DRAGON: A Dialogue-Based Robot for Assistive Navigation with Visual Language Grounding

TL;DR

DRAGON is a dialogue-based assistive robot that helps visually impaired users navigate and understand their environment through natural language communication and visual grounding, improving accessibility and user experience.

Contribution

This paper introduces DRAGON, a novel robot system combining dialogue and visual-language grounding for assistive navigation, which is a new approach in this domain.

Findings

Effective communication with users in indoor environments

Successful grounding of free-form descriptions to environmental landmarks

Positive user study results demonstrating improved navigation experience

Abstract

Persons with visual impairments (PwVI) have difficulties understanding and navigating spaces around them. Current wayfinding technologies either focus solely on navigation or provide limited communication about the environment. Motivated by recent advances in visual-language grounding and semantic navigation, we propose DRAGON, a guiding robot powered by a dialogue system and the ability to associate the environment with natural language. By understanding the commands from the user, DRAGON is able to guide the user to the desired landmarks on the map, describe the environment, and answer questions from visual observations. Through effective utilization of dialogue, the robot can ground the user's free-form descriptions to landmarks in the environment, and give the user semantic information through spoken language. We conduct a user study with blindfolded participants in an everyday indoor environment. Our results demonstrate that DRAGON is able to communicate with the user smoothly, provide a good guiding experience, and connect users with their surrounding environment in an intuitive manner. Videos and code are available at https://sites.google.com/view/dragon-wayfinding/home.