Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
This dataset expands research frontiers for embodied language agents in simulated environments, but it is incremental as it builds on existing VLN datasets.
The authors introduced Room-Across-Room (RxR), a new multilingual Vision-and-Language Navigation dataset that is larger and addresses biases in paths and language references, establishing baseline scores for various settings.
We introduce Room-Across-Room (RxR), a new Vision-and-Language Navigation (VLN) dataset. RxR is multilingual (English, Hindi, and Telugu) and larger (more paths and instructions) than other VLN datasets. It emphasizes the role of language in VLN by addressing known biases in paths and eliciting more references to visible entities. Furthermore, each word in an instruction is time-aligned to the virtual poses of instruction creators and validators. We establish baseline scores for monolingual and multilingual settings and multitask learning when including Room-to-Room annotations. We also provide results for a model that learns from synchronized pose traces by focusing only on portions of the panorama attended to in human demonstrations. The size, scope and detail of RxR dramatically expands the frontier for research on embodied language agents in simulated, photo-realistic environments.