url = {http://www.aaai.org/ocs/index.php/WS/AAAIW16/paper/view/12555}
}