Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding

TLDR

We introduce Room‑Across‑Room (RxR), a new Vision‑and‑Language Navigation dataset. RxR emphasizes language by correcting path biases, providing time‑aligned word‑pose pairs, and establishing baseline scores for monolingual, multilingual, and multitask settings. RxR is multilingual (English, Hindi, Telugu), larger than prior VLN datasets, yields baseline scores, demonstrates a model that learns from synchronized pose traces, and expands the frontier for embodied language agents in photorealistic environments.

Abstract

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 (Anderson et al., 2018). 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 photorealistic simulated environments.