Keywords: embodied language learning, language grounding, language-supported robot learning
TL;DR: This article explores the current standing of research in embodied language learning from the perspective of language understanding research, summarizing opportunities and challenges, as well as identifying current research gaps.
Abstract: While large language and vision-language models showcase impressive capabilities, they face a notable limitation: the inability to connect language with the physical world. To bridge this gap, research has focused on embodied language learning, where the language learner is situated in the world, perceives it, and interacts with it. This article explores the current standing of research in embodied language learning, highlighting opportunities and discussing common challenges. Lastly, it identifies existing gaps from the perspective of language understanding research within the embodied world and suggests potential future directions.
Submission Type: Short Paper (4 Pages)
Archival Option: This is a non-archival submission
Flagged For Ethics Review: true
Submission Number: 4
Loading