2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) 2013
DOI: 10.1109/devlrn.2013.6652534
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: This paper discusses grounded acquisition experiments of increasing complexity. Humanoid robots acquire English spatial lexicons from robot tutors. We identify how various spatial language systems, such as projective, absolute and proximal can be learned. The proposed learning mechanisms do not rely on direct meaning transfer or direct access to world models of interlocutors. Finally, we show how multiple systems can be acquired at the same time.

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
17
0

Year Published

2014
2014
2021
2021

Publication Types

Select...
4
1
1

Relationship

3
3

Authors

Journals

citations
Cited by 12 publications
(18 citation statements)
references
References 15 publications
1
17
0
Order By: Relevance
“…KNN is the only tested algorithm for continuous meaning cross-situational learning [19]. Centroid algorithms are the goto method for interactive learning [14], [15], [20].…”
Section: Learning Algorithmsmentioning
confidence: 99%
See 2 more Smart Citations
“…KNN is the only tested algorithm for continuous meaning cross-situational learning [19]. Centroid algorithms are the goto method for interactive learning [14], [15], [20].…”
Section: Learning Algorithmsmentioning
confidence: 99%
“…In interactive learning researchers often propose to use prototypes for the learner's lexicon [14], [15], [20] and to update these prototypes iteratively as new samples of word object mappings are collected by the learner. a) Representation: The learner stores prototypes p ∈ R 3 .…”
Section: B Prototype Estimation (Pe)mentioning
confidence: 99%
See 1 more Smart Citation
“…Consequently, referential uncertainty can occur in single object contexts This is different from WOM, where referential uncertainty is exclusively related to the number of objects in the context. c) Continuous Meaning Space Models (CMS): Few models address the learning of words related to representations in continuous vector spaces [7], [8]. The problem of referential uncertainty in continuous meaning spaces is large and depends chiefly on the number of objects in a learning context, the number of dimensions of meaning vectors and whether or not objects can refer to subspaces of the meaning space (color space etc).…”
Section: Introductionmentioning
confidence: 99%
“…Our group has done various experiments concerning the acquisition of words and concepts [7], [8] and the acquisition of grammar [9]. In these experiments there is either one robot acting as tutor and another one as learner or a human plays the role of tutor.…”
Section: Introductionmentioning
confidence: 99%