Explore until Confident: Efficient Exploration for Embodied Question Answering

arXiv:2403.15941v1 Announce Type: cross
Abstract: We consider the problem of Embodied Question Answering (EQA), which refers to settings where an embodied agent such as a robot needs to actively explore an environment to gather information until it is confident about the answer to a question. In this work, we leverage the strong semantic reasoning capabilities of large vision-language models (VLMs) to efficiently explore and answer such questions. However, there are two main challenges when using VLMs in EQA: they do …

arxiv cs.ai cs.cv cs.lg cs.ro embodied exploration explore question question answering type