Relatively Lazy: Indoor-Outdoor Navigation Using Vision and GNSS

TL;DR

This paper presents a navigation method combining vision and GNSS that enables robots to follow paths seamlessly across indoor and outdoor environments without requiring map optimization.

Contribution

It introduces a lazy mapping approach that delays estimation until necessary, allowing immediate path following without absolute state estimation or map optimization.

Findings

Successful 3.5 km indoor-outdoor route repetition

Maintains smooth error signals despite sensor dropouts

Effective in varying lighting conditions

Abstract

Visual Teach and Repeat has shown relative navigation is a robust and efficient solution for autonomous vision-based path following in difficult environments. Adding additional absolute sensors such as Global Navigation Satellite Systems (GNSS) has the potential to expand the domain of Visual Teach and Repeat to environments where the ability to visually localize is not guaranteed. Our method of lazy mapping and delaying estimation until a path-tracking error is needed avoids the need to estimate absolute states. As a result, map optimization is not required and paths can be driven immediately after being taught. We validate our approach on a real robot through an experiment in a joint indoor-outdoor environment comprising 3.5km of autonomous route repeating across a variety of lighting conditions. We achieve smooth error signals throughout the runs despite large sections of dropout for each sensor.