From Robot Learning To Robot Understanding: Leveraging Causal Graphical Models For Robotics

Kaylene Caswell Stocking, Alison Gopnik, Claire Tomlin
Proceedings of the 5th Conference on Robot Learning, PMLR 164:1776-1781, 2022.

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 this Paper

BibTeX
@InProceedings{pmlr-v164-stocking22a, title = {From Robot Learning To Robot Understanding: Leveraging Causal Graphical Models For Robotics}, author = {Stocking, Kaylene Caswell and Gopnik, Alison and Tomlin, Claire}, booktitle = {Proceedings of the 5th Conference on Robot Learning}, pages = {1776--1781}, year = {2022}, editor = {Faust, Aleksandra and Hsu, David and Neumann, Gerhard}, volume = {164}, series = {Proceedings of Machine Learning Research}, month = {08--11 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v164/stocking22a/stocking22a.pdf}, url = {https://proceedings.mlr.press/v164/stocking22a.html}, 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.} }
Endnote
%0 Conference Paper %T From Robot Learning To Robot Understanding: Leveraging Causal Graphical Models For Robotics %A Kaylene Caswell Stocking %A Alison Gopnik %A Claire Tomlin %B Proceedings of the 5th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2022 %E Aleksandra Faust %E David Hsu %E Gerhard Neumann %F pmlr-v164-stocking22a %I PMLR %P 1776--1781 %U https://proceedings.mlr.press/v164/stocking22a.html %V 164 %X 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.
APA
Stocking, K.C., Gopnik, A. & Tomlin, C.. (2022). From Robot Learning To Robot Understanding: Leveraging Causal Graphical Models For Robotics. Proceedings of the 5th Conference on Robot Learning, in Proceedings of Machine Learning Research 164:1776-1781 Available from https://proceedings.mlr.press/v164/stocking22a.html.

Related Material