ELBA: Learning by Asking for Embodied Visual Navigation and Task Completion

TL;DR

This paper introduces ELBA, a model enabling embodied agents to ask questions actively for better task completion in visual navigation, improving performance by dynamically resolving ambiguities in embodied environments.

Contribution

The paper presents a novel ELBA model that learns when and what questions to ask, integrating question-asking into embodied visual navigation and task completion.

Findings

ELBA outperforms baseline models on TEACh dataset.

Question-asking improves task success rates.

Dynamic information acquisition enhances embodied agent performance.

Abstract

The research community has shown increasing interest in designing intelligent embodied agents that can assist humans in accomplishing tasks. Although there have been significant advancements in related vision-language benchmarks, most prior work has focused on building agents that follow instructions rather than endowing agents the ability to ask questions to actively resolve ambiguities arising naturally in embodied environments. To address this gap, we propose an Embodied Learning-By-Asking (ELBA) model that learns when and what questions to ask to dynamically acquire additional information for completing the task. We evaluate ELBA on the TEACh vision-dialog navigation and task completion dataset. Experimental results show that the proposed method achieves improved task performance compared to baseline models without question-answering capabilities.