Abstract. This article studies how a robot can learn nouns and adjectives in language. Towards this end, we extended a framework that enabled robots to learn affordances from its sensorimotor interactions, to learn nouns and adjectives using labeling from humans. Specifically, an iCub humanoid robot interacted with a set of objects (each labeled with a set of adjectives and a noun) and learned to predict the effects (as labeled with a set of verbs) it can generate on them with its behaviors. Different from appearance-based studies that directly link the appearances of objects to nouns and adjectives, we first predict the affordances of an object through a set of Support Vector Machine classifiers which provided a functional view of the object. Then, we learned the mapping between these predicted affordance values and nouns and adjectives. We evaluated and compared a number of different approaches towards the learning of nouns and adjectives on a small set of novel objects.The results show that the proposed method provides better generalization than the appearance-based approaches towards learning adjectives whereas, for nouns, the reverse is the case. We conclude that affordances of objects can be more informative for (a subset of) adjectives describing objects in language.
Günlük hayatta bir iş için seçilecek el aleti genellikle o aletin dış görünüşü ve nesnelerüzerindeki etkisinden yola çıkılarak seçilir. Bu etki, seçilen aletin saglarlıgını (ing. affordance) belirler. Bu çalışmanın amacı, el aletlerinin sadece dış görünüşlerini kullanarak onların saglarlıklarını belirlemek ve insansı robotların basit alet kullanımı için bir zemin oluşturmaktır. Bu amaçla yapılan çalışmada insan tarafından etkileşilen el aletlerinin fonksiyonel bölgelerinin düzlük, sivrilik, iki uç arası uzaklık, griölçek renk histogramı gibï oznitelikler çıkartılarak belli saglarlık modelleri egitilmiştir.Saglarlıklarıögrenilmek istenen el aletinden çıkarılan her bir oznitelik, egitilmiş modellere verilerek bu aletin kesebilme, delebilme, sıkıştırabilme ve ittirebilme saglarlıklarından hangilerine sahip oldugu belirlenir. Testlerde modelin %93.1 oranında saglarlıkları dogru tahmin ettigi görülmüştür. Bu sonuçlara bakılarak modelin insansı robotlarda basit alet kullanımı için uygun bir zemin oluşturdugu söylenebilir. ABSTRACTIn daily life, the selection of a hand tool for a job depends on appereance of the tool and its effect on the objects .The effect determines the affordance of the chosen tool. Aim of this work is to determine the affordances of hand tools based only on their appereance and to build a basis for simple tool usage of humanoid robots. Towards this end, in this work from the functional regions of human interacted hand tools, sharpness,bluntness, distance between two tip and grayscale histogram features are extracted and specific affordance models are trained. The features of a hand tool which its affordances wanted to be learned are given to the trained models to determine which affordances that the tool has like can cut, can push, can squeeze, can pierce. During testing, the model predicted the affordances %93.1. From this results it can be said that, this model sets a basis for simple tool usage of humanoid robots.Bu çalışma Tübitak tarafından desteklenmektedir. 978-1-4673-0056-8/12/$26.00 c 2012 IEEE
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.