Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments

11/29/2018 ∙ by Howard Chen, et al. ∙ 10

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 to a goal position, and then identify in the observed image a location described in natural language to find a hidden object. The data contains 9,326 examples of English instructions and spatial descriptions paired with demonstrations. We perform qualitative linguistic analysis, and show that the data displays richer use of spatial reasoning compared to related resources. Empirical analysis shows the data presents an open challenge to existing methods.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

page 14

page 15

page 16

page 17

page 18

page 19

page 20

Code Repositories

touchdown

Cornell Touchdown natural language navigation and spatial reasoning dataset.


view repo

ciff

Cornell Instruction Following Framework


view repo

VLN-Transformer

Implementation of "Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation"


view repo

touchdown

Cloned from https://github.com/lil-lab/touchdown


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.