— Under construction —
195193
maths
items
1
0
author
asc
1
https://whatfeelingislike.net/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22instance%22%3A%22zotpress-b9ecfc594c79f2070a2c12b18f3610d3%22%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%22BMTNXHCM%22%2C%22library%22%3A%7B%22id%22%3A195193%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Laflaqui%5Cu00e8re%20et%20al.%22%2C%22parsedDate%22%3A%222015-09%22%2C%22numChildren%22%3A6%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3ELaflaqui%26%23xE8%3Bre%2C%20A.%2C%20O%26%23x2019%3BRegan%2C%20J.%20K.%2C%20Argentieri%2C%20S.%2C%20Gas%2C%20B.%2C%20%26amp%3B%20Terekhov%2C%20A.%20V.%20%282015%29.%20Learning%20agent%26%23x2019%3Bs%20spatial%20configuration%20from%20sensorimotor%20invariants.%20%3Ci%3ERobotics%20and%20Autonomous%20Systems%3C%5C%2Fi%3E%2C%20%3Ci%3E71%3C%5C%2Fi%3E%2C%2049%26%23x2013%3B59.%20%3Ca%20href%3D%27https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.robot.2015.01.003%27%3Ehttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.robot.2015.01.003%3C%5C%2Fa%3E%20%3Ca%20title%3D%27Download%27%20class%3D%27zp-DownloadURL%27%20href%3D%27https%3A%5C%2F%5C%2Fwhatfeelingislike.net%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.dl.php%3Fapi_user_id%3D195193%26amp%3Bdlkey%3DUR59VM3E%26amp%3Bcontent_type%3Dapplication%5C%2Fpdf%27%3EDownload%3C%5C%2Fa%3E%20%3Ca%20title%3D%27Download%27%20class%3D%27zp-DownloadURL%27%20href%3D%27https%3A%5C%2F%5C%2Fwhatfeelingislike.net%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.dl.php%3Fapi_user_id%3D195193%26amp%3Bdlkey%3D93ITG7C2%26amp%3Bcontent_type%3Dapplication%5C%2Fpdf%27%3EDownload%3C%5C%2Fa%3E%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Learning%20agent%5Cu2019s%20spatial%20configuration%20from%20sensorimotor%20invariants%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alban%22%2C%22lastName%22%3A%22Laflaqui%5Cu00e8re%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J.%20Kevin%22%2C%22lastName%22%3A%22O%5Cu2019Regan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sylvain%22%2C%22lastName%22%3A%22Argentieri%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bruno%22%2C%22lastName%22%3A%22Gas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexander%20V.%22%2C%22lastName%22%3A%22Terekhov%22%7D%5D%2C%22abstractNote%22%3A%22The%20design%20of%20robotic%20systems%20is%20largely%20dictated%20by%20our%20purely%20human%20intuition%20about%20how%20we%20perceive%20the%20world.%20This%20intuition%20has%20been%20proven%20incorrect%20with%20regard%20to%20a%20number%20of%20critical%20issues%2C%20such%20as%20visual%20change%20blindness.%20In%20order%20to%20develop%20truly%20autonomous%20robots%2C%20we%20must%20step%20away%20from%20this%20intuition%20and%20let%20robotic%20agents%20develop%20their%20own%20way%20of%20perceiving.%20The%20robot%20should%20start%20from%20scratch%20and%20gradually%20develop%20perceptual%20notions%2C%20under%20no%20prior%20assumptions%2C%20exclusively%20by%20looking%20into%20its%20sensorimotor%20experience%20and%20identifying%20repetitive%20patterns%20and%20invariants.%20One%20of%20the%20most%20fundamental%20perceptual%20notions%2C%20space%2C%20cannot%20be%20an%20exception%20to%20this%20requirement.%20In%20this%20paper%20we%20look%20into%20the%20prerequisites%20for%20the%20emergence%20of%20simplified%20spatial%20notions%20on%20the%20basis%20of%20a%20robot%5Cu2019s%20sensorimotor%20flow.%20We%20show%20that%20the%20notion%20of%20space%20as%20environment-independent%20cannot%20be%20deduced%20solely%20from%20exteroceptive%20information%2C%20which%20is%20highly%20variable%20and%20is%20mainly%20determined%20by%20the%20contents%20of%20the%20environment.%20The%20environment-independent%20definition%20of%20space%20can%20be%20approached%20by%20looking%20into%20the%20functions%20that%20link%20the%20motor%20commands%20to%20changes%20in%20exteroceptive%20inputs.%20In%20a%20sufficiently%20rich%20environment%2C%20the%20kernels%20of%20these%20functions%20correspond%20uniquely%20to%20the%20spatial%20configuration%20of%20the%20agent%5Cu2019s%20exteroceptors.%20We%20simulate%20a%20redundant%20robotic%20arm%20with%20a%20retina%20installed%20at%20its%20end-point%20and%20show%20how%20this%20agent%20can%20learn%20the%20configuration%20space%20of%20its%20retina.%20The%20resulting%20manifold%20has%20the%20topology%20of%20the%20Cartesian%20product%20of%20a%20plane%20and%20a%20circle%2C%20and%20corresponds%20to%20the%20planar%20position%20and%20orientation%20of%20the%20retina.%22%2C%22date%22%3A%22September%202015%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.robot.2015.01.003%22%2C%22ISSN%22%3A%220921-8890%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fwww.sciencedirect.com%5C%2Fscience%5C%2Farticle%5C%2Fpii%5C%2FS092188901500010X%22%2C%22collections%22%3A%5B%22T993CKP7%22%2C%22KZDKIUWB%22%2C%22T85AP8FW%22%5D%2C%22dateModified%22%3A%222023-09-28T05%3A42%3A38Z%22%7D%7D%2C%7B%22key%22%3A%22CEZEE8WB%22%2C%22library%22%3A%7B%22id%22%3A195193%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Laflaquiere%20et%20al.%22%2C%22parsedDate%22%3A%222013-11-03%22%2C%22numChildren%22%3A4%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3ELaflaquiere%2C%20A.%2C%20Terekhov%2C%20A.%20V.%2C%20Gas%2C%20B.%2C%20%26amp%3B%20O%26%23x2019%3BRegan%2C%20J.%20K.%20%282013%29.%20Learning%20an%20internal%20representation%20of%20the%20end-effector%20configuration%20space.%20%3Ci%3EIntelligent%20Robots%20and%20Systems%20%28IROS%29%2C%202013%20IEEE%5C%2FRSJ%20International%20Conference%20On%3C%5C%2Fi%3E%2C%201230%26%23x2013%3B1235.%20%3Ca%20href%3D%27http%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fxpls%5C%2Fabs_all.jsp%3Farnumber%3D6696507%27%3Ehttp%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fxpls%5C%2Fabs_all.jsp%3Farnumber%3D6696507%3C%5C%2Fa%3E%20%3Ca%20title%3D%27Download%27%20class%3D%27zp-DownloadURL%27%20href%3D%27https%3A%5C%2F%5C%2Fwhatfeelingislike.net%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.dl.php%3Fapi_user_id%3D195193%26amp%3Bdlkey%3DNCI2RNBU%26amp%3Bcontent_type%3Dapplication%5C%2Fpdf%27%3EDownload%3C%5C%2Fa%3E%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Learning%20an%20internal%20representation%20of%20the%20end-effector%20configuration%20space%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alban%22%2C%22lastName%22%3A%22Laflaquiere%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexander%20V.%22%2C%22lastName%22%3A%22Terekhov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bruno%22%2C%22lastName%22%3A%22Gas%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J.%20Kevin%22%2C%22lastName%22%3A%22O%27Regan%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%22November%203-7%2C%202013%22%2C%22proceedingsTitle%22%3A%22Intelligent%20Robots%20and%20Systems%20%28IROS%29%2C%202013%20IEEE%5C%2FRSJ%20International%20Conference%20on%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fxpls%5C%2Fabs_all.jsp%3Farnumber%3D6696507%22%2C%22collections%22%3A%5B%22SEW3CDK5%22%2C%22KZDKIUWB%22%5D%2C%22dateModified%22%3A%222021-04-11T17%3A10%3A44Z%22%7D%7D%2C%7B%22key%22%3A%22I6H9VXE6%22%2C%22library%22%3A%7B%22id%22%3A195193%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Terekhov%20and%20O%27Regan%22%2C%22parsedDate%22%3A%222016-03%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3ETerekhov%2C%20A.%20V.%2C%20%26amp%3B%20O%26%23x2019%3BRegan%2C%20J.%20K.%20%282016%29.%20Space%20as%20an%20Invention%20of%20Active%20Agents.%20%3Ci%3EFront.%20Robot.%20AI%3C%5C%2Fi%3E%2C%20%3Ci%3E3%3C%5C%2Fi%3E%284%29.%20%3Ca%20href%3D%27https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3389%5C%2Ffrobt.2016.00004%27%3Ehttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3389%5C%2Ffrobt.2016.00004%3C%5C%2Fa%3E%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Space%20as%20an%20Invention%20of%20Active%20Agents%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexander%20V.%22%2C%22lastName%22%3A%22Terekhov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J.%20Kevin%22%2C%22lastName%22%3A%22O%27Regan%22%7D%5D%2C%22abstractNote%22%3A%22The%20question%20of%20the%20nature%20of%20space%20around%20us%20has%20occupied%20thinkers%20since%20the%20dawn%20of%20humanity%2C%20with%20scientists%20and%20philosophers%20today%20implicitly%20assuming%20that%20space%20is%20something%20that%20exists%20objectively.%20Here%20we%20show%20that%20this%20does%20not%20have%20to%20be%20the%20case%3A%20the%20notion%20of%20space%20could%20emerge%20when%20biological%20organisms%20seek%20an%20economic%20representation%20of%20their%20sensorimotor%20flow.%20The%20emergence%20of%20spatial%20notions%20does%20not%20necessitate%20the%20existence%20of%20real%20physical%20space%2C%20but%20only%20requires%20the%20presence%20of%20sensorimotor%20invariants%20called%20%60compensable%27%20sensory%20changes.%20We%20show%20mathematically%20and%20then%20in%20simulations%20that%20na%5C%5C%5C%22ive%20agents%20making%20no%20assumptions%20about%20the%20existence%20of%20space%20are%20able%20to%20learn%20these%20invariants%20and%20to%20build%20the%20abstract%20notion%20that%20physicists%20call%20rigid%20displacement%2C%20which%20is%20independent%20of%20what%20is%20being%20displaced.%20Rigid%20displacements%20may%20underly%20perception%20of%20space%20as%20an%20unchanging%20medium%20within%20which%20objects%20are%20described%20by%20their%20relative%20positions.%20Our%20findings%20suggest%20that%20the%20question%20of%20the%20nature%20of%20space%2C%20currently%20exclusive%20to%20philosophy%20and%20physics%2C%20should%20also%20be%20addressed%20from%20the%20standpoint%20of%20neuroscience%20and%20artificial%20intelligence.%22%2C%22date%22%3A%22March%202016%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.3389%5C%2Ffrobt.2016.00004%22%2C%22ISSN%22%3A%22%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%2245TUMIMC%22%2C%22SEW3CDK5%22%2C%22VIJ96JC8%22%2C%22T993CKP7%22%2C%22KZDKIUWB%22%5D%2C%22dateModified%22%3A%222021-11-29T09%3A52%3A40Z%22%7D%7D%2C%7B%22key%22%3A%22MA7VINSN%22%2C%22library%22%3A%7B%22id%22%3A195193%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Terekhov%20and%20O%27Regan%22%2C%22parsedDate%22%3A%222014-10%22%2C%22numChildren%22%3A3%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3ETerekhov%2C%20A.%20V.%2C%20%26amp%3B%20O%26%23x2019%3BRegan%2C%20J.%20K.%20%282014%29.%20Learning%20abstract%20perceptual%20notions%3A%20The%20example%20of%20space.%20%3Ci%3E2014%20Joint%20IEEE%20International%20Conferences%20on%20Development%20and%20Learning%20and%20Epigenetic%20Robotics%20%28ICDL-Epirob%29%3C%5C%2Fi%3E%2C%20368%26%23x2013%3B373.%20%3Ca%20href%3D%27https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FDEVLRN.2014.6983009%27%3Ehttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FDEVLRN.2014.6983009%3C%5C%2Fa%3E%20%3Ca%20title%3D%27Download%27%20class%3D%27zp-DownloadURL%27%20href%3D%27https%3A%5C%2F%5C%2Fwhatfeelingislike.net%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.dl.php%3Fapi_user_id%3D195193%26amp%3Bdlkey%3DN8VQPERW%26amp%3Bcontent_type%3Dapplication%5C%2Fpdf%27%3EDownload%3C%5C%2Fa%3E%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Learning%20abstract%20perceptual%20notions%3A%20The%20example%20of%20space%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexander%20V.%22%2C%22lastName%22%3A%22Terekhov%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J.%20Kevin%22%2C%22lastName%22%3A%22O%27Regan%22%7D%5D%2C%22abstractNote%22%3A%22Humans%20are%20extremely%20swift%20learners.%20We%20are%20able%20to%20grasp%20highly%20abstract%20notions%2C%20whether%20they%20come%20from%20art%20perception%20or%20pure%20mathematics.%20Current%20machine%20learning%20techniques%20demonstrate%20astonishing%20results%20in%20extracting%20patterns%20in%20information.%20Yet%20the%20abstract%20notions%20we%20possess%20are%20more%20than%20just%20statistical%20patterns%20in%20the%20incoming%20information.%20Sensorimotor%20theory%20suggests%20that%20they%20represent%20functions%2C%20laws%2C%20describing%20how%20the%20information%20can%20be%20transformed%2C%20or%2C%20in%20other%20words%2C%20they%20represent%20the%20statistics%20of%20sensorimotor%20changes%20rather%20than%20sensory%20inputs%20themselves.%20The%20aim%20of%20our%20work%20is%20to%20suggest%20a%20way%20for%20machine%20learning%20and%20sensorimotor%20theory%20to%20benefit%20from%20each%20other%20so%20as%20to%20pave%20the%20way%20toward%20new%20horizons%20in%20learning.%20We%20show%20in%20this%20study%20that%20a%20highly%20abstract%20notion%2C%20that%20of%20space%2C%20can%20be%20seen%20as%20a%20collection%20of%20laws%20of%20transformations%20of%20sensory%20information%20and%20that%20these%20laws%20could%20in%20theory%20be%20learned%20by%20a%20naive%20agent.%20As%20an%20illustration%20we%20do%20a%20one-dimensional%20simulation%20in%20which%20an%20agent%20extracts%20spatial%20knowledge%20in%20the%20form%20of%20internalized%20%28%5Cu201csensible%5Cu201d%29%20rigid%20displacements.%20The%20agent%20uses%20them%20to%20encode%20its%20own%20displacements%20in%20a%20way%20which%20is%20isometrically%20related%20to%20external%20space.%20Though%20the%20algorithm%20allowing%20acquisition%20of%20rigid%20displacements%20is%20designed%20ad%20hoc%2C%20we%20believe%20it%20can%20stimulate%20the%20development%20of%20unsupervised%20learning%20techniques%20leading%20to%20similar%20results.%22%2C%22date%22%3A%22October%202014%22%2C%22proceedingsTitle%22%3A%222014%20Joint%20IEEE%20International%20Conferences%20on%20Development%20and%20Learning%20and%20Epigenetic%20Robotics%20%28ICDL-Epirob%29%22%2C%22conferenceName%22%3A%222014%20Joint%20IEEE%20International%20Conferences%20on%20Development%20and%20Learning%20and%20Epigenetic%20Robotics%20%28ICDL-Epirob%29%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FDEVLRN.2014.6983009%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%22KZDKIUWB%22%2C%22T85AP8FW%22%5D%2C%22dateModified%22%3A%222023-09-28T05%3A38%3A58Z%22%7D%7D%5D%7D
Laflaquière, A., O’Regan, J. K., Argentieri, S., Gas, B., & Terekhov, A. V. (2015). Learning agent’s spatial configuration from sensorimotor invariants. Robotics and Autonomous Systems, 71, 49–59. https://doi.org/10.1016/j.robot.2015.01.003 Download Download
Laflaquiere, A., Terekhov, A. V., Gas, B., & O’Regan, J. K. (2013). Learning an internal representation of the end-effector configuration space. Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference On, 1230–1235. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6696507 Download
Terekhov, A. V., & O’Regan, J. K. (2016). Space as an Invention of Active Agents. Front. Robot. AI, 3(4). https://doi.org/10.3389/frobt.2016.00004
Terekhov, A. V., & O’Regan, J. K. (2014). Learning abstract perceptual notions: The example of space. 2014 Joint IEEE International Conferences on Development and Learning and Epigenetic Robotics (ICDL-Epirob), 368–373. https://doi.org/10.1109/DEVLRN.2014.6983009 Download