Mobile Robot Navigation Using Hand-Drawn Maps: A Vision Language Model Approach

TL;DR

This paper presents HAM-Nav, a novel vision language model-based system that enables mobile robots to navigate using hand-drawn maps despite inaccuracies, by integrating topological estimation and landmark inference, validated through extensive experiments.

Contribution

Introduces HAM-Nav, a new architecture leveraging pre-trained vision language models for robust robot navigation with hand-drawn maps, handling inaccuracies and diverse environments.

Findings

HAM-Nav achieves high success rates in simulated environments.

The system effectively infers missing landmarks in hand-drawn maps.

User studies confirm practical utility in real-world scenarios.

Abstract

Hand-drawn maps can be used to convey navigation instructions between humans and robots in a natural and efficient manner. However, these maps can often contain inaccuracies such as scale distortions and missing landmarks which present challenges for mobile robot navigation. This paper introduces a novel Hand-drawn Map Navigation (HAM-Nav) architecture that leverages pre-trained vision language models (VLMs) for robot navigation across diverse environments, hand-drawing styles, and robot embodiments, even in the presence of map inaccuracies. HAM-Nav integrates a unique Selective Visual Association Prompting approach for topological map-based position estimation and navigation planning as well as a Predictive Navigation Plan Parser to infer missing landmarks. Extensive experiments were conducted in photorealistic simulated environments, using both wheeled and legged robots, demonstrating the effectiveness of HAM-Nav in terms of navigation success rates and Success weighted by Path Length. Furthermore, a user study in real-world environments highlighted the practical utility of hand-drawn maps for robot navigation as well as successful navigation outcomes compared against a non-hand-drawn map approach.