ELBA: Learning by Asking for Embodied Visual Navigation and Task Completion
This addresses the challenge of active information acquisition for embodied AI agents, representing an incremental step beyond instruction-following agents.
The paper tackles the problem of enabling embodied agents to ask questions to resolve ambiguities in visual navigation and task completion, proposing the ELBA model which achieves improved task performance on the TEACh dataset compared to baseline models without question-answering capabilities.
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.