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

Howard Chen, Alane Suhr, Dipendra Misra, Noah Snavely, Yoav Artzi
11/29/2018
cs.CVcs.AIcs.CL

Official code: lil-lab/touchdown (115 stars, CC-BY-4.0, last commit 2020-09-05).

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.

View on arXivView PDF

Code Implementations(1)

lil-lab/touchdownOfficial100%
CC-BY-4.0

Cornell Touchdown natural language navigation and spatial reasoning dataset.

11514PythonNov 21, 20186 years agoCC-BY-4.0
computer-visionmachine-learningnatural-language-processingvisual-language-grounding

Similar Papers

SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning

88% match2025

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

88% match1 repo122024

Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models

88% match1 repo612024

SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation

88% match1 repo92024

SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models

88% match1 repo842024

Reasoning under Vision: Understanding Visual-Spatial Cognition in Vision-Language Models for CAPTCHA

88% match2025

Cite this paper

@article{chen2018touchdown,
  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},
  year   = {2018},
  eprint = {1811.12354},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1811.12354}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1811.12354.svg)](https://codeofpaper.com/paper/1811.12354)

Discussion