Natural language grounding and grammar induction for robotic manipulation commands

M. Alomari, P. Duckworth, M. Hawasly, D. C. Hogg, A. G. Cohn

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Citations (Scopus)

Abstract

We present a cognitively plausible system capable of acquiring knowledge in language and vision from pairs of short video clips and linguistic descriptions. The aim of this work is to teach a robot manipulator how to execute natural language commands by demonstration. This is achieved by first learning a set of visual 'concepts' that abstract the visual feature spaces into concepts that have human-level meaning. Second, learning the mapping/grounding between words and the extracted visual concepts. Third, inducing grammar rules via a semantic representation known as Robot Control Language (RCL). We evaluate our approach against state-of-the-art supervised and unsupervised grounding and grammar induction systems, and show that a robot can learn to execute never seenbefore commands from pairs of unlabelled linguistic and visual inputs.

Original languageEnglish
Title of host publicationProceedings of the 1st Workshop on Language Grounding for Robotics, RoboNLP 2017 at the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
EditorsMohit Bansal, Cynthia Matuszek, Jacob Andreas, Yoav Artzi, Yonatan Bisk
PublisherAssociation for Computational Linguistics (ACL)
Pages35-43
Number of pages9
ISBN (Electronic)9781945626647
Publication statusPublished - 2017
Externally publishedYes
Event1st Workshop on Language Grounding for Robotics, RoboNLP 2017 at the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: 3 Aug 2017 → …

Publication series

NameProceedings of the 1st Workshop on Language Grounding for Robotics, RoboNLP 2017 at the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

Conference

Conference1st Workshop on Language Grounding for Robotics, RoboNLP 2017 at the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/TerritoryCanada
CityVancouver
Period3/08/17 → …

Fingerprint

Dive into the research topics of 'Natural language grounding and grammar induction for robotic manipulation commands'. Together they form a unique fingerprint.

Cite this