From Robot Learning to Robot Understanding: Leveraging Causal Graphical Models for Robotics
Abstract
Causal graphical models have been proposed as a way to efficiently and explicitly reason about novel situations and the likely outcomes of decisions. A key challenge facing widespread implementation of these models in robots is using prior knowledge to hypothesize good candidate causal structures when the relevant environmental features are not known in advance. The tight link between causal reasoning and the ability to intervene in the world suggests that robotics has much to contribute to this challenge and would reap significant benefits from progress.
Cite
Text
Stocking et al. "From Robot Learning to Robot Understanding: Leveraging Causal Graphical Models for Robotics." Conference on Robot Learning, 2021.Markdown
[Stocking et al. "From Robot Learning to Robot Understanding: Leveraging Causal Graphical Models for Robotics." Conference on Robot Learning, 2021.](https://mlanthology.org/corl/2021/stocking2021corl-robot/)BibTeX
@inproceedings{stocking2021corl-robot,
title = {{From Robot Learning to Robot Understanding: Leveraging Causal Graphical Models for Robotics}},
author = {Stocking, Kaylene Caswell and Gopnik, Alison and Tomlin, Claire},
booktitle = {Conference on Robot Learning},
year = {2021},
pages = {1776-1781},
volume = {164},
url = {https://mlanthology.org/corl/2021/stocking2021corl-robot/}
}