Cargando…

A Neural Network Model for Learning 3D Object Representations Through Haptic Exploration

Humans initially learn about objects through the sense of touch, in a process called “haptic exploration.” In this paper, we present a neural network model of this learning process. The model implements two key assumptions. The first is that haptic exploration can be thought of as a type of navigati...

Descripción completa

Detalles Bibliográficos
Autores principales: Yan, Xiaogang, Mills, Steven, Knott, Alistair
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8027115/
https://www.ncbi.nlm.nih.gov/pubmed/33841123
http://dx.doi.org/10.3389/fnbot.2021.639001
_version_ 1783675759435448320
author Yan, Xiaogang
Mills, Steven
Knott, Alistair
author_facet Yan, Xiaogang
Mills, Steven
Knott, Alistair
author_sort Yan, Xiaogang
collection PubMed
description Humans initially learn about objects through the sense of touch, in a process called “haptic exploration.” In this paper, we present a neural network model of this learning process. The model implements two key assumptions. The first is that haptic exploration can be thought of as a type of navigation, where the exploring hand plays the role of an autonomous agent, and the explored object is this agent's “local environment.” In this scheme, the agent's movements are registered in the coordinate system of the hand, through slip sensors on the palm and fingers. Our second assumption is that the learning process rests heavily on a simple model of sequence learning, where frequently-encountered sequences of hand movements are encoded declaratively, as “chunks.” The geometry of the object being explored places constraints on possible movement sequences: our proposal is that representations of possible, or frequently-attested sequences implicitly encode the shape of the explored object, along with its haptic affordances. We evaluate our model in two ways. We assess how much information about the hand's actual location is conveyed by its internal representations of movement sequences. We also assess how effective the model's representations are in a reinforcement learning task, where the agent must learn how to reach a given location on an explored object. Both metrics validate the basic claims of the model. We also show that the model learns better if objects are asymmetrical, or contain tactile landmarks, or if the navigating hand is articulated, which further constrains the movement sequences supported by the explored object.
format Online
Article
Text
id pubmed-8027115
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-80271152021-04-09 A Neural Network Model for Learning 3D Object Representations Through Haptic Exploration Yan, Xiaogang Mills, Steven Knott, Alistair Front Neurorobot Neuroscience Humans initially learn about objects through the sense of touch, in a process called “haptic exploration.” In this paper, we present a neural network model of this learning process. The model implements two key assumptions. The first is that haptic exploration can be thought of as a type of navigation, where the exploring hand plays the role of an autonomous agent, and the explored object is this agent's “local environment.” In this scheme, the agent's movements are registered in the coordinate system of the hand, through slip sensors on the palm and fingers. Our second assumption is that the learning process rests heavily on a simple model of sequence learning, where frequently-encountered sequences of hand movements are encoded declaratively, as “chunks.” The geometry of the object being explored places constraints on possible movement sequences: our proposal is that representations of possible, or frequently-attested sequences implicitly encode the shape of the explored object, along with its haptic affordances. We evaluate our model in two ways. We assess how much information about the hand's actual location is conveyed by its internal representations of movement sequences. We also assess how effective the model's representations are in a reinforcement learning task, where the agent must learn how to reach a given location on an explored object. Both metrics validate the basic claims of the model. We also show that the model learns better if objects are asymmetrical, or contain tactile landmarks, or if the navigating hand is articulated, which further constrains the movement sequences supported by the explored object. Frontiers Media S.A. 2021-03-25 /pmc/articles/PMC8027115/ /pubmed/33841123 http://dx.doi.org/10.3389/fnbot.2021.639001 Text en Copyright © 2021 Yan, Mills and Knott. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Yan, Xiaogang
Mills, Steven
Knott, Alistair
A Neural Network Model for Learning 3D Object Representations Through Haptic Exploration
title A Neural Network Model for Learning 3D Object Representations Through Haptic Exploration
title_full A Neural Network Model for Learning 3D Object Representations Through Haptic Exploration
title_fullStr A Neural Network Model for Learning 3D Object Representations Through Haptic Exploration
title_full_unstemmed A Neural Network Model for Learning 3D Object Representations Through Haptic Exploration
title_short A Neural Network Model for Learning 3D Object Representations Through Haptic Exploration
title_sort neural network model for learning 3d object representations through haptic exploration
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8027115/
https://www.ncbi.nlm.nih.gov/pubmed/33841123
http://dx.doi.org/10.3389/fnbot.2021.639001
work_keys_str_mv AT yanxiaogang aneuralnetworkmodelforlearning3dobjectrepresentationsthroughhapticexploration
AT millssteven aneuralnetworkmodelforlearning3dobjectrepresentationsthroughhapticexploration
AT knottalistair aneuralnetworkmodelforlearning3dobjectrepresentationsthroughhapticexploration
AT yanxiaogang neuralnetworkmodelforlearning3dobjectrepresentationsthroughhapticexploration
AT millssteven neuralnetworkmodelforlearning3dobjectrepresentationsthroughhapticexploration
AT knottalistair neuralnetworkmodelforlearning3dobjectrepresentationsthroughhapticexploration