A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility. (arXiv:2202.02312v3 [cs.CL] UPDATED)

Vision-language navigation (VLN), in which an agent follows language
instruction in a visual environment, has been studied under the premise that
the input command is fully feasible in the environment. Yet in practice, a
request may not be possible due to language ambiguity or environment changes.
To study VLN with unknown command feasibility, we introduce a new dataset
Mobile app Tasks with Iterative Feedback (MoTIF), where the goal is to complete
a natural language command in a mobile app. Mobile …

arxiv dataset interactive language navigation vision