NAVCON: A Cognitively Inspired and Linguistically Grounded Corpus for Vision and Language Navigation

TL;DR

NAVCON is a large, linguistically grounded corpus for vision and language navigation, introducing cognitively inspired concepts and annotations to improve understanding and instruction execution in navigation tasks.

Contribution

The paper presents NAVCON, a novel large-scale corpus with cognitively motivated navigation concepts and annotations, enhancing the understanding of natural language instructions in vision-language navigation.

Findings

NAVCON contains 236,316 concept annotations and 2.7 million aligned images.

Human evaluation confirms the quality of silver annotations.

Few-shot GPT-4o models perform well using NAVCON annotations.

Abstract

We present NAVCON, a large-scale annotated Vision-Language Navigation (VLN) corpus built on top of two popular datasets (R2R and RxR). The paper introduces four core, cognitively motivated and linguistically grounded, navigation concepts and an algorithm for generating large-scale silver annotations of naturally occurring linguistic realizations of these concepts in navigation instructions. We pair the annotated instructions with video clips of an agent acting on these instructions. NAVCON contains 236, 316 concept annotations for approximately 30, 0000 instructions and 2.7 million aligned images (from approximately 19, 000 instructions) showing what the agent sees when executing an instruction. To our knowledge, this is the first comprehensive resource of navigation concepts. We evaluated the quality of the silver annotations by conducting human evaluation studies on NAVCON samples. As further validation of the quality and usefulness of the resource, we trained a model for detecting navigation concepts and their linguistic realizations in unseen instructions. Additionally, we show that few-shot learning with GPT-4o performs well on this task using large-scale silver annotations of NAVCON.