Unsupervised, Bottom-up Category Discovery for Symbol Grounding with a Curious Robot

arXiv:2404.03092v1 Announce Type: new
Abstract: Towards addressing the Symbol Grounding Problem and motivated by early childhood language development, we leverage a robot which has been equipped with an approximate model of curiosity with particular focus on bottom-up building of unsupervised categories grounded in the physical world. That is, rather than starting with a top-down symbol (e.g., a word referring to an object) and providing meaning through the application of predetermined samples, the robot autonomously and gradually breaks up its exploration …

arxiv cs.cl cs.ro discovery robot type unsupervised