AI Guide Dog: Egocentric Path Prediction on Smartphone

TL;DR

AI Guide Dog (AIGD) is a lightweight egocentric navigation system for visually impaired users that combines vision-based path prediction with GPS integration for indoor and outdoor environments, enabling goal-oriented and exploratory navigation.

Contribution

This work introduces a novel egocentric navigation system that handles both indoor and outdoor environments, integrating GPS and high-level directions for the first time.

Findings

Achieves real-time navigation on smartphones

Handles both goal-oriented and exploratory navigation

Establishes a new benchmark in assistive navigation systems

Abstract

This paper presents AI Guide Dog (AIGD), a lightweight egocentric (first-person) navigation system for visually impaired users, designed for real-time deployment on smartphones. AIGD employs a vision-only multi-label classification approach to predict directional commands, ensuring safe navigation across diverse environments. We introduce a novel technique for goal-based outdoor navigation by integrating GPS signals and high-level directions, while also handling uncertain multi-path predictions for destination-free indoor navigation. As the first navigation assistance system to handle both goal-oriented and exploratory navigation across indoor and outdoor settings, AIGD establishes a new benchmark in blind navigation. We present methods, datasets, evaluations, and deployment insights to encourage further innovations in assistive navigation systems.