| id |
oapen-20.500.12657-32838
|
| record_format |
dspace
|
| spelling |
oapen-20.500.12657-328382022-08-31T07:02:21Z How mobile robots can self-organise a vocabulary Vogt, Paul language in robots artificial intelligence Feature extraction Feature vector Joint attention Lexicon Reference Symbol grounding problem Talking Heads bic Book Industry Communication::C Language::CF linguistics bic Book Industry Communication::U Computing & information technology One of the hardest problems in science is the symbol grounding problem, a question that has intrigued philosophers and linguists for more than a century. With the rise of artificial intelligence, the question has become very actual, especially within the field of robotics. The problem is that an agent, be it a robot or a human, perceives the world in analogue signals. Yet humans have the ability to categorise the world in symbols that they, for instance, may use for language. This book presents a series of experiments in which two robots try to solve the symbol grounding problem. The experiments are based on the language game paradigm, and involve real mobile robots that are able to develop a grounded lexicon about the objects that they can detect in their world. Crucially, neither the lexicon nor the ontology of the robots has been preprogrammed, so the experiments demonstrate how a population of embodied language users can develop their own vocabularies from scratch. 2016-12-31 23:55:55 2018-12-12 10:19:03 2020-04-01T14:20:21Z 2020-04-01T14:20:21Z 2015 book 603358 OCN: 945783174 9783946234012 http://library.oapen.org/handle/20.500.12657/32838 eng Computational Models of Language Evolution application/pdf Attribution 4.0 International 603358.pdf http://langsci-press.org/catalog/book/50 Language Science Press 10.26530/OAPEN_603358 10.26530/OAPEN_603358 0bad921f-3055-43b9-a9f1-ea5b2d949173 9783946234012 2 270 open access
|
| institution |
OAPEN
|
| collection |
DSpace
|
| language |
English
|
| description |
One of the hardest problems in science is the symbol grounding problem, a question that has intrigued philosophers and linguists for more than a century. With the rise of artificial intelligence, the question has become very actual, especially within the field of robotics. The problem is that an agent, be it a robot or a human, perceives the world in analogue signals. Yet humans have the ability to categorise the world in symbols that they, for instance, may use for language. This book presents a series of experiments in which two robots try to solve the symbol grounding problem. The experiments are based on the language game paradigm, and involve real mobile robots that are able to develop a grounded lexicon about the objects that they can detect in their world. Crucially, neither the lexicon nor the ontology of the robots has been preprogrammed, so the experiments demonstrate how a population of embodied language users can develop their own vocabularies from scratch.
|
| title |
603358.pdf
|
| spellingShingle |
603358.pdf
|
| title_short |
603358.pdf
|
| title_full |
603358.pdf
|
| title_fullStr |
603358.pdf
|
| title_full_unstemmed |
603358.pdf
|
| title_sort |
603358.pdf
|
| publisher |
Language Science Press
|
| publishDate |
2016
|
| url |
http://langsci-press.org/catalog/book/50
|
| _version_ |
1771297626347536384
|
