Cargando…

Mechanical intelligence for learning embodied sensor-object relationships

Intelligence involves processing sensory experiences into representations useful for prediction. Understanding sensory experiences and building these contextual representations without prior knowledge of sensor models and environment is a challenging unsupervised learning problem. Current machine le...

Descripción completa

Detalles Bibliográficos
Autores principales: Prabhakar, Ahalya, Murphey, Todd
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9287329/
https://www.ncbi.nlm.nih.gov/pubmed/35840570
http://dx.doi.org/10.1038/s41467-022-31795-2
_version_ 1784748228966612992
author Prabhakar, Ahalya
Murphey, Todd
author_facet Prabhakar, Ahalya
Murphey, Todd
author_sort Prabhakar, Ahalya
collection PubMed
description Intelligence involves processing sensory experiences into representations useful for prediction. Understanding sensory experiences and building these contextual representations without prior knowledge of sensor models and environment is a challenging unsupervised learning problem. Current machine learning methods process new sensory data using prior knowledge defined by either domain knowledge or datasets. When datasets are not available, data acquisition is needed, though automating exploration in support of learning is still an unsolved problem. Here we develop a method that enables agents to efficiently collect data for learning a predictive sensor model—without requiring domain knowledge, human input, or previously existing data—using ergodicity to specify the data acquisition process. This approach is based entirely on data-driven sensor characteristics rather than predefined knowledge of the sensor model and its physical characteristics. We learn higher quality models with lower energy expenditure during exploration for data acquisition compared to competing approaches, including both random sampling and information maximization. In addition to applications in autonomy, our approach provides a potential model of how animals use their motor control to develop high quality models of their sensors (sight, sound, touch) before having knowledge of their sensor capabilities or their surrounding environment.
format Online
Article
Text
id pubmed-9287329
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-92873292022-07-17 Mechanical intelligence for learning embodied sensor-object relationships Prabhakar, Ahalya Murphey, Todd Nat Commun Article Intelligence involves processing sensory experiences into representations useful for prediction. Understanding sensory experiences and building these contextual representations without prior knowledge of sensor models and environment is a challenging unsupervised learning problem. Current machine learning methods process new sensory data using prior knowledge defined by either domain knowledge or datasets. When datasets are not available, data acquisition is needed, though automating exploration in support of learning is still an unsolved problem. Here we develop a method that enables agents to efficiently collect data for learning a predictive sensor model—without requiring domain knowledge, human input, or previously existing data—using ergodicity to specify the data acquisition process. This approach is based entirely on data-driven sensor characteristics rather than predefined knowledge of the sensor model and its physical characteristics. We learn higher quality models with lower energy expenditure during exploration for data acquisition compared to competing approaches, including both random sampling and information maximization. In addition to applications in autonomy, our approach provides a potential model of how animals use their motor control to develop high quality models of their sensors (sight, sound, touch) before having knowledge of their sensor capabilities or their surrounding environment. Nature Publishing Group UK 2022-07-15 /pmc/articles/PMC9287329/ /pubmed/35840570 http://dx.doi.org/10.1038/s41467-022-31795-2 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Prabhakar, Ahalya
Murphey, Todd
Mechanical intelligence for learning embodied sensor-object relationships
title Mechanical intelligence for learning embodied sensor-object relationships
title_full Mechanical intelligence for learning embodied sensor-object relationships
title_fullStr Mechanical intelligence for learning embodied sensor-object relationships
title_full_unstemmed Mechanical intelligence for learning embodied sensor-object relationships
title_short Mechanical intelligence for learning embodied sensor-object relationships
title_sort mechanical intelligence for learning embodied sensor-object relationships
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9287329/
https://www.ncbi.nlm.nih.gov/pubmed/35840570
http://dx.doi.org/10.1038/s41467-022-31795-2
work_keys_str_mv AT prabhakarahalya mechanicalintelligenceforlearningembodiedsensorobjectrelationships
AT murpheytodd mechanicalintelligenceforlearningembodiedsensorobjectrelationships