Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
Computer Vision and Pattern Recognition
2020-05-19 v7 Artificial Intelligence
Computation and Language
Machine Learning
Abstract
We study the problem of jointly reasoning about language and vision through a navigation and spatial reasoning task. We introduce the Touchdown task and dataset, where an agent must first follow navigation instructions in a real-life visual urban environment, and then identify a location described in natural language to find a hidden object at the goal position. The data contains 9,326 examples of English instructions and spatial descriptions paired with demonstrations. Empirical analysis shows the data presents an open challenge to existing methods, and qualitative linguistic analysis shows that the data displays richer use of spatial reasoning compared to related resources.
Cite
@article{arxiv.1811.12354,
title = {Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments},
author = {Howard Chen and Alane Suhr and Dipendra Misra and Noah Snavely and Yoav Artzi},
journal= {arXiv preprint arXiv:1811.12354},
year = {2020}
}
Comments
arXiv admin note: text overlap with arXiv:1809.00786