Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View

TL;DR

This paper releases a large dataset of Street View panoramas and provides reference implementations for Touchdown tasks, facilitating research in language grounding and navigation in urban environments.

Contribution

It publicly releases 29,000 Street View panoramas and offers reference implementations for Touchdown's vision and language navigation and spatial description resolution tasks.

Findings

The released panoramas support Touchdown tasks effectively.

Model results are comparable to previous Touchdown studies.

The dataset enables further research in urban navigation and language grounding.

Abstract

The Touchdown dataset (Chen et al., 2019) provides instructions by human annotators for navigation through New York City streets and for resolving spatial descriptions at a given location. To enable the wider research community to work effectively with the Touchdown tasks, we are publicly releasing the 29k raw Street View panoramas needed for Touchdown. We follow the process used for the StreetLearn data release (Mirowski et al., 2019) to check panoramas for personally identifiable information and blur them as necessary. These have been added to the StreetLearn dataset and can be obtained via the same process as used previously for StreetLearn. We also provide a reference implementation for both of the Touchdown tasks: vision and language navigation (VLN) and spatial description resolution (SDR). We compare our model results to those given in Chen et al. (2019) and show that the panoramas we have added to StreetLearn fully support both Touchdown tasks and can be used effectively for further research and comparison.