Conference paper Open Access
Cognitive Architecture for Joint Attentional Learning of word-object mapping with a Humanoid Robot
Jonas Gonzalez-BIllandon; Lukas Grasse; Alessandra Sciutti; Matthew Tata; Francesco Rea
Since infancy humans can learn from social context to associate words with their meanings, for example associating names with objects. The open-question is which computational framework could replicate the abilities of toddlers in developing language and its meaning in robots. We propose a computational framework in this paper to be implemented on a robotics platform to replicate the early learning process of humans for the specific task of word-object mapping.
Files
(365.8 kB)
| Name | Size | |
|---|---|---|
|
Cognitive_architecture_word_object_learning.pdf
md5:9ae431c2393906b2eef4aa0493e35cab |
365.8 kB | Download |
31
18
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 31 | 31 |
| Downloads | 18 | 18 |
| Data volume | 6.6 MB | 6.6 MB |
| Unique views | 25 | 25 |
| Unique downloads | 18 | 18 |
Indexed in
- Publication date:
- November 8, 2019
- DOI:
-
- Keyword(s):
- Self supervised learning Deep Learning Cognitive development
- Meeting:
- International Conference on Intelligent Robots and Systems (IROS), MACAU, 2019
- License (for files):
- Creative Commons Attribution 4.0 International